diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.et.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a.et.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.et.jpg and /dev/null differ diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.pcm.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a.pcm.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.pcm.jpg and /dev/null differ diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.te.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a.te.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a.te.jpg and /dev/null differ diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.et.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.et.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.et.jpg and /dev/null differ diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.pcm.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.pcm.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.pcm.jpg and /dev/null differ diff --git a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.te.jpg b/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.te.jpg deleted file mode 100644 index 7112c185..00000000 Binary files a/translated_images/1200px-Girl_and_cat.89bd70951181e86a088f41f72415b6324ba4fe506148c6f18dca4e2ef3079ec3.te.jpg and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283.et.png b/translated_images/AND-OR-Tree.5592d2c70187f283.et.png deleted file mode 100644 index d57ef2af..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283.et.png and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283.pcm.png b/translated_images/AND-OR-Tree.5592d2c70187f283.pcm.png deleted file mode 100644 index da3830ed..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283.pcm.png and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283.te.png b/translated_images/AND-OR-Tree.5592d2c70187f283.te.png deleted file mode 100644 index edde19a8..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283.te.png and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.et.png b/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.et.png deleted file mode 100644 index d57ef2af..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.et.png and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.pcm.png b/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.pcm.png deleted file mode 100644 index da3830ed..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.pcm.png and /dev/null differ diff --git a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.te.png b/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.te.png deleted file mode 100644 index edde19a8..00000000 Binary files a/translated_images/AND-OR-Tree.5592d2c70187f283703c8e9c0d69d6a786eb370f4ace67f9a7aae5ada3d260b0.te.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb2215.et.png b/translated_images/ComputeGraph.463c9d8ebdcb2215.et.png deleted file mode 100644 index ea8c0fd9..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb2215.et.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb2215.pcm.png b/translated_images/ComputeGraph.463c9d8ebdcb2215.pcm.png deleted file mode 100644 index 88c2acaa..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb2215.pcm.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb2215.te.png b/translated_images/ComputeGraph.463c9d8ebdcb2215.te.png deleted file mode 100644 index 97f61cb2..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb2215.te.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.et.png b/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.et.png deleted file mode 100644 index ea8c0fd9..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.et.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.pcm.png b/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.pcm.png deleted file mode 100644 index 88c2acaa..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.pcm.png and /dev/null differ diff --git a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.te.png b/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.te.png deleted file mode 100644 index 97f61cb2..00000000 Binary files a/translated_images/ComputeGraph.463c9d8ebdcb22158e0563fcc50171dfbf3cb40443b597bc642b0f34ac23abbf.te.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de03507.et.png b/translated_images/ComputeGraphGrad.4626252c0de03507.et.png deleted file mode 100644 index e2fbde78..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de03507.et.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de03507.pcm.png b/translated_images/ComputeGraphGrad.4626252c0de03507.pcm.png deleted file mode 100644 index 3364f051..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de03507.pcm.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de03507.te.png b/translated_images/ComputeGraphGrad.4626252c0de03507.te.png deleted file mode 100644 index 68234d0f..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de03507.te.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.et.png b/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.et.png deleted file mode 100644 index e2fbde78..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.et.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.pcm.png b/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.pcm.png deleted file mode 100644 index 3364f051..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.pcm.png and /dev/null differ diff --git a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.te.png b/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.te.png deleted file mode 100644 index 68234d0f..00000000 Binary files a/translated_images/ComputeGraphGrad.4626252c0de035075e5cd2b7f71b776d5e3e8f64f2dc472b4420d3fdfaf53ba8.te.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d6.et.png b/translated_images/CoreferenceResolution.861924d6d384a7d6.et.png deleted file mode 100644 index efb5c668..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d6.et.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d6.pcm.png b/translated_images/CoreferenceResolution.861924d6d384a7d6.pcm.png deleted file mode 100644 index 2fab94de..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d6.pcm.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d6.te.png b/translated_images/CoreferenceResolution.861924d6d384a7d6.te.png deleted file mode 100644 index c8882c1d..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d6.te.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.et.png b/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.et.png deleted file mode 100644 index efb5c668..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.et.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.pcm.png b/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.pcm.png deleted file mode 100644 index 2fab94de..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.pcm.png and /dev/null differ diff --git a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.te.png b/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.te.png deleted file mode 100644 index c8882c1d..00000000 Binary files a/translated_images/CoreferenceResolution.861924d6d384a7d68d8d0039d06a71a151f18a796b8b1330239d3590bd4947eb.te.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.et.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.et.png deleted file mode 100644 index f8371feb..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.et.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.pcm.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.pcm.png deleted file mode 100644 index 4070373e..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.pcm.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.te.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.te.png deleted file mode 100644 index 0feab9d8..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3.te.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.et.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.et.png deleted file mode 100644 index f8371feb..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.et.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.pcm.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.pcm.png deleted file mode 100644 index 4070373e..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.pcm.png and /dev/null differ diff --git a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.te.png b/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.te.png deleted file mode 100644 index 0feab9d8..00000000 Binary files a/translated_images/Cross-Entropy-Loss.dc7ba633d2467ef3ae9ff8f06546ffcdff1347fa032b8e4b3d70b9e4ad0bf506.te.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.et.png b/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.et.png deleted file mode 100644 index 817ac42d..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.et.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.pcm.png b/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.pcm.png deleted file mode 100644 index 817ac42d..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.pcm.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.te.png b/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.te.png deleted file mode 100644 index 817ac42d..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c94d2b8e9337d8a006f2a7a90e067f3c34a8c6425ea905f490.te.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.et.png b/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.et.png deleted file mode 100644 index 2d43fa37..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.et.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.pcm.png b/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.pcm.png deleted file mode 100644 index 2d43fa37..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.pcm.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.te.png b/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.te.png deleted file mode 100644 index 2d43fa37..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbfb6ddc71819ae0ba025e10144c73ad0ce906933e5382d081d.te.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.et.png b/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.et.png deleted file mode 100644 index 8072fbe4..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.et.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.pcm.png b/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.pcm.png deleted file mode 100644 index 8072fbe4..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.pcm.png and /dev/null differ diff --git a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.te.png b/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.te.png deleted file mode 100644 index 8072fbe4..00000000 Binary files a/translated_images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d952ff424cc6533143559f9d97298020f64ebac91356cbb416.te.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.et.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.et.png deleted file mode 100644 index 52ec7f1b..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.et.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.pcm.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.pcm.png deleted file mode 100644 index d3f61383..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.pcm.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.te.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.te.png deleted file mode 100644 index 228f1a67..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5b.te.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.et.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.et.png deleted file mode 100644 index 52ec7f1b..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.et.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.pcm.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.pcm.png deleted file mode 100644 index d3f61383..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.pcm.png and /dev/null differ diff --git a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.te.png b/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.te.png deleted file mode 100644 index 228f1a67..00000000 Binary files a/translated_images/DIKW_Pyramid.94126f7d2bd8db5be71c6f1658b94bd3c85342e3cb827913b556b0414d358340.te.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.et.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.et.png deleted file mode 100644 index 8b190449..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.et.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.pcm.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.pcm.png deleted file mode 100644 index 48ab27ea..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.pcm.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.te.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.te.png deleted file mode 100644 index f2bffe18..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.te.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.et.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.et.png deleted file mode 100644 index 8b190449..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.et.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.pcm.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.pcm.png deleted file mode 100644 index 48ab27ea..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.pcm.png and /dev/null differ diff --git a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.te.png b/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.te.png deleted file mode 100644 index f2bffe18..00000000 Binary files a/translated_images/FeatureExtractionCNN.d9b456cbdae7cb643fde3032b81b2940e3cf8be842e29afac3f482725ba7f95c.te.png and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.et.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.et.jpg deleted file mode 100644 index 2ac07487..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.et.jpg and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.pcm.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.pcm.jpg deleted file mode 100644 index 3f17612f..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.pcm.jpg and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.te.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.te.jpg deleted file mode 100644 index a73d19c9..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.te.jpg and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.et.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.et.jpg deleted file mode 100644 index 2ac07487..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.et.jpg and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.pcm.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.pcm.jpg deleted file mode 100644 index 3f17612f..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.pcm.jpg and /dev/null differ diff --git a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.te.jpg b/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.te.jpg deleted file mode 100644 index a73d19c9..00000000 Binary files a/translated_images/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9fb32bab6ae07e40faa202be1935c0fbd8c2bc2600a87bcb1.te.jpg and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3.et.png b/translated_images/NetLogo-Main.32653711ec1a01b3.et.png deleted file mode 100644 index cb632dec..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3.et.png and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3.pcm.png b/translated_images/NetLogo-Main.32653711ec1a01b3.pcm.png deleted file mode 100644 index 3f23ae04..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3.pcm.png and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3.te.png b/translated_images/NetLogo-Main.32653711ec1a01b3.te.png deleted file mode 100644 index b4a5d228..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3.te.png and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.et.png b/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.et.png deleted file mode 100644 index cb632dec..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.et.png and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.pcm.png b/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.pcm.png deleted file mode 100644 index 3f23ae04..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.pcm.png and /dev/null differ diff --git a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.te.png b/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.te.png deleted file mode 100644 index b4a5d228..00000000 Binary files a/translated_images/NetLogo-Main.32653711ec1a01b3cab22ec0b148e64193d0b979b055285bef329d5e3d6958c5.te.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c05.et.png b/translated_images/NetLogo-ModelLib.efe023afb4763c05.et.png deleted file mode 100644 index e66a3c7a..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c05.et.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c05.pcm.png b/translated_images/NetLogo-ModelLib.efe023afb4763c05.pcm.png deleted file mode 100644 index 3a356610..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c05.pcm.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c05.te.png b/translated_images/NetLogo-ModelLib.efe023afb4763c05.te.png deleted file mode 100644 index 3f2e5a84..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c05.te.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.et.png b/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.et.png deleted file mode 100644 index e66a3c7a..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.et.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.pcm.png b/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.pcm.png deleted file mode 100644 index 3a356610..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.pcm.png and /dev/null differ diff --git a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.te.png b/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.te.png deleted file mode 100644 index 3f2e5a84..00000000 Binary files a/translated_images/NetLogo-ModelLib.efe023afb4763c059704a8ac0e2cd5e51889b117e8eac02aaa5334cfe1c52c13.te.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721.et.png b/translated_images/NeuroArch.4e17cdba5e445721.et.png deleted file mode 100644 index 81df41e9..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721.et.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721.pcm.png b/translated_images/NeuroArch.4e17cdba5e445721.pcm.png deleted file mode 100644 index f25bb683..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721.pcm.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721.te.png b/translated_images/NeuroArch.4e17cdba5e445721.te.png deleted file mode 100644 index 60d52188..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721.te.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.et.png b/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.et.png deleted file mode 100644 index 81df41e9..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.et.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.pcm.png b/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.pcm.png deleted file mode 100644 index f25bb683..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.pcm.png and /dev/null differ diff --git a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.te.png b/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.te.png deleted file mode 100644 index 60d52188..00000000 Binary files a/translated_images/NeuroArch.4e17cdba5e445721ad0a94a738c6f1178fc9c5f36486fb0f8fccfd61964d528c.te.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.et.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.et.png deleted file mode 100644 index 39e68622..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.et.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.pcm.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.pcm.png deleted file mode 100644 index 2516e3ce..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.pcm.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.te.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.te.png deleted file mode 100644 index 79890fee..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.te.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.et.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.et.png deleted file mode 100644 index 39e68622..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.et.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.pcm.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.pcm.png deleted file mode 100644 index 2516e3ce..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.pcm.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.te.png b/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.te.png deleted file mode 100644 index 79890fee..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecall.d2ef5b6081a0b094b5242ff6aa810ef25285f5a4e0efcc604c31708798fd51ee.te.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.et.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.et.png deleted file mode 100644 index 6f0c8e54..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.et.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.pcm.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.pcm.png deleted file mode 100644 index d67c18b8..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.pcm.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.te.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.te.png deleted file mode 100644 index 441c8756..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.te.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.et.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.et.png deleted file mode 100644 index 6f0c8e54..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.et.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.pcm.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.pcm.png deleted file mode 100644 index d67c18b8..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.pcm.png and /dev/null differ diff --git a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.te.png b/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.te.png deleted file mode 100644 index 441c8756..00000000 Binary files a/translated_images/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a6f0db4193ce61830ea03e505138410480fc16f9051694a40.te.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371.et.png b/translated_images/Overfitting.408ad91cd90b4371.et.png deleted file mode 100644 index 5ecef78e..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371.et.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371.pcm.png b/translated_images/Overfitting.408ad91cd90b4371.pcm.png deleted file mode 100644 index 0e1b239e..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371.pcm.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371.te.png b/translated_images/Overfitting.408ad91cd90b4371.te.png deleted file mode 100644 index b36b2797..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371.te.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.et.png b/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.et.png deleted file mode 100644 index 5ecef78e..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.et.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.pcm.png b/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.pcm.png deleted file mode 100644 index 0e1b239e..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.pcm.png and /dev/null differ diff --git a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.te.png b/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.te.png deleted file mode 100644 index b36b2797..00000000 Binary files a/translated_images/Overfitting.408ad91cd90b4371d0a81f4287e1409c359751adeb1ae450332af50e84f08c3e.te.png and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.et.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d.et.jpg deleted file mode 100644 index a240a200..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.et.jpg and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.pcm.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d.pcm.jpg deleted file mode 100644 index 3f9f150a..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.pcm.jpg and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.te.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d.te.jpg deleted file mode 100644 index e5e8837d..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d.te.jpg and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.et.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.et.jpg deleted file mode 100644 index a240a200..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.et.jpg and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.pcm.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.pcm.jpg deleted file mode 100644 index 3f9f150a..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.pcm.jpg and /dev/null differ diff --git a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.te.jpg b/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.te.jpg deleted file mode 100644 index e5e8837d..00000000 Binary files a/translated_images/Rosenblatt-wikipedia.294821b285ac796d2281a556fe3de9a7aa328e34cdd25f3ac9deefa0982ea2df.te.jpg and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.et.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.et.png deleted file mode 100644 index 3d017ca9..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.et.png and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.pcm.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.pcm.png deleted file mode 100644 index c3708fcd..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.pcm.png and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.te.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.te.png deleted file mode 100644 index dd82ecc6..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.te.png and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.et.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.et.png deleted file mode 100644 index 3d017ca9..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.et.png and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.pcm.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.pcm.png deleted file mode 100644 index c3708fcd..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.pcm.png and /dev/null differ diff --git a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.te.png b/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.te.png deleted file mode 100644 index dd82ecc6..00000000 Binary files a/translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be1b905373ed9c858102c054b16e4595c76ec3f7bba0feb549.te.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.et.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.et.png deleted file mode 100644 index 155f435c..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.et.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.pcm.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.pcm.png deleted file mode 100644 index 718d8667..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.te.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.te.png deleted file mode 100644 index e880ce7c..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.te.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.et.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.et.png deleted file mode 100644 index 155f435c..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.et.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.pcm.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.pcm.png deleted file mode 100644 index 718d8667..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.te.png b/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.te.png deleted file mode 100644 index e880ce7c..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683b9d36a613b364deb7454760cd39205623fc1e3938fa133c0.te.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.et.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.et.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.et.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.pcm.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.pcm.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.te.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.te.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.te.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.et.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.et.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.et.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.pcm.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.pcm.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.te.png b/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.te.png deleted file mode 100644 index 0e739ec7..00000000 Binary files a/translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a439077e1c32cc8afdf714e634fe24dc78dc5aa45fd2f560b0ed5.te.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.et.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.et.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.et.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.pcm.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.pcm.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.te.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.te.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.te.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.et.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.et.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.et.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.pcm.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.pcm.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.pcm.png and /dev/null differ diff --git a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.te.png b/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.te.png deleted file mode 100644 index c2daf0e1..00000000 Binary files a/translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d09dc96de938b9f95bde8a7e1c721f48f286a7795bf16d56c7.te.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9.et.png b/translated_images/aae.9d418a990fc75bf9.et.png deleted file mode 100644 index 362ffa90..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9.et.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9.pcm.png b/translated_images/aae.9d418a990fc75bf9.pcm.png deleted file mode 100644 index ccd356f1..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9.pcm.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9.te.png b/translated_images/aae.9d418a990fc75bf9.te.png deleted file mode 100644 index e3987922..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9.te.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.et.png b/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.et.png deleted file mode 100644 index 362ffa90..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.et.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.pcm.png b/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.pcm.png deleted file mode 100644 index ccd356f1..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.pcm.png and /dev/null differ diff --git a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.te.png b/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.te.png deleted file mode 100644 index e3987922..00000000 Binary files a/translated_images/aae.9d418a990fc75bf9204b701eb6998206fd1b986643cc4e9b899aabdd27504702.te.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce7764.et.png b/translated_images/activation-func.b4924007c7ce7764.et.png deleted file mode 100644 index 7daca0da..00000000 Binary files a/translated_images/activation-func.b4924007c7ce7764.et.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce7764.pcm.png b/translated_images/activation-func.b4924007c7ce7764.pcm.png deleted file mode 100644 index 20e4ef41..00000000 Binary files a/translated_images/activation-func.b4924007c7ce7764.pcm.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce7764.te.png b/translated_images/activation-func.b4924007c7ce7764.te.png deleted file mode 100644 index 8002f1fe..00000000 Binary files a/translated_images/activation-func.b4924007c7ce7764.te.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.et.png b/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.et.png deleted file mode 100644 index 7daca0da..00000000 Binary files a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.et.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.pcm.png b/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.pcm.png deleted file mode 100644 index 20e4ef41..00000000 Binary files a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.pcm.png and /dev/null differ diff --git a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.te.png b/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.te.png deleted file mode 100644 index 8002f1fe..00000000 Binary files a/translated_images/activation-func.b4924007c7ce77648d4b1dd3e81c689453204902c096c626735c7b53688cdc63.te.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89.et.png b/translated_images/adversarial-dog.d9fc7773b0142b89.et.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89.et.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89.pcm.png b/translated_images/adversarial-dog.d9fc7773b0142b89.pcm.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89.pcm.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89.te.png b/translated_images/adversarial-dog.d9fc7773b0142b89.te.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89.te.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.et.png b/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.et.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.et.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.pcm.png b/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.pcm.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.pcm.png and /dev/null differ diff --git a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.te.png b/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.te.png deleted file mode 100644 index 2da4f4e2..00000000 Binary files a/translated_images/adversarial-dog.d9fc7773b0142b89752539bfbf884118de845b3851c5162146ea0b8809fc820f.te.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76.et.png b/translated_images/ai-computervision.6506ebebac3fbf76.et.png deleted file mode 100644 index d72571a9..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76.et.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76.pcm.png b/translated_images/ai-computervision.6506ebebac3fbf76.pcm.png deleted file mode 100644 index b6596a42..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76.pcm.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76.te.png b/translated_images/ai-computervision.6506ebebac3fbf76.te.png deleted file mode 100644 index acfdabb8..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76.te.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.et.png b/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.et.png deleted file mode 100644 index d72571a9..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.et.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.pcm.png b/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.pcm.png deleted file mode 100644 index b6596a42..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.pcm.png and /dev/null differ diff --git a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.te.png b/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.te.png deleted file mode 100644 index acfdabb8..00000000 Binary files a/translated_images/ai-computervision.6506ebebac3fbf76cdb78989d7d3dfea87e88285c0feaade53aa7804a22b248f.te.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70.et.png b/translated_images/ai-for-beginners.b354ca904b22cd70.et.png deleted file mode 100644 index fcaea981..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70.et.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70.pcm.png b/translated_images/ai-for-beginners.b354ca904b22cd70.pcm.png deleted file mode 100644 index 021fd59b..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70.pcm.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70.te.png b/translated_images/ai-for-beginners.b354ca904b22cd70.te.png deleted file mode 100644 index 63d97911..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70.te.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.et.png b/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.et.png deleted file mode 100644 index fcaea981..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.et.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.pcm.png b/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.pcm.png deleted file mode 100644 index 021fd59b..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.pcm.png and /dev/null differ diff --git a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.te.png b/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.te.png deleted file mode 100644 index 63d97911..00000000 Binary files a/translated_images/ai-for-beginners.b354ca904b22cd70ef0d0df7b0c8633af55878f9aba882d9b9971d12badff175.te.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c.et.png b/translated_images/ai-intro.bf28d1ac4235881c.et.png deleted file mode 100644 index 406611fe..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c.et.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c.pcm.png b/translated_images/ai-intro.bf28d1ac4235881c.pcm.png deleted file mode 100644 index 1a312e64..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c.pcm.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c.te.png b/translated_images/ai-intro.bf28d1ac4235881c.te.png deleted file mode 100644 index aaa8b01d..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c.te.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.et.png b/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.et.png deleted file mode 100644 index 406611fe..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.et.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.pcm.png b/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.pcm.png deleted file mode 100644 index 1a312e64..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.pcm.png and /dev/null differ diff --git a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.te.png b/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.te.png deleted file mode 100644 index aaa8b01d..00000000 Binary files a/translated_images/ai-intro.bf28d1ac4235881c096f0ffdb320ba4102940eafcca4e9d7a55a03914361f8f3.te.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.et.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e83.et.png deleted file mode 100644 index f2feb55b..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.et.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.pcm.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e83.pcm.png deleted file mode 100644 index 5a91b1c4..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.pcm.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.te.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e83.te.png deleted file mode 100644 index 94a1012e..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e83.te.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.et.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.et.png deleted file mode 100644 index f2feb55b..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.et.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.pcm.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.pcm.png deleted file mode 100644 index 5a91b1c4..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.pcm.png and /dev/null differ diff --git a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.te.png b/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.te.png deleted file mode 100644 index 94a1012e..00000000 Binary files a/translated_images/ai-neuralnetworks.1c687ae40bc86e834f497844866a26d3e0886650a67a4bbe29442e2f157d3b18.te.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707cea.et.png b/translated_images/ai-nlp.b22dcb8ca4707cea.et.png deleted file mode 100644 index a882a9aa..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707cea.et.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707cea.pcm.png b/translated_images/ai-nlp.b22dcb8ca4707cea.pcm.png deleted file mode 100644 index 3b966153..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707cea.pcm.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707cea.te.png b/translated_images/ai-nlp.b22dcb8ca4707cea.te.png deleted file mode 100644 index 058202ca..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707cea.te.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.et.png b/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.et.png deleted file mode 100644 index a882a9aa..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.et.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.pcm.png b/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.pcm.png deleted file mode 100644 index 3b966153..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.pcm.png and /dev/null differ diff --git a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.te.png b/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.te.png deleted file mode 100644 index 058202ca..00000000 Binary files a/translated_images/ai-nlp.b22dcb8ca4707ceaee8576db1c5f4089c8cac2f454e9e03ea554f07fda4556b8.te.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500.et.png b/translated_images/ai-overview.0857791951d19500.et.png deleted file mode 100644 index c35e56d2..00000000 Binary files a/translated_images/ai-overview.0857791951d19500.et.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500.pcm.png b/translated_images/ai-overview.0857791951d19500.pcm.png deleted file mode 100644 index 061ee18d..00000000 Binary files a/translated_images/ai-overview.0857791951d19500.pcm.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500.te.png b/translated_images/ai-overview.0857791951d19500.te.png deleted file mode 100644 index 75f81f7a..00000000 Binary files a/translated_images/ai-overview.0857791951d19500.te.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.et.png b/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.et.png deleted file mode 100644 index c35e56d2..00000000 Binary files a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.et.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.pcm.png b/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.pcm.png deleted file mode 100644 index 061ee18d..00000000 Binary files a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.pcm.png and /dev/null differ diff --git a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.te.png b/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.te.png deleted file mode 100644 index 75f81f7a..00000000 Binary files a/translated_images/ai-overview.0857791951d19500d0ef8b803d77110c738dcafc52306e6d68724742cd4af167.te.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6.et.png b/translated_images/ai-symbolic.715a30cb610411a6.et.png deleted file mode 100644 index a84d8853..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6.et.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6.pcm.png b/translated_images/ai-symbolic.715a30cb610411a6.pcm.png deleted file mode 100644 index 0bf8c21d..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6.pcm.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6.te.png b/translated_images/ai-symbolic.715a30cb610411a6.te.png deleted file mode 100644 index 8e221020..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6.te.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.et.png b/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.et.png deleted file mode 100644 index a84d8853..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.et.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.pcm.png b/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.pcm.png deleted file mode 100644 index 0bf8c21d..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.pcm.png and /dev/null differ diff --git a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.te.png b/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.te.png deleted file mode 100644 index 8e221020..00000000 Binary files a/translated_images/ai-symbolic.715a30cb610411a6964d2e2f23f24364cb338a07cb4844c1f97084d366e586c3.te.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1c.et.png b/translated_images/arch-human.5d4d35f1bba3ab1c.et.png deleted file mode 100644 index 2f9ce1c7..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1c.et.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1c.pcm.png b/translated_images/arch-human.5d4d35f1bba3ab1c.pcm.png deleted file mode 100644 index 23e7f0d1..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1c.pcm.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1c.te.png b/translated_images/arch-human.5d4d35f1bba3ab1c.te.png deleted file mode 100644 index b633c76e..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1c.te.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.et.png b/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.et.png deleted file mode 100644 index 2f9ce1c7..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.et.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.pcm.png b/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.pcm.png deleted file mode 100644 index 23e7f0d1..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.pcm.png and /dev/null differ diff --git a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.te.png b/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.te.png deleted file mode 100644 index b633c76e..00000000 Binary files a/translated_images/arch-human.5d4d35f1bba3ab1cdfda96af2f10b89574eb31e9796d0e3011cd9beda1c35112.te.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8da.et.png b/translated_images/arch-kbs.3ec5c150b09fa8da.et.png deleted file mode 100644 index 1b2bc531..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8da.et.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8da.pcm.png b/translated_images/arch-kbs.3ec5c150b09fa8da.pcm.png deleted file mode 100644 index f109a072..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8da.pcm.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8da.te.png b/translated_images/arch-kbs.3ec5c150b09fa8da.te.png deleted file mode 100644 index 8b659fd1..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8da.te.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.et.png b/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.et.png deleted file mode 100644 index 1b2bc531..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.et.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.pcm.png b/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.pcm.png deleted file mode 100644 index f109a072..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.pcm.png and /dev/null differ diff --git a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.te.png b/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.te.png deleted file mode 100644 index 8b659fd1..00000000 Binary files a/translated_images/arch-kbs.3ec5c150b09fa8dadc2beb0931a4983c9e2b03913a89eebcc103b5bb841b0212.te.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f.et.png b/translated_images/artneuron.1a5daa88d20ebe6f.et.png deleted file mode 100644 index 62dc5b5c..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f.et.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f.pcm.png b/translated_images/artneuron.1a5daa88d20ebe6f.pcm.png deleted file mode 100644 index 111a4cfe..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f.pcm.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f.te.png b/translated_images/artneuron.1a5daa88d20ebe6f.te.png deleted file mode 100644 index edcca101..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f.te.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.et.png b/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.et.png deleted file mode 100644 index 62dc5b5c..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.et.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.pcm.png b/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.pcm.png deleted file mode 100644 index 111a4cfe..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.pcm.png and /dev/null differ diff --git a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.te.png b/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.te.png deleted file mode 100644 index edcca101..00000000 Binary files a/translated_images/artneuron.1a5daa88d20ebe6f5824ddb89fba0bdaaf49f67e8230c1afbec42909df1fc17e.te.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.et.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.et.png deleted file mode 100644 index 951d84b3..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.et.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.pcm.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.pcm.png deleted file mode 100644 index 0d6dba79..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.pcm.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.te.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.te.png deleted file mode 100644 index 15da1132..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ff.te.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.et.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.et.png deleted file mode 100644 index 951d84b3..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.et.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.pcm.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.pcm.png deleted file mode 100644 index 0d6dba79..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.pcm.png and /dev/null differ diff --git a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.te.png b/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.te.png deleted file mode 100644 index 15da1132..00000000 Binary files a/translated_images/ascii-character-map.18ed6aa7f3b0a7ffeb29db95be05a245b6a20712bb2c3a9963c1ec7e9df70358.te.png and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.et.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.et.jpg deleted file mode 100644 index 46633a44..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.et.jpg and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg deleted file mode 100644 index e3a1be0e..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.te.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.te.jpg deleted file mode 100644 index 359f750d..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb61.te.jpg and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.et.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.et.jpg deleted file mode 100644 index 46633a44..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.et.jpg and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.pcm.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.pcm.jpg deleted file mode 100644 index e3a1be0e..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.pcm.jpg and /dev/null differ diff --git a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.te.jpg b/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.te.jpg deleted file mode 100644 index 359f750d..00000000 Binary files a/translated_images/autoencoder_schema.5e6fc9ad98a5eb6197f3513cf3baf4dfbe1389a6ae74daebda64de9f1c99f142.te.jpg and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba9.et.png b/translated_images/bag-of-words-example.606fc1738f1d7ba9.et.png deleted file mode 100644 index 92c0b085..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba9.et.png and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba9.pcm.png b/translated_images/bag-of-words-example.606fc1738f1d7ba9.pcm.png deleted file mode 100644 index 1d673015..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba9.pcm.png and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba9.te.png b/translated_images/bag-of-words-example.606fc1738f1d7ba9.te.png deleted file mode 100644 index 63586dda..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba9.te.png and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.et.png b/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.et.png deleted file mode 100644 index 92c0b085..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.et.png and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.pcm.png b/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.pcm.png deleted file mode 100644 index 1d673015..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.pcm.png and /dev/null differ diff --git a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.te.png b/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.te.png deleted file mode 100644 index 63586dda..00000000 Binary files a/translated_images/bag-of-words-example.606fc1738f1d7ba98a9d693e3bcd706c6e83fa7bf8221e6e90d1a206d82f2ea4.te.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af.et.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af.et.png deleted file mode 100644 index ee22de9e..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af.et.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png deleted file mode 100644 index fe3004e1..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af.te.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af.te.png deleted file mode 100644 index a5b17a99..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af.te.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.et.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.et.png deleted file mode 100644 index ee22de9e..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.et.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.pcm.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.pcm.png deleted file mode 100644 index fe3004e1..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.pcm.png and /dev/null differ diff --git a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.te.png b/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.te.png deleted file mode 100644 index a5b17a99..00000000 Binary files a/translated_images/bahdanau-fig3.09ba2d37f202a6af11de6c82d2d197830ba5f4528d9ea430eb65fd3a75065973.te.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad275.et.png b/translated_images/bot-ner.4b09235dbb0ad275.et.png deleted file mode 100644 index cba632ce..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad275.et.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad275.pcm.png b/translated_images/bot-ner.4b09235dbb0ad275.pcm.png deleted file mode 100644 index ca6ebe8e..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad275.pcm.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad275.te.png b/translated_images/bot-ner.4b09235dbb0ad275.te.png deleted file mode 100644 index 661bd44d..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad275.te.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.et.png b/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.et.png deleted file mode 100644 index cba632ce..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.et.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.pcm.png b/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.pcm.png deleted file mode 100644 index ca6ebe8e..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.pcm.png and /dev/null differ diff --git a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.te.png b/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.te.png deleted file mode 100644 index 661bd44d..00000000 Binary files a/translated_images/bot-ner.4b09235dbb0ad2754ec1f54c8c797f902cbb0b45ac90b0cfc8287343cef8df2f.te.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d.et.png b/translated_images/bow.3811869cff59368d.et.png deleted file mode 100644 index c55ca672..00000000 Binary files a/translated_images/bow.3811869cff59368d.et.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d.pcm.png b/translated_images/bow.3811869cff59368d.pcm.png deleted file mode 100644 index ead1d89b..00000000 Binary files a/translated_images/bow.3811869cff59368d.pcm.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d.te.png b/translated_images/bow.3811869cff59368d.te.png deleted file mode 100644 index 27c6704d..00000000 Binary files a/translated_images/bow.3811869cff59368d.te.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.et.png b/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.et.png deleted file mode 100644 index c55ca672..00000000 Binary files a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.et.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.pcm.png b/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.pcm.png deleted file mode 100644 index ead1d89b..00000000 Binary files a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.pcm.png and /dev/null differ diff --git a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.te.png b/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.te.png deleted file mode 100644 index 27c6704d..00000000 Binary files a/translated_images/bow.3811869cff59368d951c7a765ed20ebeaf7d10680eb602ea7c5312fb22f7b7ad.te.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c7.et.png b/translated_images/braille-result.46530fea020b03c7.et.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c7.et.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c7.pcm.png b/translated_images/braille-result.46530fea020b03c7.pcm.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c7.pcm.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c7.te.png b/translated_images/braille-result.46530fea020b03c7.te.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c7.te.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.et.png b/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.et.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.et.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.pcm.png b/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.pcm.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.pcm.png and /dev/null differ diff --git a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.te.png b/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.te.png deleted file mode 100644 index 82fa8e43..00000000 Binary files a/translated_images/braille-result.46530fea020b03c76aac532d7d6eeef7f6fb35b55b1001cd21627907dabef3ed.te.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d5339.et.png b/translated_images/braille-symbols.0159185ab69d5339.et.png deleted file mode 100644 index c1a256ef..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d5339.et.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d5339.pcm.png b/translated_images/braille-symbols.0159185ab69d5339.pcm.png deleted file mode 100644 index 63c4a6c6..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d5339.pcm.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d5339.te.png b/translated_images/braille-symbols.0159185ab69d5339.te.png deleted file mode 100644 index f1f4508e..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d5339.te.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.et.png b/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.et.png deleted file mode 100644 index c1a256ef..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.et.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.pcm.png b/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.pcm.png deleted file mode 100644 index 63c4a6c6..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.pcm.png and /dev/null differ diff --git a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.te.png b/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.te.png deleted file mode 100644 index f1f4508e..00000000 Binary files a/translated_images/braille-symbols.0159185ab69d533909dc4d7d26a1971b51401c6a80eb3a5584f250ea880af88b.te.png and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd70.et.jpeg b/translated_images/braille.341962ff76b1bd70.et.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd70.et.jpeg and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd70.pcm.jpeg b/translated_images/braille.341962ff76b1bd70.pcm.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd70.pcm.jpeg and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd70.te.jpeg b/translated_images/braille.341962ff76b1bd70.te.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd70.te.jpeg and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.et.jpeg b/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.et.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.et.jpeg and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.pcm.jpeg b/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.pcm.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.pcm.jpeg and /dev/null differ diff --git a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.te.jpeg b/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.te.jpeg deleted file mode 100644 index 5d3ee5e4..00000000 Binary files a/translated_images/braille.341962ff76b1bd7044409371d3de09ced5028132aef97344ea4b7468c1208126.te.jpeg and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170.et.png b/translated_images/cartpole.f52a67f27e058170.et.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170.et.png and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170.pcm.png b/translated_images/cartpole.f52a67f27e058170.pcm.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170.pcm.png and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170.te.png b/translated_images/cartpole.f52a67f27e058170.te.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170.te.png and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.et.png b/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.et.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.et.png and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.pcm.png b/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.pcm.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.pcm.png and /dev/null differ diff --git a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.te.png b/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.te.png deleted file mode 100644 index 76b66c47..00000000 Binary files a/translated_images/cartpole.f52a67f27e058170c25efc1bca8375b60906570ea757fe8d7ef04ae8e53df29d.te.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.et.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f0.et.png deleted file mode 100644 index e4e841ec..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.et.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.pcm.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f0.pcm.png deleted file mode 100644 index 0c5cbb2f..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.pcm.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.te.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f0.te.png deleted file mode 100644 index d8bb8cef..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f0.te.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.et.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.et.png deleted file mode 100644 index e4e841ec..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.et.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.pcm.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.pcm.png deleted file mode 100644 index 0c5cbb2f..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.pcm.png and /dev/null differ diff --git a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.te.png b/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.te.png deleted file mode 100644 index d8bb8cef..00000000 Binary files a/translated_images/catsdogsdataset.a7aff8e6085fd3f062a882179ac5e5a9e652f82ca35c5f5a94f96f526da34498.te.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be.et.png b/translated_images/clip-arch.b3dbf20b4e8ed8be.et.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be.et.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be.pcm.png b/translated_images/clip-arch.b3dbf20b4e8ed8be.pcm.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be.pcm.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be.te.png b/translated_images/clip-arch.b3dbf20b4e8ed8be.te.png deleted file mode 100644 index 84d26a67..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be.te.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.et.png b/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.et.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.et.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.pcm.png b/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.pcm.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.pcm.png and /dev/null differ diff --git a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.te.png b/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.te.png deleted file mode 100644 index 84d26a67..00000000 Binary files a/translated_images/clip-arch.b3dbf20b4e8ed8be1c38e2bc6100fd3cc257c33cda4692b301be91f791b13ea7.te.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369.et.png b/translated_images/clip-class.3af42ef0b2b19369.et.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369.et.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369.pcm.png b/translated_images/clip-class.3af42ef0b2b19369.pcm.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369.pcm.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369.te.png b/translated_images/clip-class.3af42ef0b2b19369.te.png deleted file mode 100644 index 84d26a67..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369.te.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.et.png b/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.et.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.et.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.pcm.png b/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.pcm.png deleted file mode 100644 index fba8ec26..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.pcm.png and /dev/null differ diff --git a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.te.png b/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.te.png deleted file mode 100644 index 84d26a67..00000000 Binary files a/translated_images/clip-class.3af42ef0b2b19369a633df5f20ddf4f5a01d6c8ffa181e9d3a0572c19f919f72.te.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce.et.png b/translated_images/cnn-pyramid.85915455759ef0ce.et.png deleted file mode 100644 index 2eea9ffd..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce.et.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce.pcm.png b/translated_images/cnn-pyramid.85915455759ef0ce.pcm.png deleted file mode 100644 index a04eee6f..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce.pcm.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce.te.png b/translated_images/cnn-pyramid.85915455759ef0ce.te.png deleted file mode 100644 index e134c656..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce.te.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.et.png b/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.et.png deleted file mode 100644 index 2eea9ffd..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.et.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.pcm.png b/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.pcm.png deleted file mode 100644 index a04eee6f..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.pcm.png and /dev/null differ diff --git a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.te.png b/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.te.png deleted file mode 100644 index e134c656..00000000 Binary files a/translated_images/cnn-pyramid.85915455759ef0ce6a8cc9da2170492c85bfd9e1b61832650e2228e037039ec4.te.png and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb.et.jpg b/translated_images/coco-examples.71bc60380fa6cceb.et.jpg deleted file mode 100644 index ec58cab6..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb.et.jpg and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb.pcm.jpg b/translated_images/coco-examples.71bc60380fa6cceb.pcm.jpg deleted file mode 100644 index b1ce9d8d..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb.pcm.jpg and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb.te.jpg b/translated_images/coco-examples.71bc60380fa6cceb.te.jpg deleted file mode 100644 index 07274b5d..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb.te.jpg and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.et.jpg b/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.et.jpg deleted file mode 100644 index ec58cab6..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.et.jpg and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.pcm.jpg b/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.pcm.jpg deleted file mode 100644 index b1ce9d8d..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.pcm.jpg and /dev/null differ diff --git a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.te.jpg b/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.te.jpg deleted file mode 100644 index 07274b5d..00000000 Binary files a/translated_images/coco-examples.71bc60380fa6cceb7caad48bd09e35b6028caabd363aa04fee89c414e0870e86.te.jpg and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0.et.png b/translated_images/convolutionExample.634615d5ff7081e0.et.png deleted file mode 100644 index efda46cf..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0.et.png and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0.pcm.png b/translated_images/convolutionExample.634615d5ff7081e0.pcm.png deleted file mode 100644 index b32cd62c..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0.pcm.png and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0.te.png b/translated_images/convolutionExample.634615d5ff7081e0.te.png deleted file mode 100644 index cc4ea636..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0.te.png and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.et.png b/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.et.png deleted file mode 100644 index efda46cf..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.et.png and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.pcm.png b/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.pcm.png deleted file mode 100644 index b32cd62c..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.pcm.png and /dev/null differ diff --git a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.te.png b/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.te.png deleted file mode 100644 index cc4ea636..00000000 Binary files a/translated_images/convolutionExample.634615d5ff7081e0b73416b9e398f9eade32856616386fdc0cf412ce898cc192.te.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0.et.png b/translated_images/data.50b2a9d5484bdbf0.et.png deleted file mode 100644 index 57ff65b5..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0.et.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0.pcm.png b/translated_images/data.50b2a9d5484bdbf0.pcm.png deleted file mode 100644 index 2458437d..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0.pcm.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0.te.png b/translated_images/data.50b2a9d5484bdbf0.te.png deleted file mode 100644 index 6bdd6c84..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0.te.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.et.png b/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.et.png deleted file mode 100644 index 57ff65b5..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.et.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.pcm.png b/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.pcm.png deleted file mode 100644 index 2458437d..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.pcm.png and /dev/null differ diff --git a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.te.png b/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.te.png deleted file mode 100644 index 6bdd6c84..00000000 Binary files a/translated_images/data.50b2a9d5484bdbf0f52f5765b381cec9efe2bd296a98f007f90bedb6ac67f2a8.te.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5.et.png b/translated_images/dcgan_generator.b500988ec2bc8ba5.et.png deleted file mode 100644 index e6edd21f..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5.et.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5.pcm.png b/translated_images/dcgan_generator.b500988ec2bc8ba5.pcm.png deleted file mode 100644 index b1d27d59..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5.pcm.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5.te.png b/translated_images/dcgan_generator.b500988ec2bc8ba5.te.png deleted file mode 100644 index bc37519b..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5.te.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.et.png b/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.et.png deleted file mode 100644 index e6edd21f..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.et.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.pcm.png b/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.pcm.png deleted file mode 100644 index b1d27d59..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.pcm.png and /dev/null differ diff --git a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.te.png b/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.te.png deleted file mode 100644 index bc37519b..00000000 Binary files a/translated_images/dcgan_generator.b500988ec2bc8ba5cb38dae855fece348933171227c0536743b9c3b599f33f3d.te.png and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93.et.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93.et.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93.et.jpg and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93.pcm.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93.pcm.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93.pcm.jpg and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93.te.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93.te.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93.te.jpg and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.et.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.et.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.et.jpg and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.pcm.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.pcm.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.pcm.jpg and /dev/null differ diff --git a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.te.jpg b/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.te.jpg deleted file mode 100644 index 1ec22269..00000000 Binary files a/translated_images/dog-from-unsplash.426f9fbca2febc93f70499f8330874380bd6f2184b4fb986bac7220826d11a00.te.jpg and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f.et.png b/translated_images/dsh_age.d212a30d4e54fb5f.et.png deleted file mode 100644 index 566efa14..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f.et.png and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f.pcm.png b/translated_images/dsh_age.d212a30d4e54fb5f.pcm.png deleted file mode 100644 index 3a0eeaf9..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f.pcm.png and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f.te.png b/translated_images/dsh_age.d212a30d4e54fb5f.te.png deleted file mode 100644 index 3a0eeaf9..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f.te.png and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.et.png b/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.et.png deleted file mode 100644 index 566efa14..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.et.png and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.pcm.png b/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.pcm.png deleted file mode 100644 index 3a0eeaf9..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.pcm.png and /dev/null differ diff --git a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.te.png b/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.te.png deleted file mode 100644 index 3a0eeaf9..00000000 Binary files a/translated_images/dsh_age.d212a30d4e54fb5f68b94a624aad64bc086124bcbbec9561ae5bd5da661e22d8.te.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eee.et.png b/translated_images/embedding-classifier-example.b77f021a7ee67eee.et.png deleted file mode 100644 index b3938f57..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eee.et.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png b/translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png deleted file mode 100644 index 2a8c0eed..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eee.te.png b/translated_images/embedding-classifier-example.b77f021a7ee67eee.te.png deleted file mode 100644 index 062dd2f7..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eee.te.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.et.png b/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.et.png deleted file mode 100644 index b3938f57..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.et.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.pcm.png b/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.pcm.png deleted file mode 100644 index 2a8c0eed..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.pcm.png and /dev/null differ diff --git a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.te.png b/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.te.png deleted file mode 100644 index 062dd2f7..00000000 Binary files a/translated_images/embedding-classifier-example.b77f021a7ee67eeec8e68bfe11636c5b97d6eaa067515a129bfb1d0034b1ac5b.te.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567.et.png b/translated_images/encoder-decoder-attention.7a726296894fb567.et.png deleted file mode 100644 index 705a26cd..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567.et.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png b/translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png deleted file mode 100644 index 574aa442..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567.te.png b/translated_images/encoder-decoder-attention.7a726296894fb567.te.png deleted file mode 100644 index 0141f113..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567.te.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.et.png b/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.et.png deleted file mode 100644 index 705a26cd..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.et.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.pcm.png b/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.pcm.png deleted file mode 100644 index 574aa442..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.pcm.png and /dev/null differ diff --git a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.te.png b/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.te.png deleted file mode 100644 index 0141f113..00000000 Binary files a/translated_images/encoder-decoder-attention.7a726296894fb567aa2898c94b17b3289087f6705c11907df8301df9e5eeb3de.te.png and /dev/null differ diff --git a/translated_images/et/.co-op-translator.json b/translated_images/et/.co-op-translator.json new file mode 100644 index 00000000..cfa0dcf5 --- /dev/null +++ b/translated_images/et/.co-op-translator.json @@ -0,0 +1,722 @@ +{ + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T07:38:27+00:00", + "source_file": "images/favicon.png", + "language_code": "et" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T07:38:34+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "et" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T07:38:56+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "et" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T07:39:19+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "et" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T07:39:36+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "et" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T07:39:46+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "et" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:40:07+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "et" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:40:33+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "et" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:40:50+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "et" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:40:54+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "et" + }, + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:40:56+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", + "language_code": "et" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:40:59+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "et" + }, + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:41:03+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", + "language_code": "et" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:41:09+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "et" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:41:18+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "et" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:41:27+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "et" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:41:32+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "et" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:41:40+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "et" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:41:46+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "et" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:41:51+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "et" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:41:53+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "et" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:41:57+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "et" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:42:08+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "et" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:42:13+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "et" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:42:15+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "et" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:42:20+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "et" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:42:21+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "et" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "et" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "et" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:42:26+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "et" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:42:31+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "et" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:42:31+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "et" + }, + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:42:33+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "et" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:42:36+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "et" + }, + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:42:38+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", + "language_code": "et" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:42:39+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "et" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:42:41+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "et" + }, + "1200px-Girl_and_cat.89bd70951181e86a.webp": { + "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", + "translation_date": "2026-01-16T07:42:42+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", + "language_code": "et" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:42:47+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "et" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:42:53+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "et" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:42:59+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "et" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:43:04+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "et" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:43:07+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "et" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:43:11+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "et" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:43:17+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "et" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:43:21+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "et" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:43:27+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "et" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:43:34+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "et" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:43:39+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "et" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:43:49+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "et" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:44:01+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "et" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:44:09+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "et" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:44:22+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "et" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:44:25+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "et" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:44:29+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "et" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:44:36+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "et" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:44:41+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "et" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:44:49+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "et" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:44:54+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "et" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:44:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "et" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:44:58+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "et" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:45:11+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "et" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:45:34+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "et" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:45:51+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "et" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:45:52+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "et" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:45:55+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "et" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:46:02+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "et" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:46:13+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "et" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:46:14+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", + "language_code": "et" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:46:19+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "et" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:46:33+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "et" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:46:45+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "et" + }, + "AND-OR-Tree.5592d2c70187f283.webp": { + "original_hash": "2674b6cf8f768491c6b5a167f272a002", + "translation_date": "2026-01-16T07:47:04+00:00", + "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", + "language_code": "et" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:47:42+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "et" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:47:58+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "et" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:48:06+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "et" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:48:15+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "et" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:48:35+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "et" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:49:04+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "et" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:49:09+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "et" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:49:11+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "et" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:49:14+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", + "language_code": "et" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:49:19+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "et" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:49:26+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "et" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:49:30+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "et" + }, + "ComputeGraphGrad.4626252c0de03507.webp": { + "original_hash": "b0bf679245a237b1e7785ae2357a5376", + "translation_date": "2026-01-16T07:49:34+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", + "language_code": "et" + }, + "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { + "original_hash": "11dd0fd77a272755d0ef5db9f71217da", + "translation_date": "2026-01-16T07:49:41+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", + "language_code": "et" + }, + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:49:46+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", + "language_code": "et" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:49:50+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "et" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:49:53+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "et" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:49:55+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "et" + }, + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:49:58+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "et" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:02+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "et" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:50:08+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", + "language_code": "et" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:11+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "et" + }, + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:50:17+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "et" + }, + "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { + "original_hash": "dd063fda04db937ab7210064af9d6151", + "translation_date": "2026-01-16T07:50:19+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.png", + "language_code": "et" + }, + "DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp": { + "original_hash": "2cc9ab0daf8e1af7071fbc9eaf84970b", + "translation_date": "2026-01-16T07:50:20+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", + "language_code": "et" + }, + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:50:22+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "language_code": "et" + }, + "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { + "original_hash": "7064cd71a562523998203c756842c96d", + "translation_date": "2026-01-16T07:50:22+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", + "language_code": "et" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:50:24+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "et" + }, + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:50:28+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "language_code": "et" + }, + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:50:39+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "language_code": "et" + }, + "ascii-character-map.18ed6aa7f3b0a7ff.webp": { + "original_hash": "afc5ff2601be320926d89f1ad897eda8", + "translation_date": "2026-01-16T07:50:56+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", + "language_code": "et" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:51:04+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "et" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:51:09+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "et" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:51:20+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "et" + }, + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:51:32+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", + "language_code": "et" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:51:44+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "et" + }, + "bahdanau-fig3.09ba2d37f202a6af.webp": { + "original_hash": "b5cfbb9cad3b0d3fbdcc63dcd2ed514f", + "translation_date": "2026-01-16T07:51:56+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", + "language_code": "et" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:52:03+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "et" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:52:13+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "et" + }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:52:23+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "et" + }, + "bot-ner.4b09235dbb0ad275.webp": { + "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", + "translation_date": "2026-01-16T07:52:35+00:00", + "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", + "language_code": "et" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:52:48+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "et" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:52:52+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "et" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:52:58+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "et" + }, + "embedding-classifier-example.b77f021a7ee67eee.webp": { + "original_hash": "0c4233111f66d9c6925af5b97f9519a0", + "translation_date": "2026-01-16T07:53:02+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", + "language_code": "et" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:53:08+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "et" + }, + "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { + "original_hash": "6e976f26b9bb4c7a021187e834132123", + "translation_date": "2026-01-16T07:53:12+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", + "language_code": "et" + } +} \ No newline at end of file diff --git a/translated_images/et/1200px-Girl_and_cat.89bd70951181e86a.webp b/translated_images/et/1200px-Girl_and_cat.89bd70951181e86a.webp new file mode 100644 index 00000000..47042c75 Binary files /dev/null and b/translated_images/et/1200px-Girl_and_cat.89bd70951181e86a.webp differ diff --git a/translated_images/et/AND-OR-Tree.5592d2c70187f283.webp b/translated_images/et/AND-OR-Tree.5592d2c70187f283.webp new file mode 100644 index 00000000..89f28bfa Binary files /dev/null and b/translated_images/et/AND-OR-Tree.5592d2c70187f283.webp differ diff --git a/translated_images/et/ComputeGraph.463c9d8ebdcb2215.webp b/translated_images/et/ComputeGraph.463c9d8ebdcb2215.webp new file mode 100644 index 00000000..1e008392 Binary files /dev/null and b/translated_images/et/ComputeGraph.463c9d8ebdcb2215.webp differ diff --git a/translated_images/et/ComputeGraphGrad.4626252c0de03507.webp b/translated_images/et/ComputeGraphGrad.4626252c0de03507.webp new file mode 100644 index 00000000..e3d25d2e Binary files /dev/null and b/translated_images/et/ComputeGraphGrad.4626252c0de03507.webp differ diff --git a/translated_images/et/CoreferenceResolution.861924d6d384a7d6.webp b/translated_images/et/CoreferenceResolution.861924d6d384a7d6.webp new file mode 100644 index 00000000..e3b57abb Binary files /dev/null and b/translated_images/et/CoreferenceResolution.861924d6d384a7d6.webp differ diff --git a/translated_images/et/Cross-Entropy-Loss.dc7ba633d2467ef3.webp b/translated_images/et/Cross-Entropy-Loss.dc7ba633d2467ef3.webp new file mode 100644 index 00000000..1bb96511 Binary files /dev/null and b/translated_images/et/Cross-Entropy-Loss.dc7ba633d2467ef3.webp differ diff --git a/translated_images/et/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp b/translated_images/et/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp new file mode 100644 index 00000000..222db344 Binary files /dev/null and b/translated_images/et/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp differ diff --git a/translated_images/et/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp b/translated_images/et/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp new file mode 100644 index 00000000..f3b973c5 Binary files /dev/null and b/translated_images/et/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp differ diff --git a/translated_images/et/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp b/translated_images/et/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp new file mode 100644 index 00000000..b8f4286a Binary files /dev/null and b/translated_images/et/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp differ diff --git a/translated_images/et/DIKW_Pyramid.94126f7d2bd8db5b.webp b/translated_images/et/DIKW_Pyramid.94126f7d2bd8db5b.webp new file mode 100644 index 00000000..7da5db99 Binary files /dev/null and b/translated_images/et/DIKW_Pyramid.94126f7d2bd8db5b.webp differ diff --git a/translated_images/et/FeatureExtractionCNN.d9b456cbdae7cb64.webp b/translated_images/et/FeatureExtractionCNN.d9b456cbdae7cb64.webp new file mode 100644 index 00000000..57fc4ab1 Binary files /dev/null and b/translated_images/et/FeatureExtractionCNN.d9b456cbdae7cb64.webp differ diff --git a/translated_images/et/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp b/translated_images/et/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp new file mode 100644 index 00000000..46489154 Binary files /dev/null and b/translated_images/et/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp differ diff --git a/translated_images/et/NetLogo-Main.32653711ec1a01b3.webp b/translated_images/et/NetLogo-Main.32653711ec1a01b3.webp new file mode 100644 index 00000000..a36e3a84 Binary files /dev/null and b/translated_images/et/NetLogo-Main.32653711ec1a01b3.webp differ diff --git a/translated_images/et/NetLogo-ModelLib.efe023afb4763c05.webp b/translated_images/et/NetLogo-ModelLib.efe023afb4763c05.webp new file mode 100644 index 00000000..e1b120af Binary files /dev/null and b/translated_images/et/NetLogo-ModelLib.efe023afb4763c05.webp differ diff --git a/translated_images/et/NeuroArch.4e17cdba5e445721.webp b/translated_images/et/NeuroArch.4e17cdba5e445721.webp new file mode 100644 index 00000000..aa1d4e0d Binary files /dev/null and b/translated_images/et/NeuroArch.4e17cdba5e445721.webp differ diff --git a/translated_images/et/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp b/translated_images/et/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp new file mode 100644 index 00000000..d787966c Binary files /dev/null and b/translated_images/et/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp differ diff --git a/translated_images/et/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp b/translated_images/et/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp new file mode 100644 index 00000000..5c6ba9be Binary files /dev/null and b/translated_images/et/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp differ diff --git a/translated_images/et/Overfitting.408ad91cd90b4371.webp b/translated_images/et/Overfitting.408ad91cd90b4371.webp new file mode 100644 index 00000000..2f5ba05e Binary files /dev/null and b/translated_images/et/Overfitting.408ad91cd90b4371.webp differ diff --git a/translated_images/et/Rosenblatt-wikipedia.294821b285ac796d.webp b/translated_images/et/Rosenblatt-wikipedia.294821b285ac796d.webp new file mode 100644 index 00000000..ee733c23 Binary files /dev/null and b/translated_images/et/Rosenblatt-wikipedia.294821b285ac796d.webp differ diff --git a/translated_images/et/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp b/translated_images/et/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp new file mode 100644 index 00000000..b764b6d4 Binary files /dev/null and b/translated_images/et/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp differ diff --git a/translated_images/et/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp b/translated_images/et/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp new file mode 100644 index 00000000..ee032762 Binary files /dev/null and b/translated_images/et/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp differ diff --git a/translated_images/et/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp b/translated_images/et/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp new file mode 100644 index 00000000..52ce29a9 Binary files /dev/null and b/translated_images/et/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp differ diff --git a/translated_images/et/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp b/translated_images/et/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp new file mode 100644 index 00000000..fba04870 Binary files /dev/null and b/translated_images/et/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp differ diff --git a/translated_images/et/aae.9d418a990fc75bf9.webp b/translated_images/et/aae.9d418a990fc75bf9.webp new file mode 100644 index 00000000..23dc1215 Binary files /dev/null and b/translated_images/et/aae.9d418a990fc75bf9.webp differ diff --git a/translated_images/et/activation-func.b4924007c7ce7764.webp b/translated_images/et/activation-func.b4924007c7ce7764.webp new file mode 100644 index 00000000..8138807f Binary files /dev/null and b/translated_images/et/activation-func.b4924007c7ce7764.webp differ diff --git a/translated_images/et/adversarial-dog.d9fc7773b0142b89.webp b/translated_images/et/adversarial-dog.d9fc7773b0142b89.webp new file mode 100644 index 00000000..8816fc84 Binary files /dev/null and b/translated_images/et/adversarial-dog.d9fc7773b0142b89.webp differ diff --git a/translated_images/et/ai-computervision.6506ebebac3fbf76.webp b/translated_images/et/ai-computervision.6506ebebac3fbf76.webp new file mode 100644 index 00000000..e51cd01b Binary files /dev/null and b/translated_images/et/ai-computervision.6506ebebac3fbf76.webp differ diff --git a/translated_images/et/ai-for-beginners.b354ca904b22cd70.webp b/translated_images/et/ai-for-beginners.b354ca904b22cd70.webp new file mode 100644 index 00000000..8d14cf07 Binary files /dev/null and b/translated_images/et/ai-for-beginners.b354ca904b22cd70.webp differ diff --git a/translated_images/et/ai-intro.bf28d1ac4235881c.webp b/translated_images/et/ai-intro.bf28d1ac4235881c.webp new file mode 100644 index 00000000..2d2aad02 Binary files /dev/null and b/translated_images/et/ai-intro.bf28d1ac4235881c.webp differ diff --git a/translated_images/et/ai-neuralnetworks.1c687ae40bc86e83.webp b/translated_images/et/ai-neuralnetworks.1c687ae40bc86e83.webp new file mode 100644 index 00000000..79701030 Binary files /dev/null and b/translated_images/et/ai-neuralnetworks.1c687ae40bc86e83.webp differ diff --git a/translated_images/et/ai-nlp.b22dcb8ca4707cea.webp b/translated_images/et/ai-nlp.b22dcb8ca4707cea.webp new file mode 100644 index 00000000..cbd3bdd3 Binary files /dev/null and b/translated_images/et/ai-nlp.b22dcb8ca4707cea.webp differ diff --git a/translated_images/et/ai-overview.0857791951d19500.webp b/translated_images/et/ai-overview.0857791951d19500.webp new file mode 100644 index 00000000..610ff9f9 Binary files /dev/null and b/translated_images/et/ai-overview.0857791951d19500.webp differ diff --git a/translated_images/et/ai-symbolic.715a30cb610411a6.webp b/translated_images/et/ai-symbolic.715a30cb610411a6.webp new file mode 100644 index 00000000..e951c10b Binary files /dev/null and b/translated_images/et/ai-symbolic.715a30cb610411a6.webp differ diff --git a/translated_images/et/arch-human.5d4d35f1bba3ab1c.webp b/translated_images/et/arch-human.5d4d35f1bba3ab1c.webp new file mode 100644 index 00000000..d6563213 Binary files /dev/null and b/translated_images/et/arch-human.5d4d35f1bba3ab1c.webp differ diff --git a/translated_images/et/arch-kbs.3ec5c150b09fa8da.webp b/translated_images/et/arch-kbs.3ec5c150b09fa8da.webp new file mode 100644 index 00000000..acaf1a53 Binary files /dev/null and b/translated_images/et/arch-kbs.3ec5c150b09fa8da.webp differ diff --git a/translated_images/et/artneuron.1a5daa88d20ebe6f.webp b/translated_images/et/artneuron.1a5daa88d20ebe6f.webp new file mode 100644 index 00000000..9e300afa Binary files /dev/null and b/translated_images/et/artneuron.1a5daa88d20ebe6f.webp differ diff --git a/translated_images/et/ascii-character-map.18ed6aa7f3b0a7ff.webp b/translated_images/et/ascii-character-map.18ed6aa7f3b0a7ff.webp new file mode 100644 index 00000000..5c646bb1 Binary files /dev/null and b/translated_images/et/ascii-character-map.18ed6aa7f3b0a7ff.webp differ diff --git a/translated_images/et/autoencoder_schema.5e6fc9ad98a5eb61.webp b/translated_images/et/autoencoder_schema.5e6fc9ad98a5eb61.webp new file mode 100644 index 00000000..15d9d427 Binary files /dev/null and b/translated_images/et/autoencoder_schema.5e6fc9ad98a5eb61.webp differ diff --git a/translated_images/et/bag-of-words-example.606fc1738f1d7ba9.webp b/translated_images/et/bag-of-words-example.606fc1738f1d7ba9.webp new file mode 100644 index 00000000..b14b4115 Binary files /dev/null and b/translated_images/et/bag-of-words-example.606fc1738f1d7ba9.webp differ diff --git a/translated_images/et/bahdanau-fig3.09ba2d37f202a6af.webp b/translated_images/et/bahdanau-fig3.09ba2d37f202a6af.webp new file mode 100644 index 00000000..511a3413 Binary files /dev/null and b/translated_images/et/bahdanau-fig3.09ba2d37f202a6af.webp differ diff --git a/translated_images/et/bot-ner.4b09235dbb0ad275.webp b/translated_images/et/bot-ner.4b09235dbb0ad275.webp new file mode 100644 index 00000000..5b5e2762 Binary files /dev/null and b/translated_images/et/bot-ner.4b09235dbb0ad275.webp differ diff --git a/translated_images/et/bow.3811869cff59368d.webp b/translated_images/et/bow.3811869cff59368d.webp new file mode 100644 index 00000000..a5145253 Binary files /dev/null and b/translated_images/et/bow.3811869cff59368d.webp differ diff --git a/translated_images/et/braille-result.46530fea020b03c7.webp b/translated_images/et/braille-result.46530fea020b03c7.webp new file mode 100644 index 00000000..0235d8f6 Binary files /dev/null and b/translated_images/et/braille-result.46530fea020b03c7.webp differ diff --git a/translated_images/et/braille-symbols.0159185ab69d5339.webp b/translated_images/et/braille-symbols.0159185ab69d5339.webp new file mode 100644 index 00000000..aaa5691f Binary files /dev/null and b/translated_images/et/braille-symbols.0159185ab69d5339.webp differ diff --git a/translated_images/et/braille.341962ff76b1bd70.webp b/translated_images/et/braille.341962ff76b1bd70.webp new file mode 100644 index 00000000..6751696b Binary files /dev/null and b/translated_images/et/braille.341962ff76b1bd70.webp differ diff --git a/translated_images/et/cartpole.f52a67f27e058170.webp b/translated_images/et/cartpole.f52a67f27e058170.webp new file mode 100644 index 00000000..848d3ee7 Binary files /dev/null and b/translated_images/et/cartpole.f52a67f27e058170.webp differ diff --git a/translated_images/et/catsdogsdataset.a7aff8e6085fd3f0.webp b/translated_images/et/catsdogsdataset.a7aff8e6085fd3f0.webp new file mode 100644 index 00000000..76e98dbf Binary files /dev/null and b/translated_images/et/catsdogsdataset.a7aff8e6085fd3f0.webp differ diff --git a/translated_images/et/clip-arch.b3dbf20b4e8ed8be.webp b/translated_images/et/clip-arch.b3dbf20b4e8ed8be.webp new file mode 100644 index 00000000..a3ec7e55 Binary files /dev/null and b/translated_images/et/clip-arch.b3dbf20b4e8ed8be.webp differ diff --git a/translated_images/et/clip-class.3af42ef0b2b19369.webp b/translated_images/et/clip-class.3af42ef0b2b19369.webp new file mode 100644 index 00000000..46293f8c Binary files /dev/null and b/translated_images/et/clip-class.3af42ef0b2b19369.webp differ diff --git a/translated_images/et/cnn-pyramid.85915455759ef0ce.webp b/translated_images/et/cnn-pyramid.85915455759ef0ce.webp new file mode 100644 index 00000000..070ff508 Binary files /dev/null and b/translated_images/et/cnn-pyramid.85915455759ef0ce.webp differ diff --git a/translated_images/et/coco-examples.71bc60380fa6cceb.webp b/translated_images/et/coco-examples.71bc60380fa6cceb.webp new file mode 100644 index 00000000..5ef1e9da Binary files /dev/null and b/translated_images/et/coco-examples.71bc60380fa6cceb.webp differ diff --git a/translated_images/et/convolutionExample.634615d5ff7081e0.webp b/translated_images/et/convolutionExample.634615d5ff7081e0.webp new file mode 100644 index 00000000..571cbb9c Binary files /dev/null and b/translated_images/et/convolutionExample.634615d5ff7081e0.webp differ diff --git a/translated_images/et/data.50b2a9d5484bdbf0.webp b/translated_images/et/data.50b2a9d5484bdbf0.webp new file mode 100644 index 00000000..a0f47738 Binary files /dev/null and b/translated_images/et/data.50b2a9d5484bdbf0.webp differ diff --git a/translated_images/et/dcgan_generator.b500988ec2bc8ba5.webp b/translated_images/et/dcgan_generator.b500988ec2bc8ba5.webp new file mode 100644 index 00000000..304ad717 Binary files /dev/null and b/translated_images/et/dcgan_generator.b500988ec2bc8ba5.webp differ diff --git a/translated_images/et/dog-from-unsplash.426f9fbca2febc93.webp b/translated_images/et/dog-from-unsplash.426f9fbca2febc93.webp new file mode 100644 index 00000000..2d2fef68 Binary files /dev/null and b/translated_images/et/dog-from-unsplash.426f9fbca2febc93.webp differ diff --git a/translated_images/et/dsh_age.d212a30d4e54fb5f.webp b/translated_images/et/dsh_age.d212a30d4e54fb5f.webp new file mode 100644 index 00000000..98793010 Binary files /dev/null and b/translated_images/et/dsh_age.d212a30d4e54fb5f.webp differ diff --git a/translated_images/et/embedding-classifier-example.b77f021a7ee67eee.webp b/translated_images/et/embedding-classifier-example.b77f021a7ee67eee.webp new file mode 100644 index 00000000..08f49f73 Binary files /dev/null and b/translated_images/et/embedding-classifier-example.b77f021a7ee67eee.webp differ diff --git a/translated_images/et/encoder-decoder-attention.7a726296894fb567.webp b/translated_images/et/encoder-decoder-attention.7a726296894fb567.webp new file mode 100644 index 00000000..721d1dd4 Binary files /dev/null and b/translated_images/et/encoder-decoder-attention.7a726296894fb567.webp differ diff --git a/translated_images/et/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp b/translated_images/et/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp new file mode 100644 index 00000000..6b60716f Binary files /dev/null and b/translated_images/et/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp differ diff --git a/translated_images/et/f-rcnn.3cda6d9bb4188875.webp b/translated_images/et/f-rcnn.3cda6d9bb4188875.webp new file mode 100644 index 00000000..3ece6a42 Binary files /dev/null and b/translated_images/et/f-rcnn.3cda6d9bb4188875.webp differ diff --git a/translated_images/et/faster-rcnn.8d46c099b87ef30a.webp b/translated_images/et/faster-rcnn.8d46c099b87ef30a.webp new file mode 100644 index 00000000..9c09b318 Binary files /dev/null and b/translated_images/et/faster-rcnn.8d46c099b87ef30a.webp differ diff --git a/translated_images/et/favicon.37b561214b36d454.webp b/translated_images/et/favicon.37b561214b36d454.webp new file mode 100644 index 00000000..48a53960 Binary files /dev/null and b/translated_images/et/favicon.37b561214b36d454.webp differ diff --git a/translated_images/et/features.6291f9c7ba3a0b95.webp b/translated_images/et/features.6291f9c7ba3a0b95.webp new file mode 100644 index 00000000..03679af2 Binary files /dev/null and b/translated_images/et/features.6291f9c7ba3a0b95.webp differ diff --git a/translated_images/et/filter-horiz.59b80ed4feb946ef.webp b/translated_images/et/filter-horiz.59b80ed4feb946ef.webp new file mode 100644 index 00000000..1d82c28d Binary files /dev/null and b/translated_images/et/filter-horiz.59b80ed4feb946ef.webp differ diff --git a/translated_images/et/filter-vert.b7148390ca0bc356.webp b/translated_images/et/filter-vert.b7148390ca0bc356.webp new file mode 100644 index 00000000..666449c7 Binary files /dev/null and b/translated_images/et/filter-vert.b7148390ca0bc356.webp differ diff --git a/translated_images/et/frame-difference.706f805491a0883c.webp b/translated_images/et/frame-difference.706f805491a0883c.webp new file mode 100644 index 00000000..6a1b8343 Binary files /dev/null and b/translated_images/et/frame-difference.706f805491a0883c.webp differ diff --git a/translated_images/et/gan_arch_detail.46b95fd366f8e543.webp b/translated_images/et/gan_arch_detail.46b95fd366f8e543.webp new file mode 100644 index 00000000..001a53bf Binary files /dev/null and b/translated_images/et/gan_arch_detail.46b95fd366f8e543.webp differ diff --git a/translated_images/et/gan_architecture.8f3a5ab62b8d5d69.webp b/translated_images/et/gan_architecture.8f3a5ab62b8d5d69.webp new file mode 100644 index 00000000..574464f5 Binary files /dev/null and b/translated_images/et/gan_architecture.8f3a5ab62b8d5d69.webp differ diff --git a/translated_images/et/history-of-ai.7e83efa70b537f5a.webp b/translated_images/et/history-of-ai.7e83efa70b537f5a.webp new file mode 100644 index 00000000..3c87f6e1 Binary files /dev/null and b/translated_images/et/history-of-ai.7e83efa70b537f5a.webp differ diff --git a/translated_images/et/ideal-cat-loop.999fbb8ff306e044.webp b/translated_images/et/ideal-cat-loop.999fbb8ff306e044.webp new file mode 100644 index 00000000..24beaa63 Binary files /dev/null and b/translated_images/et/ideal-cat-loop.999fbb8ff306e044.webp differ diff --git a/translated_images/et/ideal-cat.203dd4597643d6b0.webp b/translated_images/et/ideal-cat.203dd4597643d6b0.webp new file mode 100644 index 00000000..a8d167b1 Binary files /dev/null and b/translated_images/et/ideal-cat.203dd4597643d6b0.webp differ diff --git a/translated_images/et/ideal-zebra.7f70e8b54ee15a7a.webp b/translated_images/et/ideal-zebra.7f70e8b54ee15a7a.webp new file mode 100644 index 00000000..be349483 Binary files /dev/null and b/translated_images/et/ideal-zebra.7f70e8b54ee15a7a.webp differ diff --git a/translated_images/et/image.896e8254a2c60d45.webp b/translated_images/et/image.896e8254a2c60d45.webp new file mode 100644 index 00000000..d2b9d3ce Binary files /dev/null and b/translated_images/et/image.896e8254a2c60d45.webp differ diff --git a/translated_images/et/inception.a6605b85bcbc6f52.webp b/translated_images/et/inception.a6605b85bcbc6f52.webp new file mode 100644 index 00000000..f45e0f2e Binary files /dev/null and b/translated_images/et/inception.a6605b85bcbc6f52.webp differ diff --git a/translated_images/et/instance_vs_semantic.eee9812bebf8cd45.webp b/translated_images/et/instance_vs_semantic.eee9812bebf8cd45.webp new file mode 100644 index 00000000..58588ab7 Binary files /dev/null and b/translated_images/et/instance_vs_semantic.eee9812bebf8cd45.webp differ diff --git a/translated_images/et/iou_equation.9a4751d40fff4e11.webp b/translated_images/et/iou_equation.9a4751d40fff4e11.webp new file mode 100644 index 00000000..abe730f2 Binary files /dev/null and b/translated_images/et/iou_equation.9a4751d40fff4e11.webp differ diff --git a/translated_images/et/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp b/translated_images/et/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp new file mode 100644 index 00000000..dbd738c7 Binary files /dev/null and b/translated_images/et/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp differ diff --git a/translated_images/et/knowledge-spectrum.b60df631852c0217.webp b/translated_images/et/knowledge-spectrum.b60df631852c0217.webp new file mode 100644 index 00000000..11ea4340 Binary files /dev/null and b/translated_images/et/knowledge-spectrum.b60df631852c0217.webp differ diff --git a/translated_images/et/lmfilters.ea9e4868a82cf74c.webp b/translated_images/et/lmfilters.ea9e4868a82cf74c.webp new file mode 100644 index 00000000..73254d4b Binary files /dev/null and b/translated_images/et/lmfilters.ea9e4868a82cf74c.webp differ diff --git a/translated_images/et/ml-for-beginners.9e4fed176fd5817d.webp b/translated_images/et/ml-for-beginners.9e4fed176fd5817d.webp new file mode 100644 index 00000000..7bff99c0 Binary files /dev/null and b/translated_images/et/ml-for-beginners.9e4fed176fd5817d.webp differ diff --git a/translated_images/et/mountaincar.f7b7a7f6d4f9933b.webp b/translated_images/et/mountaincar.f7b7a7f6d4f9933b.webp new file mode 100644 index 00000000..93bf6a97 Binary files /dev/null and b/translated_images/et/mountaincar.f7b7a7f6d4f9933b.webp differ diff --git a/translated_images/et/multi-layer-lstm.dd975e29bb2a59fe.webp b/translated_images/et/multi-layer-lstm.dd975e29bb2a59fe.webp new file mode 100644 index 00000000..7390e46e Binary files /dev/null and b/translated_images/et/multi-layer-lstm.dd975e29bb2a59fe.webp differ diff --git a/translated_images/et/naive-detection.e7f1ba220ccd08c6.webp b/translated_images/et/naive-detection.e7f1ba220ccd08c6.webp new file mode 100644 index 00000000..6bf3e9da Binary files /dev/null and b/translated_images/et/naive-detection.e7f1ba220ccd08c6.webp differ diff --git a/translated_images/et/navi.2f20b727910110ea.webp b/translated_images/et/navi.2f20b727910110ea.webp new file mode 100644 index 00000000..e9254c25 Binary files /dev/null and b/translated_images/et/navi.2f20b727910110ea.webp differ diff --git a/translated_images/et/netout.1eb15eb76fd76731.webp b/translated_images/et/netout.1eb15eb76fd76731.webp new file mode 100644 index 00000000..3206efc4 Binary files /dev/null and b/translated_images/et/netout.1eb15eb76fd76731.webp differ diff --git a/translated_images/et/offset-sequence-representation.eb73fcefb29b46ee.webp b/translated_images/et/offset-sequence-representation.eb73fcefb29b46ee.webp new file mode 100644 index 00000000..b9553824 Binary files /dev/null and b/translated_images/et/offset-sequence-representation.eb73fcefb29b46ee.webp differ diff --git a/translated_images/et/optical.1f4a94464579a83a.webp b/translated_images/et/optical.1f4a94464579a83a.webp new file mode 100644 index 00000000..c37dddad Binary files /dev/null and b/translated_images/et/optical.1f4a94464579a83a.webp differ diff --git a/translated_images/et/original-dog.8f68a67d2fe0911f.webp b/translated_images/et/original-dog.8f68a67d2fe0911f.webp new file mode 100644 index 00000000..2a002703 Binary files /dev/null and b/translated_images/et/original-dog.8f68a67d2fe0911f.webp differ diff --git a/translated_images/et/overfit.a0bd57f717c15769.webp b/translated_images/et/overfit.a0bd57f717c15769.webp new file mode 100644 index 00000000..8e30e2ed Binary files /dev/null and b/translated_images/et/overfit.a0bd57f717c15769.webp differ diff --git a/translated_images/et/overfit1.f24b71c6f652e59e.webp b/translated_images/et/overfit1.f24b71c6f652e59e.webp new file mode 100644 index 00000000..de604b48 Binary files /dev/null and b/translated_images/et/overfit1.f24b71c6f652e59e.webp differ diff --git a/translated_images/et/overfit2.131f5800ae10ca5e.webp b/translated_images/et/overfit2.131f5800ae10ca5e.webp new file mode 100644 index 00000000..8dd690b9 Binary files /dev/null and b/translated_images/et/overfit2.131f5800ae10ca5e.webp differ diff --git a/translated_images/et/palm-movement.341495f0e9c47da3.webp b/translated_images/et/palm-movement.341495f0e9c47da3.webp new file mode 100644 index 00000000..0071936c Binary files /dev/null and b/translated_images/et/palm-movement.341495f0e9c47da3.webp differ diff --git a/translated_images/et/photo-cat.8c8e8fb760ffe457.webp b/translated_images/et/photo-cat.8c8e8fb760ffe457.webp new file mode 100644 index 00000000..2998a349 Binary files /dev/null and b/translated_images/et/photo-cat.8c8e8fb760ffe457.webp differ diff --git a/translated_images/et/pos-embedding.e41ce9b6cf6078af.webp b/translated_images/et/pos-embedding.e41ce9b6cf6078af.webp new file mode 100644 index 00000000..6b3b4077 Binary files /dev/null and b/translated_images/et/pos-embedding.e41ce9b6cf6078af.webp differ diff --git a/translated_images/et/protege.274177ceeac13b38.webp b/translated_images/et/protege.274177ceeac13b38.webp new file mode 100644 index 00000000..3d194250 Binary files /dev/null and b/translated_images/et/protege.274177ceeac13b38.webp differ diff --git a/translated_images/et/r-fcn.13eb88158b99a3da.webp b/translated_images/et/r-fcn.13eb88158b99a3da.webp new file mode 100644 index 00000000..985934f4 Binary files /dev/null and b/translated_images/et/r-fcn.13eb88158b99a3da.webp differ diff --git a/translated_images/et/rcnn1.cae407020dfb1d1f.webp b/translated_images/et/rcnn1.cae407020dfb1d1f.webp new file mode 100644 index 00000000..1c949129 Binary files /dev/null and b/translated_images/et/rcnn1.cae407020dfb1d1f.webp differ diff --git a/translated_images/et/rcnn2.2d9530bb83516484.webp b/translated_images/et/rcnn2.2d9530bb83516484.webp new file mode 100644 index 00000000..e9fa7fa9 Binary files /dev/null and b/translated_images/et/rcnn2.2d9530bb83516484.webp differ diff --git a/translated_images/et/resnet-block.aba4ccbcc0944434.webp b/translated_images/et/resnet-block.aba4ccbcc0944434.webp new file mode 100644 index 00000000..c7d9445b Binary files /dev/null and b/translated_images/et/resnet-block.aba4ccbcc0944434.webp differ diff --git a/translated_images/et/rnn-anatomy.79ee3f3920b3294b.webp b/translated_images/et/rnn-anatomy.79ee3f3920b3294b.webp new file mode 100644 index 00000000..5c5a3547 Binary files /dev/null and b/translated_images/et/rnn-anatomy.79ee3f3920b3294b.webp differ diff --git a/translated_images/et/rnn-generate-inf.5168dc65e0370eea.webp b/translated_images/et/rnn-generate-inf.5168dc65e0370eea.webp new file mode 100644 index 00000000..191d8694 Binary files /dev/null and b/translated_images/et/rnn-generate-inf.5168dc65e0370eea.webp differ diff --git a/translated_images/et/rnn-generate.56c54afb52f9781d.webp b/translated_images/et/rnn-generate.56c54afb52f9781d.webp new file mode 100644 index 00000000..570917d9 Binary files /dev/null and b/translated_images/et/rnn-generate.56c54afb52f9781d.webp differ diff --git a/translated_images/et/rnn.27f5c29c53d727b5.webp b/translated_images/et/rnn.27f5c29c53d727b5.webp new file mode 100644 index 00000000..686f4500 Binary files /dev/null and b/translated_images/et/rnn.27f5c29c53d727b5.webp differ diff --git a/translated_images/et/segm.92442f2cb42ff4fa.webp b/translated_images/et/segm.92442f2cb42ff4fa.webp new file mode 100644 index 00000000..51d97747 Binary files /dev/null and b/translated_images/et/segm.92442f2cb42ff4fa.webp differ diff --git a/translated_images/et/segnet.87377542aa5a8b76.webp b/translated_images/et/segnet.87377542aa5a8b76.webp new file mode 100644 index 00000000..bdd47924 Binary files /dev/null and b/translated_images/et/segnet.87377542aa5a8b76.webp differ diff --git a/translated_images/et/style.5293e85e077ab22c.webp b/translated_images/et/style.5293e85e077ab22c.webp new file mode 100644 index 00000000..39af2a0e Binary files /dev/null and b/translated_images/et/style.5293e85e077ab22c.webp differ diff --git a/translated_images/et/synapse-wikipedia.ed20a9e4726ea1c6.webp b/translated_images/et/synapse-wikipedia.ed20a9e4726ea1c6.webp new file mode 100644 index 00000000..ae75aeac Binary files /dev/null and b/translated_images/et/synapse-wikipedia.ed20a9e4726ea1c6.webp differ diff --git a/translated_images/et/transformer-layer.905e14747ca4e7d5.webp b/translated_images/et/transformer-layer.905e14747ca4e7d5.webp new file mode 100644 index 00000000..e6636c31 Binary files /dev/null and b/translated_images/et/transformer-layer.905e14747ca4e7d5.webp differ diff --git a/translated_images/et/triplet-complex.32094972c7b4441b.webp b/translated_images/et/triplet-complex.32094972c7b4441b.webp new file mode 100644 index 00000000..bdebd9ba Binary files /dev/null and b/translated_images/et/triplet-complex.32094972c7b4441b.webp differ diff --git a/translated_images/et/triplet.4b9b332587593298.webp b/translated_images/et/triplet.4b9b332587593298.webp new file mode 100644 index 00000000..fe9d21b1 Binary files /dev/null and b/translated_images/et/triplet.4b9b332587593298.webp differ diff --git a/translated_images/et/turing-test-evol.4184696701293ead.webp b/translated_images/et/turing-test-evol.4184696701293ead.webp new file mode 100644 index 00000000..a832c154 Binary files /dev/null and b/translated_images/et/turing-test-evol.4184696701293ead.webp differ diff --git a/translated_images/et/unet.3adb555bf39d3657.webp b/translated_images/et/unet.3adb555bf39d3657.webp new file mode 100644 index 00000000..af83f7b1 Binary files /dev/null and b/translated_images/et/unet.3adb555bf39d3657.webp differ diff --git a/translated_images/et/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp b/translated_images/et/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp new file mode 100644 index 00000000..a8e7581e Binary files /dev/null and b/translated_images/et/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp differ diff --git a/translated_images/et/vae.464c465a5b6a9e25.webp b/translated_images/et/vae.464c465a5b6a9e25.webp new file mode 100644 index 00000000..162bb624 Binary files /dev/null and b/translated_images/et/vae.464c465a5b6a9e25.webp differ diff --git a/translated_images/et/vaemnist-diag.694315f775d5d666.webp b/translated_images/et/vaemnist-diag.694315f775d5d666.webp new file mode 100644 index 00000000..49b53b6d Binary files /dev/null and b/translated_images/et/vaemnist-diag.694315f775d5d666.webp differ diff --git a/translated_images/et/vaemnist.cab9e602dc08dc50.webp b/translated_images/et/vaemnist.cab9e602dc08dc50.webp new file mode 100644 index 00000000..2e523d00 Binary files /dev/null and b/translated_images/et/vaemnist.cab9e602dc08dc50.webp differ diff --git a/translated_images/et/vgg-16-arch.64ff2137f50dd49f.webp b/translated_images/et/vgg-16-arch.64ff2137f50dd49f.webp new file mode 100644 index 00000000..c4f30d2d Binary files /dev/null and b/translated_images/et/vgg-16-arch.64ff2137f50dd49f.webp differ diff --git a/translated_images/et/vgg-16-arch1.d901a5583b3a51ba.webp b/translated_images/et/vgg-16-arch1.d901a5583b3a51ba.webp new file mode 100644 index 00000000..8e4f649c Binary files /dev/null and b/translated_images/et/vgg-16-arch1.d901a5583b3a51ba.webp differ diff --git a/translated_images/et/vqgan.5027fe05051dfa31.webp b/translated_images/et/vqgan.5027fe05051dfa31.webp new file mode 100644 index 00000000..e2d652c1 Binary files /dev/null and b/translated_images/et/vqgan.5027fe05051dfa31.webp differ diff --git a/translated_images/et/yolo.a2648ec82ee8bb4e.webp b/translated_images/et/yolo.a2648ec82ee8bb4e.webp new file mode 100644 index 00000000..91df20ed Binary files /dev/null and b/translated_images/et/yolo.a2648ec82ee8bb4e.webp differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.et.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.et.png deleted file mode 100644 index 2ad6e859..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.et.png and /dev/null differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png deleted file mode 100644 index ef0d21fe..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png and /dev/null differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.te.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.te.png deleted file mode 100644 index c3cc7a3a..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.te.png and /dev/null differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.et.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.et.png deleted file mode 100644 index 2ad6e859..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.et.png and /dev/null differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.pcm.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.pcm.png deleted file mode 100644 index ef0d21fe..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.pcm.png and /dev/null differ diff --git a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.te.png b/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.te.png deleted file mode 100644 index c3cc7a3a..00000000 Binary files a/translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6f0f5de66427e8a6eda63809356114e28fb1fa5f4a83ebda7.te.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb4188875.et.png b/translated_images/f-rcnn.3cda6d9bb4188875.et.png deleted file mode 100644 index 7df32137..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb4188875.et.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb4188875.pcm.png b/translated_images/f-rcnn.3cda6d9bb4188875.pcm.png deleted file mode 100644 index 31ec3c8e..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb4188875.pcm.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb4188875.te.png b/translated_images/f-rcnn.3cda6d9bb4188875.te.png deleted file mode 100644 index 3f810d73..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb4188875.te.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.et.png b/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.et.png deleted file mode 100644 index 7df32137..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.et.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.pcm.png b/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.pcm.png deleted file mode 100644 index 31ec3c8e..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.pcm.png and /dev/null differ diff --git a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.te.png b/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.te.png deleted file mode 100644 index 3f810d73..00000000 Binary files a/translated_images/f-rcnn.3cda6d9bb41888754037d2d9763e2298a96de5d9bc2a21db3147357aa5da9b1a.te.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30a.et.png b/translated_images/faster-rcnn.8d46c099b87ef30a.et.png deleted file mode 100644 index fb52e9d8..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30a.et.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30a.pcm.png b/translated_images/faster-rcnn.8d46c099b87ef30a.pcm.png deleted file mode 100644 index 4394d4c0..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30a.pcm.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30a.te.png b/translated_images/faster-rcnn.8d46c099b87ef30a.te.png deleted file mode 100644 index ca68b52a..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30a.te.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.et.png b/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.et.png deleted file mode 100644 index fb52e9d8..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.et.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.pcm.png b/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.pcm.png deleted file mode 100644 index 4394d4c0..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.pcm.png and /dev/null differ diff --git a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.te.png b/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.te.png deleted file mode 100644 index ca68b52a..00000000 Binary files a/translated_images/faster-rcnn.8d46c099b87ef30ab2ea26dbc4bdd85b974a57ba8eb526f65dc4cd0a4711de30.te.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454.et.png b/translated_images/favicon.37b561214b36d454.et.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454.et.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454.pcm.png b/translated_images/favicon.37b561214b36d454.pcm.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454.pcm.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454.te.png b/translated_images/favicon.37b561214b36d454.te.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454.te.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.et.png b/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.et.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.et.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.pcm.png b/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.pcm.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.pcm.png and /dev/null differ diff --git a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.te.png b/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.te.png deleted file mode 100644 index 26e0ae43..00000000 Binary files a/translated_images/favicon.37b561214b36d454f9fd1f725d77f310fe256eb88f2a0ae08b9cb18aeb30650c.te.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b95.et.png b/translated_images/features.6291f9c7ba3a0b95.et.png deleted file mode 100644 index b21e77a4..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b95.et.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b95.pcm.png b/translated_images/features.6291f9c7ba3a0b95.pcm.png deleted file mode 100644 index 0f6f09a9..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b95.pcm.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b95.te.png b/translated_images/features.6291f9c7ba3a0b95.te.png deleted file mode 100644 index 0f6f09a9..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b95.te.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.et.png b/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.et.png deleted file mode 100644 index b21e77a4..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.et.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.pcm.png b/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.pcm.png deleted file mode 100644 index 0f6f09a9..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.pcm.png and /dev/null differ diff --git a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.te.png b/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.te.png deleted file mode 100644 index 0f6f09a9..00000000 Binary files a/translated_images/features.6291f9c7ba3a0b951af88fc9864632b9115365410765680680d30c927dd67354.te.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946ef.et.png b/translated_images/filter-horiz.59b80ed4feb946ef.et.png deleted file mode 100644 index 4e830b38..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946ef.et.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946ef.pcm.png b/translated_images/filter-horiz.59b80ed4feb946ef.pcm.png deleted file mode 100644 index b7b5c794..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946ef.pcm.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946ef.te.png b/translated_images/filter-horiz.59b80ed4feb946ef.te.png deleted file mode 100644 index 58949e41..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946ef.te.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.et.png b/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.et.png deleted file mode 100644 index 4e830b38..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.et.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.pcm.png b/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.pcm.png deleted file mode 100644 index b7b5c794..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.pcm.png and /dev/null differ diff --git a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.te.png b/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.te.png deleted file mode 100644 index 58949e41..00000000 Binary files a/translated_images/filter-horiz.59b80ed4feb946efbe201a7fe3ca95abb3364e266e6fd90820cb893b4d3a6dda.te.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356.et.png b/translated_images/filter-vert.b7148390ca0bc356.et.png deleted file mode 100644 index eed73259..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356.et.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356.pcm.png b/translated_images/filter-vert.b7148390ca0bc356.pcm.png deleted file mode 100644 index 9ae86a0e..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356.pcm.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356.te.png b/translated_images/filter-vert.b7148390ca0bc356.te.png deleted file mode 100644 index fa14a2db..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356.te.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.et.png b/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.et.png deleted file mode 100644 index eed73259..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.et.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.pcm.png b/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.pcm.png deleted file mode 100644 index 9ae86a0e..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.pcm.png and /dev/null differ diff --git a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.te.png b/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.te.png deleted file mode 100644 index fa14a2db..00000000 Binary files a/translated_images/filter-vert.b7148390ca0bc356ddc7e55555d2481819c1e86ddde9dce4db5e71a69d6f887f.te.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c.et.png b/translated_images/frame-difference.706f805491a0883c.et.png deleted file mode 100644 index d5dbd58b..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c.et.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c.pcm.png b/translated_images/frame-difference.706f805491a0883c.pcm.png deleted file mode 100644 index ea47eef5..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c.pcm.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c.te.png b/translated_images/frame-difference.706f805491a0883c.te.png deleted file mode 100644 index 246b209d..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c.te.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.et.png b/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.et.png deleted file mode 100644 index d5dbd58b..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.et.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.pcm.png b/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.pcm.png deleted file mode 100644 index ea47eef5..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.pcm.png and /dev/null differ diff --git a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.te.png b/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.te.png deleted file mode 100644 index 246b209d..00000000 Binary files a/translated_images/frame-difference.706f805491a0883c938e16447bf5eb2f7d69e812c7f743cbe7d7c7645168f81f.te.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543.et.png b/translated_images/gan_arch_detail.46b95fd366f8e543.et.png deleted file mode 100644 index 57885732..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543.et.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543.pcm.png b/translated_images/gan_arch_detail.46b95fd366f8e543.pcm.png deleted file mode 100644 index 347ae52d..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543.pcm.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543.te.png b/translated_images/gan_arch_detail.46b95fd366f8e543.te.png deleted file mode 100644 index b6adad8c..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543.te.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.et.png b/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.et.png deleted file mode 100644 index 57885732..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.et.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.pcm.png b/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.pcm.png deleted file mode 100644 index 347ae52d..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.pcm.png and /dev/null differ diff --git a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.te.png b/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.te.png deleted file mode 100644 index b6adad8c..00000000 Binary files a/translated_images/gan_arch_detail.46b95fd366f8e543170264fe07e516683ac3e5bb699392c35449e99590a11063.te.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d69.et.png b/translated_images/gan_architecture.8f3a5ab62b8d5d69.et.png deleted file mode 100644 index fa343fb8..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d69.et.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d69.pcm.png b/translated_images/gan_architecture.8f3a5ab62b8d5d69.pcm.png deleted file mode 100644 index 7a7e52dd..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d69.pcm.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d69.te.png b/translated_images/gan_architecture.8f3a5ab62b8d5d69.te.png deleted file mode 100644 index 6d90d07f..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d69.te.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.et.png b/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.et.png deleted file mode 100644 index fa343fb8..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.et.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.pcm.png b/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.pcm.png deleted file mode 100644 index 7a7e52dd..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.pcm.png and /dev/null differ diff --git a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.te.png b/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.te.png deleted file mode 100644 index 6d90d07f..00000000 Binary files a/translated_images/gan_architecture.8f3a5ab62b8d5d698a91f7668017d8e09b81c5d8e7cc99bdb23979d90a0c475e.te.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a.et.png b/translated_images/history-of-ai.7e83efa70b537f5a.et.png deleted file mode 100644 index 5932815b..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a.et.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a.pcm.png b/translated_images/history-of-ai.7e83efa70b537f5a.pcm.png deleted file mode 100644 index 1883fcee..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a.pcm.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a.te.png b/translated_images/history-of-ai.7e83efa70b537f5a.te.png deleted file mode 100644 index f16bc737..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a.te.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.et.png b/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.et.png deleted file mode 100644 index 5932815b..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.et.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.pcm.png b/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.pcm.png deleted file mode 100644 index 1883fcee..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.pcm.png and /dev/null differ diff --git a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.te.png b/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.te.png deleted file mode 100644 index f16bc737..00000000 Binary files a/translated_images/history-of-ai.7e83efa70b537f5a0264357672b0884cf3a220fbafe35c65d70b2c3805f7bf5e.te.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044.et.png b/translated_images/ideal-cat-loop.999fbb8ff306e044.et.png deleted file mode 100644 index 7b5ab5f5..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044.et.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044.pcm.png b/translated_images/ideal-cat-loop.999fbb8ff306e044.pcm.png deleted file mode 100644 index fd2b6bd9..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044.pcm.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044.te.png b/translated_images/ideal-cat-loop.999fbb8ff306e044.te.png deleted file mode 100644 index 5d200a8b..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044.te.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.et.png b/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.et.png deleted file mode 100644 index 7b5ab5f5..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.et.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.pcm.png b/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.pcm.png deleted file mode 100644 index fd2b6bd9..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.pcm.png and /dev/null differ diff --git a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.te.png b/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.te.png deleted file mode 100644 index 5d200a8b..00000000 Binary files a/translated_images/ideal-cat-loop.999fbb8ff306e044f997032f4eef9152b453e6a990e449bbfb107de2493cc37e.te.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0.et.png b/translated_images/ideal-cat.203dd4597643d6b0.et.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0.et.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0.pcm.png b/translated_images/ideal-cat.203dd4597643d6b0.pcm.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0.pcm.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0.te.png b/translated_images/ideal-cat.203dd4597643d6b0.te.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0.te.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.et.png b/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.et.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.et.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.pcm.png b/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.pcm.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.pcm.png and /dev/null differ diff --git a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.te.png b/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.te.png deleted file mode 100644 index 54e79786..00000000 Binary files a/translated_images/ideal-cat.203dd4597643d6b0bd73038b87f9c0464322725e3a06ab145d25d4a861c70592.te.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a.et.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a.et.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a.et.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a.pcm.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a.pcm.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a.pcm.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a.te.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a.te.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a.te.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.et.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.et.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.et.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.pcm.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.pcm.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.pcm.png and /dev/null differ diff --git a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.te.png b/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.te.png deleted file mode 100644 index 0422909f..00000000 Binary files a/translated_images/ideal-zebra.7f70e8b54ee15a7a314000bb5df38a6cfe086ea04d60df4d3ef313d046b98a2b.te.png and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d45.et.jpg b/translated_images/image.896e8254a2c60d45.et.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d45.et.jpg and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d45.pcm.jpg b/translated_images/image.896e8254a2c60d45.pcm.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d45.pcm.jpg and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d45.te.jpg b/translated_images/image.896e8254a2c60d45.te.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d45.te.jpg and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.et.jpg b/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.et.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.et.jpg and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.pcm.jpg b/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.pcm.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.pcm.jpg and /dev/null differ diff --git a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.te.jpg b/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.te.jpg deleted file mode 100644 index 599c8388..00000000 Binary files a/translated_images/image.896e8254a2c60d451dbc648a499c3ed5d4b596bea265a3ca7ea581b5bc50d32f.te.jpg and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52.et.png b/translated_images/inception.a6605b85bcbc6f52.et.png deleted file mode 100644 index 662985bc..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52.et.png and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52.pcm.png b/translated_images/inception.a6605b85bcbc6f52.pcm.png deleted file mode 100644 index 36ff2b4f..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52.pcm.png and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52.te.png b/translated_images/inception.a6605b85bcbc6f52.te.png deleted file mode 100644 index 4c065a26..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52.te.png and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.et.png b/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.et.png deleted file mode 100644 index 662985bc..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.et.png and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.pcm.png b/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.pcm.png deleted file mode 100644 index 36ff2b4f..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.pcm.png and /dev/null differ diff --git a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.te.png b/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.te.png deleted file mode 100644 index 4c065a26..00000000 Binary files a/translated_images/inception.a6605b85bcbc6f52490ec55e68109dd41924cba9d7e1007453b4cdf554199c8d.te.png and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd45.et.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd45.et.jpeg deleted file mode 100644 index 9139aec7..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd45.et.jpeg and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd45.pcm.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd45.pcm.jpeg deleted file mode 100644 index bc5b725f..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd45.pcm.jpeg and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd45.te.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd45.te.jpeg deleted file mode 100644 index dcfcc04f..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd45.te.jpeg and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.et.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.et.jpeg deleted file mode 100644 index 9139aec7..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.et.jpeg and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.pcm.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.pcm.jpeg deleted file mode 100644 index bc5b725f..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.pcm.jpeg and /dev/null differ diff --git a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.te.jpeg b/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.te.jpeg deleted file mode 100644 index dcfcc04f..00000000 Binary files a/translated_images/instance_vs_semantic.eee9812bebf8cd450cdef4caaed2d4dd9c6c3b671e0c65d8aef312758ebb7b89.te.jpeg and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e11.et.png b/translated_images/iou_equation.9a4751d40fff4e11.et.png deleted file mode 100644 index cacea5b0..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e11.et.png and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e11.pcm.png b/translated_images/iou_equation.9a4751d40fff4e11.pcm.png deleted file mode 100644 index 461621cf..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e11.pcm.png and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e11.te.png b/translated_images/iou_equation.9a4751d40fff4e11.te.png deleted file mode 100644 index 5b7ef18b..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e11.te.png and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.et.png b/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.et.png deleted file mode 100644 index cacea5b0..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.et.png and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.pcm.png b/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.pcm.png deleted file mode 100644 index 461621cf..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.pcm.png and /dev/null differ diff --git a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.te.png b/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.te.png deleted file mode 100644 index 5b7ef18b..00000000 Binary files a/translated_images/iou_equation.9a4751d40fff4e119ecd0a7bcca4e71ab1dc83e0d4f2a0d66ff0859736f593cf.te.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.et.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.et.png deleted file mode 100644 index 03244b97..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.et.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png deleted file mode 100644 index 3dcd8555..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.te.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.te.png deleted file mode 100644 index 99fb38b8..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.te.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.et.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.et.png deleted file mode 100644 index 03244b97..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.et.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.pcm.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.pcm.png deleted file mode 100644 index 3dcd8555..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.pcm.png and /dev/null differ diff --git a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.te.png b/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.te.png deleted file mode 100644 index 99fb38b8..00000000 Binary files a/translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362e39ee4381aab7cad06b5465a0b5f053a0f2aa05fbe14e746.te.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217.et.png b/translated_images/knowledge-spectrum.b60df631852c0217.et.png deleted file mode 100644 index 10b65532..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217.et.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217.pcm.png b/translated_images/knowledge-spectrum.b60df631852c0217.pcm.png deleted file mode 100644 index f018fbc5..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217.pcm.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217.te.png b/translated_images/knowledge-spectrum.b60df631852c0217.te.png deleted file mode 100644 index b8211460..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217.te.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.et.png b/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.et.png deleted file mode 100644 index 10b65532..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.et.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.pcm.png b/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.pcm.png deleted file mode 100644 index f018fbc5..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.pcm.png and /dev/null differ diff --git a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.te.png b/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.te.png deleted file mode 100644 index b8211460..00000000 Binary files a/translated_images/knowledge-spectrum.b60df631852c0217e941485b79c9eee40ebd574f15f18609cec5758fcb384bf3.te.png and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74c.et.jpg b/translated_images/lmfilters.ea9e4868a82cf74c.et.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74c.et.jpg and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74c.pcm.jpg b/translated_images/lmfilters.ea9e4868a82cf74c.pcm.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74c.pcm.jpg and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74c.te.jpg b/translated_images/lmfilters.ea9e4868a82cf74c.te.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74c.te.jpg and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.et.jpg b/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.et.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.et.jpg and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.pcm.jpg b/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.pcm.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.pcm.jpg and /dev/null differ diff --git a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.te.jpg b/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.te.jpg deleted file mode 100644 index 4edba1d7..00000000 Binary files a/translated_images/lmfilters.ea9e4868a82cf74cdca05121b1128f0122297cf2879501cd06956beb88ff96a2.te.jpg and /dev/null differ diff --git a/translated_images/lt/.co-op-translator.json b/translated_images/lt/.co-op-translator.json index 1111985d..83333cbb 100644 --- a/translated_images/lt/.co-op-translator.json +++ b/translated_images/lt/.co-op-translator.json @@ -1,512 +1,20 @@ { - "favicon.37b561214b36d454.webp": { - "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", - "translation_date": "2026-01-16T06:58:23+00:00", - "source_file": "images/favicon.png", - "language_code": "lt" - }, - "ai-nlp.b22dcb8ca4707cea.webp": { - "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", - "translation_date": "2026-01-16T06:58:36+00:00", - "source_file": "lessons/sketchnotes/ai-nlp.png", - "language_code": "lt" - }, - "ai-symbolic.715a30cb610411a6.webp": { - "original_hash": "69d3628566f680ac8543651aa6fd520c", - "translation_date": "2026-01-16T06:59:05+00:00", - "source_file": "lessons/sketchnotes/ai-symbolic.png", - "language_code": "lt" - }, - "ai-computervision.6506ebebac3fbf76.webp": { - "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", - "translation_date": "2026-01-16T06:59:32+00:00", - "source_file": "lessons/sketchnotes/ai-computervision.png", - "language_code": "lt" - }, - "ai-for-beginners.b354ca904b22cd70.webp": { - "original_hash": "4b6f076798ec72ec7736b2e9039730e3", - "translation_date": "2026-01-16T06:59:44+00:00", - "source_file": "lessons/sketchnotes/ai-for-beginners.png", - "language_code": "lt" - }, - "ai-overview.0857791951d19500.webp": { - "original_hash": "7206f99da5c2b99d21581f946a660235", - "translation_date": "2026-01-16T07:00:00+00:00", - "source_file": "lessons/sketchnotes/ai-overview.png", - "language_code": "lt" - }, - "ai-intro.bf28d1ac4235881c.webp": { - "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", - "translation_date": "2026-01-16T07:00:28+00:00", - "source_file": "lessons/sketchnotes/ai-intro.png", - "language_code": "lt" - }, - "ai-neuralnetworks.1c687ae40bc86e83.webp": { - "original_hash": "6426ed635d4beb0ee499d634dfb61d65", - "translation_date": "2026-01-16T07:00:57+00:00", - "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", - "language_code": "lt" - }, - "vae.464c465a5b6a9e25.webp": { - "original_hash": "0b658c7862077e139162c756bcb98071", - "translation_date": "2026-01-16T07:01:08+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", - "language_code": "lt" - }, - "vaemnist-diag.694315f775d5d666.webp": { - "original_hash": "0652f5a95005348c6b1533438103dfcf", - "translation_date": "2026-01-16T07:01:11+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", - "language_code": "lt" - }, - "autoencoder_schema.5e6fc9ad98a5eb61.webp": { - "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", - "translation_date": "2026-01-16T07:01:15+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", - "language_code": "lt" - }, - "vaemnist.cab9e602dc08dc50.webp": { - "original_hash": "8159b2f649e6dd8efa071455d6f222b6", - "translation_date": "2026-01-16T07:01:20+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", - "language_code": "lt" - }, - "aae.9d418a990fc75bf9.webp": { - "original_hash": "92f89b37641f659a7d25c91d13076f69", - "translation_date": "2026-01-16T07:01:25+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", - "language_code": "lt" - }, - "instance_vs_semantic.eee9812bebf8cd45.webp": { - "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", - "translation_date": "2026-01-16T07:01:32+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", - "language_code": "lt" - }, - "unet.3adb555bf39d3657.webp": { - "original_hash": "49a151c11708ee9a3e94d21448146bf8", - "translation_date": "2026-01-16T07:01:44+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", - "language_code": "lt" - }, - "navi.2f20b727910110ea.webp": { - "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", - "translation_date": "2026-01-16T07:01:50+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", - "language_code": "lt" - }, - "segm.92442f2cb42ff4fa.webp": { - "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", - "translation_date": "2026-01-16T07:01:57+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", - "language_code": "lt" - }, - "segnet.87377542aa5a8b76.webp": { - "original_hash": "fa6d2d499aa2ae589a14caede7534561", - "translation_date": "2026-01-16T07:02:04+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", - "language_code": "lt" - }, - "gan_architecture.8f3a5ab62b8d5d69.webp": { - "original_hash": "4993c22b32d24c9d2d087645c2a90d81", - "translation_date": "2026-01-16T07:02:11+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", - "language_code": "lt" - }, - "style.5293e85e077ab22c.webp": { - "original_hash": "f797246177c68cc33bcdf7abae8c9b68", - "translation_date": "2026-01-16T07:02:15+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", - "language_code": "lt" - }, - "image.896e8254a2c60d45.webp": { - "original_hash": "0033165481f191386403b85801811833", - "translation_date": "2026-01-16T07:02:16+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", - "language_code": "lt" - }, - "gan_arch_detail.46b95fd366f8e543.webp": { - "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", - "translation_date": "2026-01-16T07:02:24+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", - "language_code": "lt" - }, - "dcgan_generator.b500988ec2bc8ba5.webp": { - "original_hash": "a11642e50f68e41c69b1580c9b724ef1", - "translation_date": "2026-01-16T07:02:34+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", - "language_code": "lt" - }, - "ideal-zebra.7f70e8b54ee15a7a.webp": { - "original_hash": "6944fb46795f714f0ce8e856c405498a", - "translation_date": "2026-01-16T07:02:37+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", - "language_code": "lt" - }, - "ideal-cat-loop.999fbb8ff306e044.webp": { - "original_hash": "c54e983c591431338bf8ddac9ab8415b", - "translation_date": "2026-01-16T07:02:42+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", - "language_code": "lt" - }, - "dog-from-unsplash.426f9fbca2febc93.webp": { - "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", - "translation_date": "2026-01-16T07:02:46+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", - "language_code": "lt" - }, - "features.6291f9c7ba3a0b95.webp": { - "original_hash": "e2727bfacc1156e045d1879bbe86e189", - "translation_date": "2026-01-16T07:02:49+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", - "language_code": "lt" - }, - "ideal-cat.203dd4597643d6b0.webp": { - "original_hash": "5b44760be530a91be18a5cceebbc2cc3", - "translation_date": "2026-01-16T07:02:50+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", - "language_code": "lt" - }, - "adversarial-dog.d9fc7773b0142b89.webp": { - "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", - "translation_date": "2026-01-16T07:02:51+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", - "language_code": "lt" - }, - "catsdogsdataset.a7aff8e6085fd3f0.webp": { - "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", - "translation_date": "2026-01-16T07:02:54+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", - "language_code": "lt" - }, - "original-dog.8f68a67d2fe0911f.webp": { - "original_hash": "3ed859629b4141f735fd0d3c1941f520", - "translation_date": "2026-01-16T07:02:55+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", - "language_code": "lt" - }, - "braille.341962ff76b1bd70.webp": { - "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", - "translation_date": "2026-01-16T07:02:56+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", - "language_code": "lt" - }, - "braille-symbols.0159185ab69d5339.webp": { - "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", - "translation_date": "2026-01-16T07:02:59+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", - "language_code": "lt" - }, - "frame-difference.706f805491a0883c.webp": { - "original_hash": "a141e72f08e1b8f7451392889af90072", - "translation_date": "2026-01-16T07:03:01+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", - "language_code": "lt" - }, - "braille-result.46530fea020b03c7.webp": { - "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", - "translation_date": "2026-01-16T07:03:03+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", - "language_code": "lt" - }, - "palm-movement.341495f0e9c47da3.webp": { - "original_hash": "100780b2e1d5adff2739adf58fc18404", - "translation_date": "2026-01-16T07:03:04+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", - "language_code": "lt" - }, - "optical.1f4a94464579a83a.webp": { - "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", - "translation_date": "2026-01-16T07:03:06+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", - "language_code": "lt" - }, "1200px-Girl_and_cat.89bd70951181e86a.webp": { "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", "translation_date": "2026-01-16T07:03:07+00:00", "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", "language_code": "lt" }, - "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { - "original_hash": "f31ea979f0ceabdf198899985ac84c37", - "translation_date": "2026-01-16T07:03:14+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", - "language_code": "lt" - }, - "naive-detection.e7f1ba220ccd08c6.webp": { - "original_hash": "4c96961c12a09f8e055546ed2e7de470", - "translation_date": "2026-01-16T07:03:22+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", - "language_code": "lt" - }, - "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { - "original_hash": "6704085c522f47ce42ad8402dafe6429", - "translation_date": "2026-01-16T07:03:27+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", - "language_code": "lt" - }, - "iou_equation.9a4751d40fff4e11.webp": { - "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", - "translation_date": "2026-01-16T07:03:31+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", - "language_code": "lt" - }, - "coco-examples.71bc60380fa6cceb.webp": { - "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", - "translation_date": "2026-01-16T07:03:35+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", - "language_code": "lt" - }, - "f-rcnn.3cda6d9bb4188875.webp": { - "original_hash": "fdafedad20701c95bdcf6bb923822ab1", - "translation_date": "2026-01-16T07:03:41+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", - "language_code": "lt" - }, - "rcnn1.cae407020dfb1d1f.webp": { - "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", - "translation_date": "2026-01-16T07:03:45+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", - "language_code": "lt" - }, - "faster-rcnn.8d46c099b87ef30a.webp": { - "original_hash": "067e2ca96344fd6d0490e0530a922b36", - "translation_date": "2026-01-16T07:03:54+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", - "language_code": "lt" - }, - "r-fcn.13eb88158b99a3da.webp": { - "original_hash": "38cd0e0105546e56fa17b711d445195f", - "translation_date": "2026-01-16T07:04:00+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", - "language_code": "lt" - }, - "yolo.a2648ec82ee8bb4e.webp": { - "original_hash": "e8835638234f5c21fcf36fdede6457f4", - "translation_date": "2026-01-16T07:04:05+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", - "language_code": "lt" - }, - "rcnn2.2d9530bb83516484.webp": { - "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", - "translation_date": "2026-01-16T07:04:12+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", - "language_code": "lt" - }, - "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { - "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", - "translation_date": "2026-01-16T07:04:25+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", - "language_code": "lt" - }, - "resnet-block.aba4ccbcc0944434.webp": { - "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", - "translation_date": "2026-01-16T07:04:32+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", - "language_code": "lt" - }, - "cnn-pyramid.85915455759ef0ce.webp": { - "original_hash": "7233ded4a920332806363d704bfb59a6", - "translation_date": "2026-01-16T07:04:46+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", - "language_code": "lt" - }, - "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { - "original_hash": "c9bde577c8b279b5199a8b294ee9494f", - "translation_date": "2026-01-16T07:04:55+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", - "language_code": "lt" - }, - "filter-horiz.59b80ed4feb946ef.webp": { - "original_hash": "b081df9e2042850983a46ff817b88d55", - "translation_date": "2026-01-16T07:04:57+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", - "language_code": "lt" - }, - "vgg-16-arch1.d901a5583b3a51ba.webp": { - "original_hash": "5b0f835d04dc20d097a0b89c88339966", - "translation_date": "2026-01-16T07:05:04+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", - "language_code": "lt" - }, - "vgg-16-arch.64ff2137f50dd49f.webp": { - "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", - "translation_date": "2026-01-16T07:05:10+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", - "language_code": "lt" - }, - "convolutionExample.634615d5ff7081e0.webp": { - "original_hash": "5412e092848cb3cd4fa527aba3be0545", - "translation_date": "2026-01-16T07:05:17+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", - "language_code": "lt" - }, - "inception.a6605b85bcbc6f52.webp": { - "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", - "translation_date": "2026-01-16T07:05:24+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", - "language_code": "lt" - }, - "filter-vert.b7148390ca0bc356.webp": { - "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", - "translation_date": "2026-01-16T07:05:30+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", - "language_code": "lt" - }, - "lmfilters.ea9e4868a82cf74c.webp": { - "original_hash": "aa029ea2c45afbac3026a0a558eeec43", - "translation_date": "2026-01-16T07:05:31+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", - "language_code": "lt" - }, - "data.50b2a9d5484bdbf0.webp": { - "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", - "translation_date": "2026-01-16T07:05:41+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", - "language_code": "lt" - }, - "NetLogo-ModelLib.efe023afb4763c05.webp": { - "original_hash": "edd5b28318e2f43274a4541408110fb9", - "translation_date": "2026-01-16T07:05:56+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", - "language_code": "lt" - }, - "NetLogo-Main.32653711ec1a01b3.webp": { - "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", - "translation_date": "2026-01-16T07:06:21+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", - "language_code": "lt" - }, - "cartpole.f52a67f27e058170.webp": { - "original_hash": "5399242e127ea1c18aa6ee405daecf51", - "translation_date": "2026-01-16T07:06:31+00:00", - "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", - "language_code": "lt" - }, - "mountaincar.f7b7a7f6d4f9933b.webp": { - "original_hash": "61c868cc389dc92bd2b402ea490cd162", - "translation_date": "2026-01-16T07:06:32+00:00", - "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", - "language_code": "lt" - }, - "ml-for-beginners.9e4fed176fd5817d.webp": { - "original_hash": "cd606a24083e039082b0486fc8382823", - "translation_date": "2026-01-16T07:06:35+00:00", - "source_file": "lessons/1-Intro/images/ml-for-beginners.png", - "language_code": "lt" - }, - "history-of-ai.7e83efa70b537f5a.webp": { - "original_hash": "644e648b98fcb10fb9713452ff02934d", - "translation_date": "2026-01-16T07:06:47+00:00", - "source_file": "lessons/1-Intro/images/history-of-ai.png", - "language_code": "lt" - }, - "photo-cat.8c8e8fb760ffe457.webp": { - "original_hash": "29d10fef28d240c48995ef9dd23e477a", - "translation_date": "2026-01-16T07:06:54+00:00", - "source_file": "lessons/1-Intro/images/photo-cat.jpg", - "language_code": "lt" - }, - "dsh_age.d212a30d4e54fb5f.webp": { - "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", - "translation_date": "2026-01-16T07:06:56+00:00", - "source_file": "lessons/1-Intro/images/dsh_age.png", - "language_code": "lt" - }, - "turing-test-evol.4184696701293ead.webp": { - "original_hash": "80d11b1074d61e5d6e4a207f72902e89", - "translation_date": "2026-01-16T07:07:02+00:00", - "source_file": "lessons/1-Intro/images/turing-test-evol.png", - "language_code": "lt" - }, - "knowledge-spectrum.b60df631852c0217.webp": { - "original_hash": "71b049ee26a22a68996034585436ca59", - "translation_date": "2026-01-16T07:07:16+00:00", - "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", - "language_code": "lt" - }, - "DIKW_Pyramid.94126f7d2bd8db5b.webp": { - "original_hash": "ad410ec7f25454482fd4516c4a46fc67", - "translation_date": "2026-01-16T07:07:26+00:00", - "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", - "language_code": "lt" - }, "AND-OR-Tree.5592d2c70187f283.webp": { "original_hash": "2674b6cf8f768491c6b5a167f272a002", "translation_date": "2026-01-16T07:07:59+00:00", "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", "language_code": "lt" }, - "triplet-complex.32094972c7b4441b.webp": { - "original_hash": "56a2e05839a141c311db52655b37f8ad", - "translation_date": "2026-01-16T07:08:29+00:00", - "source_file": "lessons/2-Symbolic/images/triplet-complex.png", - "language_code": "lt" - }, - "arch-human.5d4d35f1bba3ab1c.webp": { - "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", - "translation_date": "2026-01-16T07:08:41+00:00", - "source_file": "lessons/2-Symbolic/images/arch-human.png", - "language_code": "lt" - }, - "arch-kbs.3ec5c150b09fa8da.webp": { - "original_hash": "f470e6ec071db529cd3149052cfeb8ff", - "translation_date": "2026-01-16T07:08:49+00:00", - "source_file": "lessons/2-Symbolic/images/arch-kbs.png", - "language_code": "lt" - }, - "triplet.4b9b332587593298.webp": { - "original_hash": "302e53ea355ffb556d99e3962d0a6516", - "translation_date": "2026-01-16T07:08:59+00:00", - "source_file": "lessons/2-Symbolic/images/triplet.png", - "language_code": "lt" - }, - "protege.274177ceeac13b38.webp": { - "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", - "translation_date": "2026-01-16T07:09:32+00:00", - "source_file": "lessons/2-Symbolic/images/protege.png", - "language_code": "lt" - }, - "synapse-wikipedia.ed20a9e4726ea1c6.webp": { - "original_hash": "88212730ecd9b0c8b848c319951427d8", - "translation_date": "2026-01-16T07:09:59+00:00", - "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", - "language_code": "lt" - }, - "overfit2.131f5800ae10ca5e.webp": { - "original_hash": "eb04381b2f222518ec400b98ebf441b2", - "translation_date": "2026-01-16T07:10:03+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", - "language_code": "lt" - }, - "netout.1eb15eb76fd76731.webp": { - "original_hash": "187261e2b5036746ee9d9106b1f7df1b", - "translation_date": "2026-01-16T07:10:05+00:00", - "source_file": "lessons/3-NeuralNetworks/images/netout.png", - "language_code": "lt" - }, - "artneuron.1a5daa88d20ebe6f.webp": { - "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", - "translation_date": "2026-01-16T07:10:09+00:00", - "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", - "language_code": "lt" - }, - "Overfitting.408ad91cd90b4371.webp": { - "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", - "translation_date": "2026-01-16T07:10:16+00:00", - "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", - "language_code": "lt" - }, - "overfit1.f24b71c6f652e59e.webp": { - "original_hash": "76155698e85340d9dfff8e0a628d25c1", - "translation_date": "2026-01-16T07:10:21+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", - "language_code": "lt" - }, - "NeuroArch.4e17cdba5e445721.webp": { - "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", - "translation_date": "2026-01-16T07:10:26+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:10:43+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", "language_code": "lt" }, "ComputeGraphGrad.4626252c0de03507.webp": { @@ -515,66 +23,18 @@ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", "language_code": "lt" }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:13:21+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "lt" + }, "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { "original_hash": "11dd0fd77a272755d0ef5db9f71217da", "translation_date": "2026-01-16T07:10:38+00:00", "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", "language_code": "lt" }, - "ComputeGraph.463c9d8ebdcb2215.webp": { - "original_hash": "7af66742d6bede114f971689745bedf2", - "translation_date": "2026-01-16T07:10:43+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", - "language_code": "lt" - }, - "overfit.a0bd57f717c15769.webp": { - "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", - "translation_date": "2026-01-16T07:10:47+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", - "language_code": "lt" - }, - "Rosenblatt-wikipedia.294821b285ac796d.webp": { - "original_hash": "c21d9b47d0106208a0f35a920d6bff66", - "translation_date": "2026-01-16T07:10:49+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", - "language_code": "lt" - }, - "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { - "original_hash": "2cc48ff435c89ca1e162872a42b4813c", - "translation_date": "2026-01-16T07:10:52+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", - "language_code": "lt" - }, - "activation-func.b4924007c7ce7764.webp": { - "original_hash": "8d357884343ec923611a319d4e910b99", - "translation_date": "2026-01-16T07:10:54+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", - "language_code": "lt" - }, - "clip-class.3af42ef0b2b19369.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:11:00+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", - "language_code": "lt" - }, - "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { - "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", - "translation_date": "2026-01-16T07:11:04+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", - "language_code": "lt" - }, - "clip-arch.b3dbf20b4e8ed8be.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:11:09+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", - "language_code": "lt" - }, - "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { - "original_hash": "e300d75d78f6050bc7b83df091f95775", - "translation_date": "2026-01-16T07:11:13+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", - "language_code": "lt" - }, "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { "original_hash": "dd063fda04db937ab7210064af9d6151", "translation_date": "2026-01-16T07:11:15+00:00", @@ -587,10 +47,82 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", "language_code": "lt" }, - "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { - "original_hash": "ec89cbb600b14e86f353a347506554ba", - "translation_date": "2026-01-16T07:11:17+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:11:13+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "lt" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:07:26+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "lt" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:04:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "lt" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:10:52+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "lt" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:06:21+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "lt" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:05:56+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "lt" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:10:26+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "lt" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:03:27+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "lt" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:03:14+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "lt" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:10:16+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "lt" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:10:49+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "lt" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:04:25+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "lt" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:11:04+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", "language_code": "lt" }, "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { @@ -599,22 +131,88 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", "language_code": "lt" }, - "vqgan.5027fe05051dfa31.webp": { - "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", - "translation_date": "2026-01-16T07:11:20+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:11:17+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", "language_code": "lt" }, - "bag-of-words-example.606fc1738f1d7ba9.webp": { - "original_hash": "a8fa84622ff35939e498d06fac3fa515", - "translation_date": "2026-01-16T07:11:24+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:01:25+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", "language_code": "lt" }, - "bow.3811869cff59368d.webp": { - "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", - "translation_date": "2026-01-16T07:11:42+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:10:54+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "lt" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:02:51+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "lt" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T06:59:32+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "lt" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T06:59:44+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "lt" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:00:28+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "lt" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:00:57+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "lt" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T06:58:36+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "lt" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T07:00:00+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "lt" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T06:59:05+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "lt" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:08:41+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "lt" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:08:49+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "lt" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:10:09+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", "language_code": "lt" }, "ascii-character-map.18ed6aa7f3b0a7ff.webp": { @@ -623,34 +221,16 @@ "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", "language_code": "lt" }, - "multi-layer-lstm.dd975e29bb2a59fe.webp": { - "original_hash": "27b6355fd86c9e8e6d443015653be763", - "translation_date": "2026-01-16T07:12:00+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:01:15+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", "language_code": "lt" }, - "rnn-anatomy.79ee3f3920b3294b.webp": { - "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", - "translation_date": "2026-01-16T07:12:07+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", - "language_code": "lt" - }, - "rnn.27f5c29c53d727b5.webp": { - "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", - "translation_date": "2026-01-16T07:12:19+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", - "language_code": "lt" - }, - "encoder-decoder-attention.7a726296894fb567.webp": { - "original_hash": "e0546cbc8252d764df7f7212b371f0ed", - "translation_date": "2026-01-16T07:12:32+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", - "language_code": "lt" - }, - "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { - "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", - "translation_date": "2026-01-16T07:12:44+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:11:24+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", "language_code": "lt" }, "bahdanau-fig3.09ba2d37f202a6af.webp": { @@ -659,46 +239,100 @@ "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", "language_code": "lt" }, - "pos-embedding.e41ce9b6cf6078af.webp": { - "original_hash": "f0910082dcac063f3baae2e1f28b4e30", - "translation_date": "2026-01-16T07:13:01+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", - "language_code": "lt" - }, - "transformer-layer.905e14747ca4e7d5.webp": { - "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", - "translation_date": "2026-01-16T07:13:12+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", - "language_code": "lt" - }, - "CoreferenceResolution.861924d6d384a7d6.webp": { - "original_hash": "25b5719ec70aaa44858076c16f7c208f", - "translation_date": "2026-01-16T07:13:21+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", - "language_code": "lt" - }, "bot-ner.4b09235dbb0ad275.webp": { "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", "translation_date": "2026-01-16T07:13:36+00:00", "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", "language_code": "lt" }, - "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { - "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", - "translation_date": "2026-01-16T07:13:45+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:11:42+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", "language_code": "lt" }, - "rnn-generate.56c54afb52f9781d.webp": { - "original_hash": "67332ada2d0603921bba37c06956c70e", - "translation_date": "2026-01-16T07:13:50+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:03:03+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", "language_code": "lt" }, - "rnn-generate-inf.5168dc65e0370eea.webp": { - "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", - "translation_date": "2026-01-16T07:13:55+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:02:59+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "lt" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:02:56+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "lt" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:06:31+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "lt" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:02:54+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "lt" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:11:09+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "lt" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:11:00+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "lt" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:04:46+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "lt" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:03:35+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "lt" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:05:17+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "lt" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:05:41+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "lt" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:02:34+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "lt" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:02:46+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "lt" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:06:56+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", "language_code": "lt" }, "embedding-classifier-example.b77f021a7ee67eee.webp": { @@ -707,10 +341,10 @@ "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", "language_code": "lt" }, - "offset-sequence-representation.eb73fcefb29b46ee.webp": { - "original_hash": "52e7632a2b668957b903bb2607e953fe", - "translation_date": "2026-01-16T07:14:06+00:00", - "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:12:32+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", "language_code": "lt" }, "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { @@ -718,5 +352,371 @@ "translation_date": "2026-01-16T07:14:11+00:00", "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", "language_code": "lt" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:03:41+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "lt" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:03:54+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "lt" + }, + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T06:58:23+00:00", + "source_file": "images/favicon.png", + "language_code": "lt" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:02:49+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "lt" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:04:57+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "lt" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:05:30+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "lt" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:03:01+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "lt" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:02:24+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "lt" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:02:11+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "lt" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:06:47+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "lt" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:02:42+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "lt" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:02:50+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "lt" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:02:37+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "lt" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:02:16+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "lt" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:05:24+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "lt" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:01:32+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "lt" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:03:31+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "lt" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:12:44+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "lt" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:07:16+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "lt" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:05:31+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "lt" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:06:35+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "lt" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:06:32+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "lt" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:12:00+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "lt" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:03:22+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "lt" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:01:50+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "lt" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:10:05+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "lt" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:14:06+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "lt" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:03:06+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "lt" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:02:55+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "lt" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:10:47+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "lt" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:10:21+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "lt" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:10:03+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "lt" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:03:04+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "lt" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:06:54+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "lt" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:13:01+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "lt" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:09:32+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "lt" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:04:00+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "lt" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:03:45+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "lt" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:04:12+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "lt" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:04:32+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "lt" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:12:07+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "lt" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:13:55+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "lt" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:13:50+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "lt" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:12:19+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "lt" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:01:57+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "lt" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:02:04+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "lt" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:02:15+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "lt" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:09:59+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "lt" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:13:12+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "lt" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:08:29+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "lt" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:08:59+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "lt" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:07:02+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "lt" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:01:44+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "lt" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:13:45+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "lt" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:01:08+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "lt" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:01:11+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "lt" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:01:20+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "lt" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:05:10+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "lt" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:05:04+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "lt" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:11:20+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "lt" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:04:05+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "lt" } } \ No newline at end of file diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d.et.png b/translated_images/ml-for-beginners.9e4fed176fd5817d.et.png deleted file mode 100644 index 80894488..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d.et.png and /dev/null differ diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d.pcm.png b/translated_images/ml-for-beginners.9e4fed176fd5817d.pcm.png deleted file mode 100644 index 43a2ef98..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d.pcm.png and /dev/null differ diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d.te.png b/translated_images/ml-for-beginners.9e4fed176fd5817d.te.png deleted file mode 100644 index 8f7d22c0..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d.te.png and /dev/null differ diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.et.png b/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.et.png deleted file mode 100644 index 80894488..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.et.png and /dev/null differ diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.pcm.png b/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.pcm.png deleted file mode 100644 index 43a2ef98..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.pcm.png and /dev/null differ diff --git a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.te.png b/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.te.png deleted file mode 100644 index 8f7d22c0..00000000 Binary files a/translated_images/ml-for-beginners.9e4fed176fd5817d7d1f7d358302515186579cbf09b2a6c5bd8092b345da7f22.te.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b.et.png b/translated_images/mountaincar.f7b7a7f6d4f9933b.et.png deleted file mode 100644 index ed07b433..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b.et.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b.pcm.png b/translated_images/mountaincar.f7b7a7f6d4f9933b.pcm.png deleted file mode 100644 index da8281ed..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b.pcm.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b.te.png b/translated_images/mountaincar.f7b7a7f6d4f9933b.te.png deleted file mode 100644 index 470614b4..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b.te.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.et.png b/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.et.png deleted file mode 100644 index ed07b433..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.et.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.pcm.png b/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.pcm.png deleted file mode 100644 index da8281ed..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.pcm.png and /dev/null differ diff --git a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.te.png b/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.te.png deleted file mode 100644 index 470614b4..00000000 Binary files a/translated_images/mountaincar.f7b7a7f6d4f9933b31a5fb3453b9c026aa0d65f6644bb03513a955590aae1bc4.te.png and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.et.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe.et.jpg deleted file mode 100644 index 260a705c..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.et.jpg and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg deleted file mode 100644 index be6ceb6b..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.te.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe.te.jpg deleted file mode 100644 index 1bfa4aa3..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe.te.jpg and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.et.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.et.jpg deleted file mode 100644 index 260a705c..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.et.jpg and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.pcm.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.pcm.jpg deleted file mode 100644 index be6ceb6b..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.pcm.jpg and /dev/null differ diff --git a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.te.jpg b/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.te.jpg deleted file mode 100644 index 1bfa4aa3..00000000 Binary files a/translated_images/multi-layer-lstm.dd975e29bb2a59fe58b429db833932d734c81f211cad2783797a9608984acb8c.te.jpg and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c6.et.png b/translated_images/naive-detection.e7f1ba220ccd08c6.et.png deleted file mode 100644 index 4acab52a..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c6.et.png and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c6.pcm.png b/translated_images/naive-detection.e7f1ba220ccd08c6.pcm.png deleted file mode 100644 index 2d0845ea..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c6.pcm.png and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c6.te.png b/translated_images/naive-detection.e7f1ba220ccd08c6.te.png deleted file mode 100644 index dc1ee83b..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c6.te.png and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.et.png b/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.et.png deleted file mode 100644 index 4acab52a..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.et.png and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.pcm.png b/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.pcm.png deleted file mode 100644 index 2d0845ea..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.pcm.png and /dev/null differ diff --git a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.te.png b/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.te.png deleted file mode 100644 index dc1ee83b..00000000 Binary files a/translated_images/naive-detection.e7f1ba220ccd08c68a2ea8e06a7ed75c3fcc738c2372f9e00b7f4299a8659c01.te.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea.et.png b/translated_images/navi.2f20b727910110ea.et.png deleted file mode 100644 index e83e65fe..00000000 Binary files a/translated_images/navi.2f20b727910110ea.et.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea.pcm.png b/translated_images/navi.2f20b727910110ea.pcm.png deleted file mode 100644 index 5f1b7260..00000000 Binary files a/translated_images/navi.2f20b727910110ea.pcm.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea.te.png b/translated_images/navi.2f20b727910110ea.te.png deleted file mode 100644 index 0696957d..00000000 Binary files a/translated_images/navi.2f20b727910110ea.te.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.et.png b/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.et.png deleted file mode 100644 index e83e65fe..00000000 Binary files a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.et.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.pcm.png b/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.pcm.png deleted file mode 100644 index 5f1b7260..00000000 Binary files a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.pcm.png and /dev/null differ diff --git a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.te.png b/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.te.png deleted file mode 100644 index 0696957d..00000000 Binary files a/translated_images/navi.2f20b727910110ea593fa03a2491f2ba1b25c62c97b33c692bcf01917a1f333f.te.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd76731.et.png b/translated_images/netout.1eb15eb76fd76731.et.png deleted file mode 100644 index 8c28d320..00000000 Binary files a/translated_images/netout.1eb15eb76fd76731.et.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd76731.pcm.png b/translated_images/netout.1eb15eb76fd76731.pcm.png deleted file mode 100644 index 8ffe2568..00000000 Binary files a/translated_images/netout.1eb15eb76fd76731.pcm.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd76731.te.png b/translated_images/netout.1eb15eb76fd76731.te.png deleted file mode 100644 index bb107255..00000000 Binary files a/translated_images/netout.1eb15eb76fd76731.te.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.et.png b/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.et.png deleted file mode 100644 index 8c28d320..00000000 Binary files a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.et.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.pcm.png b/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.pcm.png deleted file mode 100644 index 8ffe2568..00000000 Binary files a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.pcm.png and /dev/null differ diff --git a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.te.png b/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.te.png deleted file mode 100644 index bb107255..00000000 Binary files a/translated_images/netout.1eb15eb76fd767313e067719f400cec4b0e5090239c3e997c29f6789d4c3c263.te.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.et.png b/translated_images/offset-sequence-representation.eb73fcefb29b46ee.et.png deleted file mode 100644 index 0abe89c1..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.et.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.pcm.png b/translated_images/offset-sequence-representation.eb73fcefb29b46ee.pcm.png deleted file mode 100644 index dfa9fd32..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.pcm.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.te.png b/translated_images/offset-sequence-representation.eb73fcefb29b46ee.te.png deleted file mode 100644 index 512f3145..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46ee.te.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.et.png b/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.et.png deleted file mode 100644 index 0abe89c1..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.et.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.pcm.png b/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.pcm.png deleted file mode 100644 index dfa9fd32..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.pcm.png and /dev/null differ diff --git a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.te.png b/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.te.png deleted file mode 100644 index 512f3145..00000000 Binary files a/translated_images/offset-sequence-representation.eb73fcefb29b46eecfbe74466077cfeb7c0f93a4f254850538a2efbc63517479.te.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a.et.png b/translated_images/optical.1f4a94464579a83a.et.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a.et.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a.pcm.png b/translated_images/optical.1f4a94464579a83a.pcm.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a.pcm.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a.te.png b/translated_images/optical.1f4a94464579a83a.te.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a.te.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.et.png b/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.et.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.et.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.pcm.png b/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.pcm.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.pcm.png and /dev/null differ diff --git a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.te.png b/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.te.png deleted file mode 100644 index f6d867c3..00000000 Binary files a/translated_images/optical.1f4a94464579a83a10784f3c07fe7228514714b96782edf50e70ccd59d2d8c4f.te.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f.et.png b/translated_images/original-dog.8f68a67d2fe0911f.et.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f.et.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f.pcm.png b/translated_images/original-dog.8f68a67d2fe0911f.pcm.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f.pcm.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f.te.png b/translated_images/original-dog.8f68a67d2fe0911f.te.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f.te.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.et.png b/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.et.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.et.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.pcm.png b/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.pcm.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.pcm.png and /dev/null differ diff --git a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.te.png b/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.te.png deleted file mode 100644 index da672bbd..00000000 Binary files a/translated_images/original-dog.8f68a67d2fe0911f33041c0f7fce8aa4ea919f9d3917ec4b468298522aeb6356.te.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c15769.et.png b/translated_images/overfit.a0bd57f717c15769.et.png deleted file mode 100644 index 46a57f84..00000000 Binary files a/translated_images/overfit.a0bd57f717c15769.et.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c15769.pcm.png b/translated_images/overfit.a0bd57f717c15769.pcm.png deleted file mode 100644 index 00e3baf1..00000000 Binary files a/translated_images/overfit.a0bd57f717c15769.pcm.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c15769.te.png b/translated_images/overfit.a0bd57f717c15769.te.png deleted file mode 100644 index 058462cf..00000000 Binary files a/translated_images/overfit.a0bd57f717c15769.te.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.et.png b/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.et.png deleted file mode 100644 index 46a57f84..00000000 Binary files a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.et.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.pcm.png b/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.pcm.png deleted file mode 100644 index 00e3baf1..00000000 Binary files a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.pcm.png and /dev/null differ diff --git a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.te.png b/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.te.png deleted file mode 100644 index 058462cf..00000000 Binary files a/translated_images/overfit.a0bd57f717c157696f30c9c73fa7c3345c49b4280e412ff30c4a1a16ba29ff49.te.png and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e.et.jpg b/translated_images/overfit1.f24b71c6f652e59e.et.jpg deleted file mode 100644 index cb96e299..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e.et.jpg and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e.pcm.jpg b/translated_images/overfit1.f24b71c6f652e59e.pcm.jpg deleted file mode 100644 index 4c05e697..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e.pcm.jpg and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e.te.jpg b/translated_images/overfit1.f24b71c6f652e59e.te.jpg deleted file mode 100644 index c068808d..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e.te.jpg and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.et.jpg b/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.et.jpg deleted file mode 100644 index cb96e299..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.et.jpg and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.pcm.jpg b/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.pcm.jpg deleted file mode 100644 index 4c05e697..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.pcm.jpg and /dev/null differ diff --git a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.te.jpg b/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.te.jpg deleted file mode 100644 index c068808d..00000000 Binary files a/translated_images/overfit1.f24b71c6f652e59e6bed7245ffbeaecc3ba320e16e2221f6832b432052c4da43.te.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e.et.jpg b/translated_images/overfit2.131f5800ae10ca5e.et.jpg deleted file mode 100644 index 7a69a2fe..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e.et.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e.pcm.jpg b/translated_images/overfit2.131f5800ae10ca5e.pcm.jpg deleted file mode 100644 index 00d3f6e0..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e.pcm.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e.te.jpg b/translated_images/overfit2.131f5800ae10ca5e.te.jpg deleted file mode 100644 index 98403f12..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e.te.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.et.jpg b/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.et.jpg deleted file mode 100644 index 7a69a2fe..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.et.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.pcm.jpg b/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.pcm.jpg deleted file mode 100644 index 00d3f6e0..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.pcm.jpg and /dev/null differ diff --git a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.te.jpg b/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.te.jpg deleted file mode 100644 index 98403f12..00000000 Binary files a/translated_images/overfit2.131f5800ae10ca5e41d12a411f5f705d9ee38b1b10916f284b787028dd55cc1c.te.jpg and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da3.et.png b/translated_images/palm-movement.341495f0e9c47da3.et.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da3.et.png and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da3.pcm.png b/translated_images/palm-movement.341495f0e9c47da3.pcm.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da3.pcm.png and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da3.te.png b/translated_images/palm-movement.341495f0e9c47da3.te.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da3.te.png and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.et.png b/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.et.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.et.png and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.pcm.png b/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.pcm.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.pcm.png and /dev/null differ diff --git a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.te.png b/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.te.png deleted file mode 100644 index bb70c019..00000000 Binary files a/translated_images/palm-movement.341495f0e9c47da39cc1f99626822a1d20203aa33ff89a86a068f14bea133e84.te.png and /dev/null differ diff --git a/translated_images/pcm/.co-op-translator.json b/translated_images/pcm/.co-op-translator.json new file mode 100644 index 00000000..a8e559e2 --- /dev/null +++ b/translated_images/pcm/.co-op-translator.json @@ -0,0 +1,722 @@ +{ + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T07:38:28+00:00", + "source_file": "images/favicon.png", + "language_code": "pcm" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T07:38:39+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "pcm" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T07:39:03+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "pcm" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T07:39:26+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "pcm" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T07:39:38+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "pcm" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T07:39:52+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "pcm" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:40:14+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "pcm" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:40:40+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "pcm" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:40:52+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "pcm" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:40:54+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "pcm" + }, + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:40:57+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", + "language_code": "pcm" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:41:01+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "pcm" + }, + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:41:05+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", + "language_code": "pcm" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:41:11+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "pcm" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:41:21+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "pcm" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:41:28+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "pcm" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:41:34+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "pcm" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:41:41+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "pcm" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:41:48+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "pcm" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:41:52+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "pcm" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:41:53+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "pcm" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:42:00+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "pcm" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:42:10+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "pcm" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:42:13+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "pcm" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:42:17+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "pcm" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:42:20+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "pcm" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:42:22+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "pcm" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "pcm" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "pcm" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:42:28+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "pcm" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:42:31+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "pcm" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:42:32+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "pcm" + }, + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:42:34+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "pcm" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:42:37+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "pcm" + }, + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:42:38+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", + "language_code": "pcm" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:42:40+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "pcm" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:42:41+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "pcm" + }, + "1200px-Girl_and_cat.89bd70951181e86a.webp": { + "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", + "translation_date": "2026-01-16T07:42:43+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", + "language_code": "pcm" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:42:49+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "pcm" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:42:55+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "pcm" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:43:01+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "pcm" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:43:05+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "pcm" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:43:08+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "pcm" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:43:13+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "pcm" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:43:17+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "pcm" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:43:22+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "pcm" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:43:29+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "pcm" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:43:35+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "pcm" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:43:41+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "pcm" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:43:55+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "pcm" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:44:02+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "pcm" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:44:15+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "pcm" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:44:23+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "pcm" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:44:25+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "pcm" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:44:32+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "pcm" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:44:37+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "pcm" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:44:44+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "pcm" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:44:50+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "pcm" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:44:54+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "pcm" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:44:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "pcm" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:45:01+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "pcm" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:45:16+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "pcm" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:45:41+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "pcm" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:45:51+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "pcm" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:45:53+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "pcm" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:45:55+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "pcm" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:46:06+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "pcm" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:46:13+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "pcm" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:46:15+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", + "language_code": "pcm" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:46:22+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "pcm" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:46:38+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "pcm" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:46:47+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "pcm" + }, + "AND-OR-Tree.5592d2c70187f283.webp": { + "original_hash": "2674b6cf8f768491c6b5a167f272a002", + "translation_date": "2026-01-16T07:47:19+00:00", + "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", + "language_code": "pcm" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:47:48+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "pcm" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:48:01+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "pcm" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:48:09+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "pcm" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:48:19+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "pcm" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:48:47+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "pcm" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:49:06+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "pcm" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:49:10+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "pcm" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:49:12+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "pcm" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:49:15+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", + "language_code": "pcm" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:49:22+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "pcm" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:49:27+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "pcm" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:49:31+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "pcm" + }, + "ComputeGraphGrad.4626252c0de03507.webp": { + "original_hash": "b0bf679245a237b1e7785ae2357a5376", + "translation_date": "2026-01-16T07:49:36+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", + "language_code": "pcm" + }, + "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { + "original_hash": "11dd0fd77a272755d0ef5db9f71217da", + "translation_date": "2026-01-16T07:49:43+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", + "language_code": "pcm" + }, + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:49:47+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", + "language_code": "pcm" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:49:51+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "pcm" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:49:54+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "pcm" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:49:56+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "pcm" + }, + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:49:58+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "pcm" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:04+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "pcm" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:50:08+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", + "language_code": "pcm" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:13+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "pcm" + }, + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:50:17+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "pcm" + }, + "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { + "original_hash": "dd063fda04db937ab7210064af9d6151", + "translation_date": "2026-01-16T07:50:19+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.png", + "language_code": "pcm" + }, + "DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp": { + "original_hash": "2cc9ab0daf8e1af7071fbc9eaf84970b", + "translation_date": "2026-01-16T07:50:21+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", + "language_code": "pcm" + }, + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:50:22+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "language_code": "pcm" + }, + "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { + "original_hash": "7064cd71a562523998203c756842c96d", + "translation_date": "2026-01-16T07:50:22+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", + "language_code": "pcm" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:50:25+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "pcm" + }, + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:50:30+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "language_code": "pcm" + }, + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:50:46+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "language_code": "pcm" + }, + "ascii-character-map.18ed6aa7f3b0a7ff.webp": { + "original_hash": "afc5ff2601be320926d89f1ad897eda8", + "translation_date": "2026-01-16T07:50:59+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", + "language_code": "pcm" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:51:05+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "pcm" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:51:12+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "pcm" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:51:24+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "pcm" + }, + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:51:35+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", + "language_code": "pcm" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:51:48+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "pcm" + }, + "bahdanau-fig3.09ba2d37f202a6af.webp": { + "original_hash": "b5cfbb9cad3b0d3fbdcc63dcd2ed514f", + "translation_date": "2026-01-16T07:51:58+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", + "language_code": "pcm" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:52:07+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "pcm" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:52:16+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "pcm" + }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:52:26+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "pcm" + }, + "bot-ner.4b09235dbb0ad275.webp": { + "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", + "translation_date": "2026-01-16T07:52:41+00:00", + "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", + "language_code": "pcm" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:52:49+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "pcm" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:52:54+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "pcm" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:52:59+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "pcm" + }, + "embedding-classifier-example.b77f021a7ee67eee.webp": { + "original_hash": "0c4233111f66d9c6925af5b97f9519a0", + "translation_date": "2026-01-16T07:53:04+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", + "language_code": "pcm" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:53:09+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "pcm" + }, + "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { + "original_hash": "6e976f26b9bb4c7a021187e834132123", + "translation_date": "2026-01-16T07:53:14+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", + "language_code": "pcm" + } +} \ No newline at end of file diff --git a/translated_images/pcm/1200px-Girl_and_cat.89bd70951181e86a.webp b/translated_images/pcm/1200px-Girl_and_cat.89bd70951181e86a.webp new file mode 100644 index 00000000..47042c75 Binary files /dev/null and b/translated_images/pcm/1200px-Girl_and_cat.89bd70951181e86a.webp differ diff --git a/translated_images/pcm/AND-OR-Tree.5592d2c70187f283.webp b/translated_images/pcm/AND-OR-Tree.5592d2c70187f283.webp new file mode 100644 index 00000000..5300079b Binary files /dev/null and b/translated_images/pcm/AND-OR-Tree.5592d2c70187f283.webp differ diff --git a/translated_images/pcm/ComputeGraph.463c9d8ebdcb2215.webp b/translated_images/pcm/ComputeGraph.463c9d8ebdcb2215.webp new file mode 100644 index 00000000..69415f9d Binary files /dev/null and b/translated_images/pcm/ComputeGraph.463c9d8ebdcb2215.webp differ diff --git a/translated_images/pcm/ComputeGraphGrad.4626252c0de03507.webp b/translated_images/pcm/ComputeGraphGrad.4626252c0de03507.webp new file mode 100644 index 00000000..9d747348 Binary files /dev/null and b/translated_images/pcm/ComputeGraphGrad.4626252c0de03507.webp differ diff --git a/translated_images/pcm/CoreferenceResolution.861924d6d384a7d6.webp b/translated_images/pcm/CoreferenceResolution.861924d6d384a7d6.webp new file mode 100644 index 00000000..6c75a34b Binary files /dev/null and b/translated_images/pcm/CoreferenceResolution.861924d6d384a7d6.webp differ diff --git a/translated_images/pcm/Cross-Entropy-Loss.dc7ba633d2467ef3.webp b/translated_images/pcm/Cross-Entropy-Loss.dc7ba633d2467ef3.webp new file mode 100644 index 00000000..2f437d4e Binary files /dev/null and b/translated_images/pcm/Cross-Entropy-Loss.dc7ba633d2467ef3.webp differ diff --git a/translated_images/pcm/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp b/translated_images/pcm/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp new file mode 100644 index 00000000..222db344 Binary files /dev/null and b/translated_images/pcm/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp differ diff --git a/translated_images/pcm/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp b/translated_images/pcm/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp new file mode 100644 index 00000000..f3b973c5 Binary files /dev/null and b/translated_images/pcm/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp differ diff --git a/translated_images/pcm/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp b/translated_images/pcm/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp new file mode 100644 index 00000000..b8f4286a Binary files /dev/null and b/translated_images/pcm/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp differ diff --git a/translated_images/pcm/DIKW_Pyramid.94126f7d2bd8db5b.webp b/translated_images/pcm/DIKW_Pyramid.94126f7d2bd8db5b.webp new file mode 100644 index 00000000..71a4d1bb Binary files /dev/null and b/translated_images/pcm/DIKW_Pyramid.94126f7d2bd8db5b.webp differ diff --git a/translated_images/pcm/FeatureExtractionCNN.d9b456cbdae7cb64.webp b/translated_images/pcm/FeatureExtractionCNN.d9b456cbdae7cb64.webp new file mode 100644 index 00000000..9d847329 Binary files /dev/null and b/translated_images/pcm/FeatureExtractionCNN.d9b456cbdae7cb64.webp differ diff --git a/translated_images/pcm/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp b/translated_images/pcm/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp new file mode 100644 index 00000000..5c85b4ef Binary files /dev/null and b/translated_images/pcm/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp differ diff --git a/translated_images/pcm/NetLogo-Main.32653711ec1a01b3.webp b/translated_images/pcm/NetLogo-Main.32653711ec1a01b3.webp new file mode 100644 index 00000000..443c10c3 Binary files /dev/null and b/translated_images/pcm/NetLogo-Main.32653711ec1a01b3.webp differ diff --git a/translated_images/pcm/NetLogo-ModelLib.efe023afb4763c05.webp b/translated_images/pcm/NetLogo-ModelLib.efe023afb4763c05.webp new file mode 100644 index 00000000..6f2b374c Binary files /dev/null and b/translated_images/pcm/NetLogo-ModelLib.efe023afb4763c05.webp differ diff --git a/translated_images/pcm/NeuroArch.4e17cdba5e445721.webp b/translated_images/pcm/NeuroArch.4e17cdba5e445721.webp new file mode 100644 index 00000000..1496c9a9 Binary files /dev/null and b/translated_images/pcm/NeuroArch.4e17cdba5e445721.webp differ diff --git a/translated_images/pcm/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp b/translated_images/pcm/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp new file mode 100644 index 00000000..8ea6ec8f Binary files /dev/null and b/translated_images/pcm/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp differ diff --git a/translated_images/pcm/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp b/translated_images/pcm/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp new file mode 100644 index 00000000..c0fe757c Binary files /dev/null and b/translated_images/pcm/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp differ diff --git a/translated_images/pcm/Overfitting.408ad91cd90b4371.webp b/translated_images/pcm/Overfitting.408ad91cd90b4371.webp new file mode 100644 index 00000000..f0fe88a5 Binary files /dev/null and b/translated_images/pcm/Overfitting.408ad91cd90b4371.webp differ diff --git a/translated_images/pcm/Rosenblatt-wikipedia.294821b285ac796d.webp b/translated_images/pcm/Rosenblatt-wikipedia.294821b285ac796d.webp new file mode 100644 index 00000000..ee733c23 Binary files /dev/null and b/translated_images/pcm/Rosenblatt-wikipedia.294821b285ac796d.webp differ diff --git a/translated_images/pcm/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp b/translated_images/pcm/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp new file mode 100644 index 00000000..bb882b26 Binary files /dev/null and b/translated_images/pcm/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp differ diff --git a/translated_images/pcm/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp b/translated_images/pcm/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp new file mode 100644 index 00000000..ee032762 Binary files /dev/null and b/translated_images/pcm/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp differ diff --git a/translated_images/pcm/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp b/translated_images/pcm/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp new file mode 100644 index 00000000..52ce29a9 Binary files /dev/null and b/translated_images/pcm/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp differ diff --git a/translated_images/pcm/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp b/translated_images/pcm/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp new file mode 100644 index 00000000..fba04870 Binary files /dev/null and b/translated_images/pcm/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp differ diff --git a/translated_images/pcm/aae.9d418a990fc75bf9.webp b/translated_images/pcm/aae.9d418a990fc75bf9.webp new file mode 100644 index 00000000..c32e34d2 Binary files /dev/null and b/translated_images/pcm/aae.9d418a990fc75bf9.webp differ diff --git a/translated_images/pcm/activation-func.b4924007c7ce7764.webp b/translated_images/pcm/activation-func.b4924007c7ce7764.webp new file mode 100644 index 00000000..20087e11 Binary files /dev/null and b/translated_images/pcm/activation-func.b4924007c7ce7764.webp differ diff --git a/translated_images/pcm/adversarial-dog.d9fc7773b0142b89.webp b/translated_images/pcm/adversarial-dog.d9fc7773b0142b89.webp new file mode 100644 index 00000000..8816fc84 Binary files /dev/null and b/translated_images/pcm/adversarial-dog.d9fc7773b0142b89.webp differ diff --git a/translated_images/pcm/ai-computervision.6506ebebac3fbf76.webp b/translated_images/pcm/ai-computervision.6506ebebac3fbf76.webp new file mode 100644 index 00000000..fe4cca1b Binary files /dev/null and b/translated_images/pcm/ai-computervision.6506ebebac3fbf76.webp differ diff --git a/translated_images/pcm/ai-for-beginners.b354ca904b22cd70.webp b/translated_images/pcm/ai-for-beginners.b354ca904b22cd70.webp new file mode 100644 index 00000000..727555ba Binary files /dev/null and b/translated_images/pcm/ai-for-beginners.b354ca904b22cd70.webp differ diff --git a/translated_images/pcm/ai-intro.bf28d1ac4235881c.webp b/translated_images/pcm/ai-intro.bf28d1ac4235881c.webp new file mode 100644 index 00000000..6143ad1b Binary files /dev/null and b/translated_images/pcm/ai-intro.bf28d1ac4235881c.webp differ diff --git a/translated_images/pcm/ai-neuralnetworks.1c687ae40bc86e83.webp b/translated_images/pcm/ai-neuralnetworks.1c687ae40bc86e83.webp new file mode 100644 index 00000000..35ebbb69 Binary files /dev/null and b/translated_images/pcm/ai-neuralnetworks.1c687ae40bc86e83.webp differ diff --git a/translated_images/pcm/ai-nlp.b22dcb8ca4707cea.webp b/translated_images/pcm/ai-nlp.b22dcb8ca4707cea.webp new file mode 100644 index 00000000..5cef4561 Binary files /dev/null and b/translated_images/pcm/ai-nlp.b22dcb8ca4707cea.webp differ diff --git a/translated_images/pcm/ai-overview.0857791951d19500.webp b/translated_images/pcm/ai-overview.0857791951d19500.webp new file mode 100644 index 00000000..33f8fe45 Binary files /dev/null and b/translated_images/pcm/ai-overview.0857791951d19500.webp differ diff --git a/translated_images/pcm/ai-symbolic.715a30cb610411a6.webp b/translated_images/pcm/ai-symbolic.715a30cb610411a6.webp new file mode 100644 index 00000000..41bf7c13 Binary files /dev/null and b/translated_images/pcm/ai-symbolic.715a30cb610411a6.webp differ diff --git a/translated_images/pcm/arch-human.5d4d35f1bba3ab1c.webp b/translated_images/pcm/arch-human.5d4d35f1bba3ab1c.webp new file mode 100644 index 00000000..b7b833fb Binary files /dev/null and b/translated_images/pcm/arch-human.5d4d35f1bba3ab1c.webp differ diff --git a/translated_images/pcm/arch-kbs.3ec5c150b09fa8da.webp b/translated_images/pcm/arch-kbs.3ec5c150b09fa8da.webp new file mode 100644 index 00000000..825d4d2a Binary files /dev/null and b/translated_images/pcm/arch-kbs.3ec5c150b09fa8da.webp differ diff --git a/translated_images/pcm/artneuron.1a5daa88d20ebe6f.webp b/translated_images/pcm/artneuron.1a5daa88d20ebe6f.webp new file mode 100644 index 00000000..9e300afa Binary files /dev/null and b/translated_images/pcm/artneuron.1a5daa88d20ebe6f.webp differ diff --git a/translated_images/pcm/ascii-character-map.18ed6aa7f3b0a7ff.webp b/translated_images/pcm/ascii-character-map.18ed6aa7f3b0a7ff.webp new file mode 100644 index 00000000..0ed792b9 Binary files /dev/null and b/translated_images/pcm/ascii-character-map.18ed6aa7f3b0a7ff.webp differ diff --git a/translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp b/translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp new file mode 100644 index 00000000..3471c567 Binary files /dev/null and b/translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp differ diff --git a/translated_images/pcm/bag-of-words-example.606fc1738f1d7ba9.webp b/translated_images/pcm/bag-of-words-example.606fc1738f1d7ba9.webp new file mode 100644 index 00000000..065c5964 Binary files /dev/null and b/translated_images/pcm/bag-of-words-example.606fc1738f1d7ba9.webp differ diff --git a/translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp b/translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp new file mode 100644 index 00000000..ad431488 Binary files /dev/null and b/translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp differ diff --git a/translated_images/pcm/bot-ner.4b09235dbb0ad275.webp b/translated_images/pcm/bot-ner.4b09235dbb0ad275.webp new file mode 100644 index 00000000..e86358db Binary files /dev/null and b/translated_images/pcm/bot-ner.4b09235dbb0ad275.webp differ diff --git a/translated_images/pcm/bow.3811869cff59368d.webp b/translated_images/pcm/bow.3811869cff59368d.webp new file mode 100644 index 00000000..756af41a Binary files /dev/null and b/translated_images/pcm/bow.3811869cff59368d.webp differ diff --git a/translated_images/pcm/braille-result.46530fea020b03c7.webp b/translated_images/pcm/braille-result.46530fea020b03c7.webp new file mode 100644 index 00000000..0235d8f6 Binary files /dev/null and b/translated_images/pcm/braille-result.46530fea020b03c7.webp differ diff --git a/translated_images/pcm/braille-symbols.0159185ab69d5339.webp b/translated_images/pcm/braille-symbols.0159185ab69d5339.webp new file mode 100644 index 00000000..c96c4b7a Binary files /dev/null and b/translated_images/pcm/braille-symbols.0159185ab69d5339.webp differ diff --git a/translated_images/pcm/braille.341962ff76b1bd70.webp b/translated_images/pcm/braille.341962ff76b1bd70.webp new file mode 100644 index 00000000..6751696b Binary files /dev/null and b/translated_images/pcm/braille.341962ff76b1bd70.webp differ diff --git a/translated_images/pcm/cartpole.f52a67f27e058170.webp b/translated_images/pcm/cartpole.f52a67f27e058170.webp new file mode 100644 index 00000000..848d3ee7 Binary files /dev/null and b/translated_images/pcm/cartpole.f52a67f27e058170.webp differ diff --git a/translated_images/pcm/catsdogsdataset.a7aff8e6085fd3f0.webp b/translated_images/pcm/catsdogsdataset.a7aff8e6085fd3f0.webp new file mode 100644 index 00000000..a9e1432a Binary files /dev/null and b/translated_images/pcm/catsdogsdataset.a7aff8e6085fd3f0.webp differ diff --git a/translated_images/pcm/clip-arch.b3dbf20b4e8ed8be.webp b/translated_images/pcm/clip-arch.b3dbf20b4e8ed8be.webp new file mode 100644 index 00000000..13b5a9a6 Binary files /dev/null and b/translated_images/pcm/clip-arch.b3dbf20b4e8ed8be.webp differ diff --git a/translated_images/pcm/clip-class.3af42ef0b2b19369.webp b/translated_images/pcm/clip-class.3af42ef0b2b19369.webp new file mode 100644 index 00000000..13b5a9a6 Binary files /dev/null and b/translated_images/pcm/clip-class.3af42ef0b2b19369.webp differ diff --git a/translated_images/pcm/cnn-pyramid.85915455759ef0ce.webp b/translated_images/pcm/cnn-pyramid.85915455759ef0ce.webp new file mode 100644 index 00000000..f854b886 Binary files /dev/null and b/translated_images/pcm/cnn-pyramid.85915455759ef0ce.webp differ diff --git a/translated_images/pcm/coco-examples.71bc60380fa6cceb.webp b/translated_images/pcm/coco-examples.71bc60380fa6cceb.webp new file mode 100644 index 00000000..f92f8f3a Binary files /dev/null and b/translated_images/pcm/coco-examples.71bc60380fa6cceb.webp differ diff --git a/translated_images/pcm/convolutionExample.634615d5ff7081e0.webp b/translated_images/pcm/convolutionExample.634615d5ff7081e0.webp new file mode 100644 index 00000000..571cbb9c Binary files /dev/null and b/translated_images/pcm/convolutionExample.634615d5ff7081e0.webp differ diff --git a/translated_images/pcm/data.50b2a9d5484bdbf0.webp b/translated_images/pcm/data.50b2a9d5484bdbf0.webp new file mode 100644 index 00000000..69ca4aaa Binary files /dev/null and b/translated_images/pcm/data.50b2a9d5484bdbf0.webp differ diff --git a/translated_images/pcm/dcgan_generator.b500988ec2bc8ba5.webp b/translated_images/pcm/dcgan_generator.b500988ec2bc8ba5.webp new file mode 100644 index 00000000..5d7a8b77 Binary files /dev/null and b/translated_images/pcm/dcgan_generator.b500988ec2bc8ba5.webp differ diff --git a/translated_images/pcm/dog-from-unsplash.426f9fbca2febc93.webp b/translated_images/pcm/dog-from-unsplash.426f9fbca2febc93.webp new file mode 100644 index 00000000..2d2fef68 Binary files /dev/null and b/translated_images/pcm/dog-from-unsplash.426f9fbca2febc93.webp differ diff --git a/translated_images/pcm/dsh_age.d212a30d4e54fb5f.webp b/translated_images/pcm/dsh_age.d212a30d4e54fb5f.webp new file mode 100644 index 00000000..98793010 Binary files /dev/null and b/translated_images/pcm/dsh_age.d212a30d4e54fb5f.webp differ diff --git a/translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp b/translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp new file mode 100644 index 00000000..b43e8f57 Binary files /dev/null and b/translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp differ diff --git a/translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp b/translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp new file mode 100644 index 00000000..9cf8b91a Binary files /dev/null and b/translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp differ diff --git a/translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp b/translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp new file mode 100644 index 00000000..d7d54c4f Binary files /dev/null and b/translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp differ diff --git a/translated_images/pcm/f-rcnn.3cda6d9bb4188875.webp b/translated_images/pcm/f-rcnn.3cda6d9bb4188875.webp new file mode 100644 index 00000000..025e2df9 Binary files /dev/null and b/translated_images/pcm/f-rcnn.3cda6d9bb4188875.webp differ diff --git a/translated_images/pcm/faster-rcnn.8d46c099b87ef30a.webp b/translated_images/pcm/faster-rcnn.8d46c099b87ef30a.webp new file mode 100644 index 00000000..af895633 Binary files /dev/null and b/translated_images/pcm/faster-rcnn.8d46c099b87ef30a.webp differ diff --git a/translated_images/pcm/favicon.37b561214b36d454.webp b/translated_images/pcm/favicon.37b561214b36d454.webp new file mode 100644 index 00000000..48a53960 Binary files /dev/null and b/translated_images/pcm/favicon.37b561214b36d454.webp differ diff --git a/translated_images/pcm/features.6291f9c7ba3a0b95.webp b/translated_images/pcm/features.6291f9c7ba3a0b95.webp new file mode 100644 index 00000000..03679af2 Binary files /dev/null and b/translated_images/pcm/features.6291f9c7ba3a0b95.webp differ diff --git a/translated_images/pcm/filter-horiz.59b80ed4feb946ef.webp b/translated_images/pcm/filter-horiz.59b80ed4feb946ef.webp new file mode 100644 index 00000000..a32157db Binary files /dev/null and b/translated_images/pcm/filter-horiz.59b80ed4feb946ef.webp differ diff --git a/translated_images/pcm/filter-vert.b7148390ca0bc356.webp b/translated_images/pcm/filter-vert.b7148390ca0bc356.webp new file mode 100644 index 00000000..61f86b5d Binary files /dev/null and b/translated_images/pcm/filter-vert.b7148390ca0bc356.webp differ diff --git a/translated_images/pcm/frame-difference.706f805491a0883c.webp b/translated_images/pcm/frame-difference.706f805491a0883c.webp new file mode 100644 index 00000000..b893b702 Binary files /dev/null and b/translated_images/pcm/frame-difference.706f805491a0883c.webp differ diff --git a/translated_images/pcm/gan_arch_detail.46b95fd366f8e543.webp b/translated_images/pcm/gan_arch_detail.46b95fd366f8e543.webp new file mode 100644 index 00000000..bafcf0ed Binary files /dev/null and b/translated_images/pcm/gan_arch_detail.46b95fd366f8e543.webp differ diff --git a/translated_images/pcm/gan_architecture.8f3a5ab62b8d5d69.webp b/translated_images/pcm/gan_architecture.8f3a5ab62b8d5d69.webp new file mode 100644 index 00000000..1f7d4e99 Binary files /dev/null and b/translated_images/pcm/gan_architecture.8f3a5ab62b8d5d69.webp differ diff --git a/translated_images/pcm/history-of-ai.7e83efa70b537f5a.webp b/translated_images/pcm/history-of-ai.7e83efa70b537f5a.webp new file mode 100644 index 00000000..556b8fc4 Binary files /dev/null and b/translated_images/pcm/history-of-ai.7e83efa70b537f5a.webp differ diff --git a/translated_images/pcm/ideal-cat-loop.999fbb8ff306e044.webp b/translated_images/pcm/ideal-cat-loop.999fbb8ff306e044.webp new file mode 100644 index 00000000..2a68794e Binary files /dev/null and b/translated_images/pcm/ideal-cat-loop.999fbb8ff306e044.webp differ diff --git a/translated_images/pcm/ideal-cat.203dd4597643d6b0.webp b/translated_images/pcm/ideal-cat.203dd4597643d6b0.webp new file mode 100644 index 00000000..a8d167b1 Binary files /dev/null and b/translated_images/pcm/ideal-cat.203dd4597643d6b0.webp differ diff --git a/translated_images/pcm/ideal-zebra.7f70e8b54ee15a7a.webp b/translated_images/pcm/ideal-zebra.7f70e8b54ee15a7a.webp new file mode 100644 index 00000000..be349483 Binary files /dev/null and b/translated_images/pcm/ideal-zebra.7f70e8b54ee15a7a.webp differ diff --git a/translated_images/pcm/image.896e8254a2c60d45.webp b/translated_images/pcm/image.896e8254a2c60d45.webp new file mode 100644 index 00000000..d2b9d3ce Binary files /dev/null and b/translated_images/pcm/image.896e8254a2c60d45.webp differ diff --git a/translated_images/pcm/inception.a6605b85bcbc6f52.webp b/translated_images/pcm/inception.a6605b85bcbc6f52.webp new file mode 100644 index 00000000..0039c09f Binary files /dev/null and b/translated_images/pcm/inception.a6605b85bcbc6f52.webp differ diff --git a/translated_images/pcm/instance_vs_semantic.eee9812bebf8cd45.webp b/translated_images/pcm/instance_vs_semantic.eee9812bebf8cd45.webp new file mode 100644 index 00000000..ced020a9 Binary files /dev/null and b/translated_images/pcm/instance_vs_semantic.eee9812bebf8cd45.webp differ diff --git a/translated_images/pcm/iou_equation.9a4751d40fff4e11.webp b/translated_images/pcm/iou_equation.9a4751d40fff4e11.webp new file mode 100644 index 00000000..a12bbabd Binary files /dev/null and b/translated_images/pcm/iou_equation.9a4751d40fff4e11.webp differ diff --git a/translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp b/translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp new file mode 100644 index 00000000..5cb84cba Binary files /dev/null and b/translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp differ diff --git a/translated_images/pcm/knowledge-spectrum.b60df631852c0217.webp b/translated_images/pcm/knowledge-spectrum.b60df631852c0217.webp new file mode 100644 index 00000000..03b883fe Binary files /dev/null and b/translated_images/pcm/knowledge-spectrum.b60df631852c0217.webp differ diff --git a/translated_images/pcm/lmfilters.ea9e4868a82cf74c.webp b/translated_images/pcm/lmfilters.ea9e4868a82cf74c.webp new file mode 100644 index 00000000..73254d4b Binary files /dev/null and b/translated_images/pcm/lmfilters.ea9e4868a82cf74c.webp differ diff --git a/translated_images/pcm/ml-for-beginners.9e4fed176fd5817d.webp b/translated_images/pcm/ml-for-beginners.9e4fed176fd5817d.webp new file mode 100644 index 00000000..4f1bc91b Binary files /dev/null and b/translated_images/pcm/ml-for-beginners.9e4fed176fd5817d.webp differ diff --git a/translated_images/pcm/mountaincar.f7b7a7f6d4f9933b.webp b/translated_images/pcm/mountaincar.f7b7a7f6d4f9933b.webp new file mode 100644 index 00000000..8773c19e Binary files /dev/null and b/translated_images/pcm/mountaincar.f7b7a7f6d4f9933b.webp differ diff --git a/translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp b/translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp new file mode 100644 index 00000000..5cad10d8 Binary files /dev/null and b/translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp differ diff --git a/translated_images/pcm/naive-detection.e7f1ba220ccd08c6.webp b/translated_images/pcm/naive-detection.e7f1ba220ccd08c6.webp new file mode 100644 index 00000000..6bf3e9da Binary files /dev/null and b/translated_images/pcm/naive-detection.e7f1ba220ccd08c6.webp differ diff --git a/translated_images/pcm/navi.2f20b727910110ea.webp b/translated_images/pcm/navi.2f20b727910110ea.webp new file mode 100644 index 00000000..e9254c25 Binary files /dev/null and b/translated_images/pcm/navi.2f20b727910110ea.webp differ diff --git a/translated_images/pcm/netout.1eb15eb76fd76731.webp b/translated_images/pcm/netout.1eb15eb76fd76731.webp new file mode 100644 index 00000000..dca51483 Binary files /dev/null and b/translated_images/pcm/netout.1eb15eb76fd76731.webp differ diff --git a/translated_images/pcm/offset-sequence-representation.eb73fcefb29b46ee.webp b/translated_images/pcm/offset-sequence-representation.eb73fcefb29b46ee.webp new file mode 100644 index 00000000..f5455033 Binary files /dev/null and b/translated_images/pcm/offset-sequence-representation.eb73fcefb29b46ee.webp differ diff --git a/translated_images/pcm/optical.1f4a94464579a83a.webp b/translated_images/pcm/optical.1f4a94464579a83a.webp new file mode 100644 index 00000000..c37dddad Binary files /dev/null and b/translated_images/pcm/optical.1f4a94464579a83a.webp differ diff --git a/translated_images/pcm/original-dog.8f68a67d2fe0911f.webp b/translated_images/pcm/original-dog.8f68a67d2fe0911f.webp new file mode 100644 index 00000000..2a002703 Binary files /dev/null and b/translated_images/pcm/original-dog.8f68a67d2fe0911f.webp differ diff --git a/translated_images/pcm/overfit.a0bd57f717c15769.webp b/translated_images/pcm/overfit.a0bd57f717c15769.webp new file mode 100644 index 00000000..8e30e2ed Binary files /dev/null and b/translated_images/pcm/overfit.a0bd57f717c15769.webp differ diff --git a/translated_images/pcm/overfit1.f24b71c6f652e59e.webp b/translated_images/pcm/overfit1.f24b71c6f652e59e.webp new file mode 100644 index 00000000..de604b48 Binary files /dev/null and b/translated_images/pcm/overfit1.f24b71c6f652e59e.webp differ diff --git a/translated_images/pcm/overfit2.131f5800ae10ca5e.webp b/translated_images/pcm/overfit2.131f5800ae10ca5e.webp new file mode 100644 index 00000000..8dd690b9 Binary files /dev/null and b/translated_images/pcm/overfit2.131f5800ae10ca5e.webp differ diff --git a/translated_images/pcm/palm-movement.341495f0e9c47da3.webp b/translated_images/pcm/palm-movement.341495f0e9c47da3.webp new file mode 100644 index 00000000..0071936c Binary files /dev/null and b/translated_images/pcm/palm-movement.341495f0e9c47da3.webp differ diff --git a/translated_images/pcm/photo-cat.8c8e8fb760ffe457.webp b/translated_images/pcm/photo-cat.8c8e8fb760ffe457.webp new file mode 100644 index 00000000..2998a349 Binary files /dev/null and b/translated_images/pcm/photo-cat.8c8e8fb760ffe457.webp differ diff --git a/translated_images/pcm/pos-embedding.e41ce9b6cf6078af.webp b/translated_images/pcm/pos-embedding.e41ce9b6cf6078af.webp new file mode 100644 index 00000000..cfb3794f Binary files /dev/null and b/translated_images/pcm/pos-embedding.e41ce9b6cf6078af.webp differ diff --git a/translated_images/pcm/protege.274177ceeac13b38.webp b/translated_images/pcm/protege.274177ceeac13b38.webp new file mode 100644 index 00000000..fa651853 Binary files /dev/null and b/translated_images/pcm/protege.274177ceeac13b38.webp differ diff --git a/translated_images/pcm/r-fcn.13eb88158b99a3da.webp b/translated_images/pcm/r-fcn.13eb88158b99a3da.webp new file mode 100644 index 00000000..57f51a20 Binary files /dev/null and b/translated_images/pcm/r-fcn.13eb88158b99a3da.webp differ diff --git a/translated_images/pcm/rcnn1.cae407020dfb1d1f.webp b/translated_images/pcm/rcnn1.cae407020dfb1d1f.webp new file mode 100644 index 00000000..1c949129 Binary files /dev/null and b/translated_images/pcm/rcnn1.cae407020dfb1d1f.webp differ diff --git a/translated_images/pcm/rcnn2.2d9530bb83516484.webp b/translated_images/pcm/rcnn2.2d9530bb83516484.webp new file mode 100644 index 00000000..1c2fbf67 Binary files /dev/null and b/translated_images/pcm/rcnn2.2d9530bb83516484.webp differ diff --git a/translated_images/pcm/resnet-block.aba4ccbcc0944434.webp b/translated_images/pcm/resnet-block.aba4ccbcc0944434.webp new file mode 100644 index 00000000..5dee145d Binary files /dev/null and b/translated_images/pcm/resnet-block.aba4ccbcc0944434.webp differ diff --git a/translated_images/pcm/rnn-anatomy.79ee3f3920b3294b.webp b/translated_images/pcm/rnn-anatomy.79ee3f3920b3294b.webp new file mode 100644 index 00000000..5c5a3547 Binary files /dev/null and b/translated_images/pcm/rnn-anatomy.79ee3f3920b3294b.webp differ diff --git a/translated_images/pcm/rnn-generate-inf.5168dc65e0370eea.webp b/translated_images/pcm/rnn-generate-inf.5168dc65e0370eea.webp new file mode 100644 index 00000000..191d8694 Binary files /dev/null and b/translated_images/pcm/rnn-generate-inf.5168dc65e0370eea.webp differ diff --git a/translated_images/pcm/rnn-generate.56c54afb52f9781d.webp b/translated_images/pcm/rnn-generate.56c54afb52f9781d.webp new file mode 100644 index 00000000..570917d9 Binary files /dev/null and b/translated_images/pcm/rnn-generate.56c54afb52f9781d.webp differ diff --git a/translated_images/pcm/rnn.27f5c29c53d727b5.webp b/translated_images/pcm/rnn.27f5c29c53d727b5.webp new file mode 100644 index 00000000..1952428d Binary files /dev/null and b/translated_images/pcm/rnn.27f5c29c53d727b5.webp differ diff --git a/translated_images/pcm/segm.92442f2cb42ff4fa.webp b/translated_images/pcm/segm.92442f2cb42ff4fa.webp new file mode 100644 index 00000000..1478189f Binary files /dev/null and b/translated_images/pcm/segm.92442f2cb42ff4fa.webp differ diff --git a/translated_images/pcm/segnet.87377542aa5a8b76.webp b/translated_images/pcm/segnet.87377542aa5a8b76.webp new file mode 100644 index 00000000..ba2f2733 Binary files /dev/null and b/translated_images/pcm/segnet.87377542aa5a8b76.webp differ diff --git a/translated_images/pcm/style.5293e85e077ab22c.webp b/translated_images/pcm/style.5293e85e077ab22c.webp new file mode 100644 index 00000000..39af2a0e Binary files /dev/null and b/translated_images/pcm/style.5293e85e077ab22c.webp differ diff --git a/translated_images/pcm/synapse-wikipedia.ed20a9e4726ea1c6.webp b/translated_images/pcm/synapse-wikipedia.ed20a9e4726ea1c6.webp new file mode 100644 index 00000000..b698b3a9 Binary files /dev/null and b/translated_images/pcm/synapse-wikipedia.ed20a9e4726ea1c6.webp differ diff --git a/translated_images/pcm/transformer-layer.905e14747ca4e7d5.webp b/translated_images/pcm/transformer-layer.905e14747ca4e7d5.webp new file mode 100644 index 00000000..60cb4250 Binary files /dev/null and b/translated_images/pcm/transformer-layer.905e14747ca4e7d5.webp differ diff --git a/translated_images/pcm/triplet-complex.32094972c7b4441b.webp b/translated_images/pcm/triplet-complex.32094972c7b4441b.webp new file mode 100644 index 00000000..15770cf3 Binary files /dev/null and b/translated_images/pcm/triplet-complex.32094972c7b4441b.webp differ diff --git a/translated_images/pcm/triplet.4b9b332587593298.webp b/translated_images/pcm/triplet.4b9b332587593298.webp new file mode 100644 index 00000000..e855d539 Binary files /dev/null and b/translated_images/pcm/triplet.4b9b332587593298.webp differ diff --git a/translated_images/pcm/turing-test-evol.4184696701293ead.webp b/translated_images/pcm/turing-test-evol.4184696701293ead.webp new file mode 100644 index 00000000..624a30a7 Binary files /dev/null and b/translated_images/pcm/turing-test-evol.4184696701293ead.webp differ diff --git a/translated_images/pcm/unet.3adb555bf39d3657.webp b/translated_images/pcm/unet.3adb555bf39d3657.webp new file mode 100644 index 00000000..362720e3 Binary files /dev/null and b/translated_images/pcm/unet.3adb555bf39d3657.webp differ diff --git a/translated_images/pcm/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp b/translated_images/pcm/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp new file mode 100644 index 00000000..25931859 Binary files /dev/null and b/translated_images/pcm/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp differ diff --git a/translated_images/pcm/vae.464c465a5b6a9e25.webp b/translated_images/pcm/vae.464c465a5b6a9e25.webp new file mode 100644 index 00000000..a194cfe7 Binary files /dev/null and b/translated_images/pcm/vae.464c465a5b6a9e25.webp differ diff --git a/translated_images/pcm/vaemnist-diag.694315f775d5d666.webp b/translated_images/pcm/vaemnist-diag.694315f775d5d666.webp new file mode 100644 index 00000000..49b53b6d Binary files /dev/null and b/translated_images/pcm/vaemnist-diag.694315f775d5d666.webp differ diff --git a/translated_images/pcm/vaemnist.cab9e602dc08dc50.webp b/translated_images/pcm/vaemnist.cab9e602dc08dc50.webp new file mode 100644 index 00000000..2e523d00 Binary files /dev/null and b/translated_images/pcm/vaemnist.cab9e602dc08dc50.webp differ diff --git a/translated_images/pcm/vgg-16-arch.64ff2137f50dd49f.webp b/translated_images/pcm/vgg-16-arch.64ff2137f50dd49f.webp new file mode 100644 index 00000000..58ee44dd Binary files /dev/null and b/translated_images/pcm/vgg-16-arch.64ff2137f50dd49f.webp differ diff --git a/translated_images/pcm/vgg-16-arch1.d901a5583b3a51ba.webp b/translated_images/pcm/vgg-16-arch1.d901a5583b3a51ba.webp new file mode 100644 index 00000000..7efaed10 Binary files /dev/null and b/translated_images/pcm/vgg-16-arch1.d901a5583b3a51ba.webp differ diff --git a/translated_images/pcm/vqgan.5027fe05051dfa31.webp b/translated_images/pcm/vqgan.5027fe05051dfa31.webp new file mode 100644 index 00000000..2060ed67 Binary files /dev/null and b/translated_images/pcm/vqgan.5027fe05051dfa31.webp differ diff --git a/translated_images/pcm/yolo.a2648ec82ee8bb4e.webp b/translated_images/pcm/yolo.a2648ec82ee8bb4e.webp new file mode 100644 index 00000000..3b5c3333 Binary files /dev/null and b/translated_images/pcm/yolo.a2648ec82ee8bb4e.webp differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe457.et.jpg b/translated_images/photo-cat.8c8e8fb760ffe457.et.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe457.et.jpg and /dev/null differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe457.pcm.jpg b/translated_images/photo-cat.8c8e8fb760ffe457.pcm.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe457.pcm.jpg and /dev/null differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe457.te.jpg b/translated_images/photo-cat.8c8e8fb760ffe457.te.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe457.te.jpg and /dev/null differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.et.jpg b/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.et.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.et.jpg and /dev/null differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.pcm.jpg b/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.pcm.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.pcm.jpg and /dev/null differ diff --git a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.te.jpg b/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.te.jpg deleted file mode 100644 index 776f24aa..00000000 Binary files a/translated_images/photo-cat.8c8e8fb760ffe45725c5b9f6b0d954e9bf114475c01c55adf0303982851b7eae.te.jpg and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078af.et.png b/translated_images/pos-embedding.e41ce9b6cf6078af.et.png deleted file mode 100644 index 9b5d64b1..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078af.et.png and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078af.pcm.png b/translated_images/pos-embedding.e41ce9b6cf6078af.pcm.png deleted file mode 100644 index 3e6a9b48..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078af.pcm.png and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078af.te.png b/translated_images/pos-embedding.e41ce9b6cf6078af.te.png deleted file mode 100644 index ab33864b..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078af.te.png and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.et.png b/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.et.png deleted file mode 100644 index 9b5d64b1..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.et.png and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.pcm.png b/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.pcm.png deleted file mode 100644 index 3e6a9b48..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.pcm.png and /dev/null differ diff --git a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.te.png b/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.te.png deleted file mode 100644 index ab33864b..00000000 Binary files a/translated_images/pos-embedding.e41ce9b6cf6078afd28da02f27e33ac7026ed4c156491df7ad9aa96be7c194bb.te.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38.et.png b/translated_images/protege.274177ceeac13b38.et.png deleted file mode 100644 index 8e128595..00000000 Binary files a/translated_images/protege.274177ceeac13b38.et.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38.pcm.png b/translated_images/protege.274177ceeac13b38.pcm.png deleted file mode 100644 index 0c8dadb3..00000000 Binary files a/translated_images/protege.274177ceeac13b38.pcm.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38.te.png b/translated_images/protege.274177ceeac13b38.te.png deleted file mode 100644 index fc77d003..00000000 Binary files a/translated_images/protege.274177ceeac13b38.te.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.et.png b/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.et.png deleted file mode 100644 index 8e128595..00000000 Binary files a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.et.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.pcm.png b/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.pcm.png deleted file mode 100644 index 0c8dadb3..00000000 Binary files a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.pcm.png and /dev/null differ diff --git a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.te.png b/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.te.png deleted file mode 100644 index fc77d003..00000000 Binary files a/translated_images/protege.274177ceeac13b38094bc425073776bb0d2525620ad6261b9d9760ebd2a8e322.te.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da.et.png b/translated_images/r-fcn.13eb88158b99a3da.et.png deleted file mode 100644 index 36e24cc6..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da.et.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da.pcm.png b/translated_images/r-fcn.13eb88158b99a3da.pcm.png deleted file mode 100644 index c85d098f..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da.pcm.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da.te.png b/translated_images/r-fcn.13eb88158b99a3da.te.png deleted file mode 100644 index 02234168..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da.te.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.et.png b/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.et.png deleted file mode 100644 index 36e24cc6..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.et.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.pcm.png b/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.pcm.png deleted file mode 100644 index c85d098f..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.pcm.png and /dev/null differ diff --git a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.te.png b/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.te.png deleted file mode 100644 index 02234168..00000000 Binary files a/translated_images/r-fcn.13eb88158b99a3da50fa2787a6be5cb310d47f0e9655cc93a1090dc7aab338d1.te.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1f.et.png b/translated_images/rcnn1.cae407020dfb1d1f.et.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1f.et.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1f.pcm.png b/translated_images/rcnn1.cae407020dfb1d1f.pcm.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1f.pcm.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1f.te.png b/translated_images/rcnn1.cae407020dfb1d1f.te.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1f.te.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.et.png b/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.et.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.et.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.pcm.png b/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.pcm.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.pcm.png and /dev/null differ diff --git a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.te.png b/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.te.png deleted file mode 100644 index 50f70d5b..00000000 Binary files a/translated_images/rcnn1.cae407020dfb1d1fb572656e44f75cd6c512cc220591c116c506652c10e47f26.te.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484.et.png b/translated_images/rcnn2.2d9530bb83516484.et.png deleted file mode 100644 index d4f09025..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484.et.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484.pcm.png b/translated_images/rcnn2.2d9530bb83516484.pcm.png deleted file mode 100644 index b095e5d7..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484.pcm.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484.te.png b/translated_images/rcnn2.2d9530bb83516484.te.png deleted file mode 100644 index 7de4e6b4..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484.te.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.et.png b/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.et.png deleted file mode 100644 index d4f09025..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.et.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.pcm.png b/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.pcm.png deleted file mode 100644 index b095e5d7..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.pcm.png and /dev/null differ diff --git a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.te.png b/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.te.png deleted file mode 100644 index 7de4e6b4..00000000 Binary files a/translated_images/rcnn2.2d9530bb83516484ec65b250c22dbf37d3d23244f32864ebcb91d98fe7c3112c.te.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc0944434.et.png b/translated_images/resnet-block.aba4ccbcc0944434.et.png deleted file mode 100644 index 12d09dbe..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc0944434.et.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc0944434.pcm.png b/translated_images/resnet-block.aba4ccbcc0944434.pcm.png deleted file mode 100644 index 72a8bc50..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc0944434.pcm.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc0944434.te.png b/translated_images/resnet-block.aba4ccbcc0944434.te.png deleted file mode 100644 index 28f744d1..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc0944434.te.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.et.png b/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.et.png deleted file mode 100644 index 12d09dbe..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.et.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.pcm.png b/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.pcm.png deleted file mode 100644 index 72a8bc50..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.pcm.png and /dev/null differ diff --git a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.te.png b/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.te.png deleted file mode 100644 index 28f744d1..00000000 Binary files a/translated_images/resnet-block.aba4ccbcc094443477d7bee189d44fed695c852d710a702462d6b809155d959a.te.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294b.et.png b/translated_images/rnn-anatomy.79ee3f3920b3294b.et.png deleted file mode 100644 index ff0fcadc..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294b.et.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294b.pcm.png b/translated_images/rnn-anatomy.79ee3f3920b3294b.pcm.png deleted file mode 100644 index d01c752d..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294b.pcm.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294b.te.png b/translated_images/rnn-anatomy.79ee3f3920b3294b.te.png deleted file mode 100644 index 00fb6832..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294b.te.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.et.png b/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.et.png deleted file mode 100644 index ff0fcadc..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.et.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.pcm.png b/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.pcm.png deleted file mode 100644 index d01c752d..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.pcm.png and /dev/null differ diff --git a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.te.png b/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.te.png deleted file mode 100644 index 00fb6832..00000000 Binary files a/translated_images/rnn-anatomy.79ee3f3920b3294bd52e9543ef36102dbca3cecf6d4d78d8c63bf0bbc95fdc90.te.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eea.et.png b/translated_images/rnn-generate-inf.5168dc65e0370eea.et.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eea.et.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eea.pcm.png b/translated_images/rnn-generate-inf.5168dc65e0370eea.pcm.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eea.pcm.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eea.te.png b/translated_images/rnn-generate-inf.5168dc65e0370eea.te.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eea.te.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.et.png b/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.et.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.et.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.pcm.png b/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.pcm.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.pcm.png and /dev/null differ diff --git a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.te.png b/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.te.png deleted file mode 100644 index 0498e867..00000000 Binary files a/translated_images/rnn-generate-inf.5168dc65e0370eeab36f83885ba6b5bf56265698de5ddbd8648dc3653e1f0b9b.te.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d.et.png b/translated_images/rnn-generate.56c54afb52f9781d.et.png deleted file mode 100644 index ae172935..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d.et.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d.pcm.png b/translated_images/rnn-generate.56c54afb52f9781d.pcm.png deleted file mode 100644 index 833a794b..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d.pcm.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d.te.png b/translated_images/rnn-generate.56c54afb52f9781d.te.png deleted file mode 100644 index 3ccd183c..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d.te.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.et.png b/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.et.png deleted file mode 100644 index ae172935..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.et.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.pcm.png b/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.pcm.png deleted file mode 100644 index 833a794b..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.pcm.png and /dev/null differ diff --git a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.te.png b/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.te.png deleted file mode 100644 index 3ccd183c..00000000 Binary files a/translated_images/rnn-generate.56c54afb52f9781d63a7c16ea9c1b86cb70e6e1eae6a742b56b7b37468576b17.te.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b5.et.png b/translated_images/rnn.27f5c29c53d727b5.et.png deleted file mode 100644 index a414a8ef..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b5.et.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b5.pcm.png b/translated_images/rnn.27f5c29c53d727b5.pcm.png deleted file mode 100644 index 58fe2ea0..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b5.pcm.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b5.te.png b/translated_images/rnn.27f5c29c53d727b5.te.png deleted file mode 100644 index 3735f7f6..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b5.te.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.et.png b/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.et.png deleted file mode 100644 index a414a8ef..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.et.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.pcm.png b/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.pcm.png deleted file mode 100644 index 58fe2ea0..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.pcm.png and /dev/null differ diff --git a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.te.png b/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.te.png deleted file mode 100644 index 3735f7f6..00000000 Binary files a/translated_images/rnn.27f5c29c53d727b546ad3961637a267f0fe9ec5ab01f2a26a853c92fcefbb574.te.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa.et.png b/translated_images/segm.92442f2cb42ff4fa.et.png deleted file mode 100644 index 4b763bdb..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa.et.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa.pcm.png b/translated_images/segm.92442f2cb42ff4fa.pcm.png deleted file mode 100644 index 841434dc..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa.pcm.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa.te.png b/translated_images/segm.92442f2cb42ff4fa.te.png deleted file mode 100644 index 124d6096..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa.te.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.et.png b/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.et.png deleted file mode 100644 index 4b763bdb..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.et.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.pcm.png b/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.pcm.png deleted file mode 100644 index 841434dc..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.pcm.png and /dev/null differ diff --git a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.te.png b/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.te.png deleted file mode 100644 index 124d6096..00000000 Binary files a/translated_images/segm.92442f2cb42ff4fa650fee858a3a02f55cf46825d9602115130e9e95a52a8526.te.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76.et.png b/translated_images/segnet.87377542aa5a8b76.et.png deleted file mode 100644 index 282097c9..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76.et.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76.pcm.png b/translated_images/segnet.87377542aa5a8b76.pcm.png deleted file mode 100644 index 2c10c768..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76.pcm.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76.te.png b/translated_images/segnet.87377542aa5a8b76.te.png deleted file mode 100644 index e4f74562..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76.te.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.et.png b/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.et.png deleted file mode 100644 index 282097c9..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.et.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.pcm.png b/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.pcm.png deleted file mode 100644 index 2c10c768..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.pcm.png and /dev/null differ diff --git a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.te.png b/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.te.png deleted file mode 100644 index e4f74562..00000000 Binary files a/translated_images/segnet.87377542aa5a8b76c6e19b715e86daec8da5c1124df41ab6064d8409b8579be6.te.png and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22c.et.jpg b/translated_images/style.5293e85e077ab22c.et.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22c.et.jpg and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22c.pcm.jpg b/translated_images/style.5293e85e077ab22c.pcm.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22c.pcm.jpg and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22c.te.jpg b/translated_images/style.5293e85e077ab22c.te.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22c.te.jpg and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.et.jpg b/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.et.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.et.jpg and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.pcm.jpg b/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.pcm.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.pcm.jpg and /dev/null differ diff --git a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.te.jpg b/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.te.jpg deleted file mode 100644 index 24361692..00000000 Binary files a/translated_images/style.5293e85e077ab22cf0e8f920132b79bd9a6d6f957085ef20079ec5eee96405c3.te.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.et.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.et.jpg deleted file mode 100644 index 49597a88..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.et.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.pcm.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.pcm.jpg deleted file mode 100644 index 92498082..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.pcm.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.te.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.te.jpg deleted file mode 100644 index 92e5a009..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6.te.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.et.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.et.jpg deleted file mode 100644 index 49597a88..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.et.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.pcm.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.pcm.jpg deleted file mode 100644 index 92498082..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.pcm.jpg and /dev/null differ diff --git a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.te.jpg b/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.te.jpg deleted file mode 100644 index 92e5a009..00000000 Binary files a/translated_images/synapse-wikipedia.ed20a9e4726ea1c6a3ce8fec51c0b9bec6181946dca0fe4e829bc12fa3bacf01.te.jpg and /dev/null differ diff --git a/translated_images/ta/.co-op-translator.json b/translated_images/ta/.co-op-translator.json index 746664ad..f152cc89 100644 --- a/translated_images/ta/.co-op-translator.json +++ b/translated_images/ta/.co-op-translator.json @@ -1,512 +1,20 @@ { - "favicon.37b561214b36d454.webp": { - "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", - "translation_date": "2026-01-16T06:58:23+00:00", - "source_file": "images/favicon.png", - "language_code": "ta" - }, - "ai-nlp.b22dcb8ca4707cea.webp": { - "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", - "translation_date": "2026-01-16T06:58:47+00:00", - "source_file": "lessons/sketchnotes/ai-nlp.png", - "language_code": "ta" - }, - "ai-symbolic.715a30cb610411a6.webp": { - "original_hash": "69d3628566f680ac8543651aa6fd520c", - "translation_date": "2026-01-16T06:59:14+00:00", - "source_file": "lessons/sketchnotes/ai-symbolic.png", - "language_code": "ta" - }, - "ai-computervision.6506ebebac3fbf76.webp": { - "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", - "translation_date": "2026-01-16T06:59:40+00:00", - "source_file": "lessons/sketchnotes/ai-computervision.png", - "language_code": "ta" - }, - "ai-for-beginners.b354ca904b22cd70.webp": { - "original_hash": "4b6f076798ec72ec7736b2e9039730e3", - "translation_date": "2026-01-16T06:59:46+00:00", - "source_file": "lessons/sketchnotes/ai-for-beginners.png", - "language_code": "ta" - }, - "ai-overview.0857791951d19500.webp": { - "original_hash": "7206f99da5c2b99d21581f946a660235", - "translation_date": "2026-01-16T07:00:08+00:00", - "source_file": "lessons/sketchnotes/ai-overview.png", - "language_code": "ta" - }, - "ai-intro.bf28d1ac4235881c.webp": { - "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", - "translation_date": "2026-01-16T07:00:38+00:00", - "source_file": "lessons/sketchnotes/ai-intro.png", - "language_code": "ta" - }, - "ai-neuralnetworks.1c687ae40bc86e83.webp": { - "original_hash": "6426ed635d4beb0ee499d634dfb61d65", - "translation_date": "2026-01-16T07:01:05+00:00", - "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", - "language_code": "ta" - }, - "vae.464c465a5b6a9e25.webp": { - "original_hash": "0b658c7862077e139162c756bcb98071", - "translation_date": "2026-01-16T07:01:10+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", - "language_code": "ta" - }, - "vaemnist-diag.694315f775d5d666.webp": { - "original_hash": "0652f5a95005348c6b1533438103dfcf", - "translation_date": "2026-01-16T07:01:11+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", - "language_code": "ta" - }, - "autoencoder_schema.5e6fc9ad98a5eb61.webp": { - "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", - "translation_date": "2026-01-16T07:01:18+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", - "language_code": "ta" - }, - "vaemnist.cab9e602dc08dc50.webp": { - "original_hash": "8159b2f649e6dd8efa071455d6f222b6", - "translation_date": "2026-01-16T07:01:22+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", - "language_code": "ta" - }, - "aae.9d418a990fc75bf9.webp": { - "original_hash": "92f89b37641f659a7d25c91d13076f69", - "translation_date": "2026-01-16T07:01:27+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", - "language_code": "ta" - }, - "instance_vs_semantic.eee9812bebf8cd45.webp": { - "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", - "translation_date": "2026-01-16T07:01:35+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", - "language_code": "ta" - }, - "unet.3adb555bf39d3657.webp": { - "original_hash": "49a151c11708ee9a3e94d21448146bf8", - "translation_date": "2026-01-16T07:01:48+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", - "language_code": "ta" - }, - "navi.2f20b727910110ea.webp": { - "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", - "translation_date": "2026-01-16T07:01:50+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", - "language_code": "ta" - }, - "segm.92442f2cb42ff4fa.webp": { - "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", - "translation_date": "2026-01-16T07:02:00+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", - "language_code": "ta" - }, - "segnet.87377542aa5a8b76.webp": { - "original_hash": "fa6d2d499aa2ae589a14caede7534561", - "translation_date": "2026-01-16T07:02:06+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", - "language_code": "ta" - }, - "gan_architecture.8f3a5ab62b8d5d69.webp": { - "original_hash": "4993c22b32d24c9d2d087645c2a90d81", - "translation_date": "2026-01-16T07:02:14+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", - "language_code": "ta" - }, - "style.5293e85e077ab22c.webp": { - "original_hash": "f797246177c68cc33bcdf7abae8c9b68", - "translation_date": "2026-01-16T07:02:15+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", - "language_code": "ta" - }, - "image.896e8254a2c60d45.webp": { - "original_hash": "0033165481f191386403b85801811833", - "translation_date": "2026-01-16T07:02:17+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", - "language_code": "ta" - }, - "gan_arch_detail.46b95fd366f8e543.webp": { - "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", - "translation_date": "2026-01-16T07:02:28+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", - "language_code": "ta" - }, - "dcgan_generator.b500988ec2bc8ba5.webp": { - "original_hash": "a11642e50f68e41c69b1580c9b724ef1", - "translation_date": "2026-01-16T07:02:36+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", - "language_code": "ta" - }, - "ideal-zebra.7f70e8b54ee15a7a.webp": { - "original_hash": "6944fb46795f714f0ce8e856c405498a", - "translation_date": "2026-01-16T07:02:37+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", - "language_code": "ta" - }, - "ideal-cat-loop.999fbb8ff306e044.webp": { - "original_hash": "c54e983c591431338bf8ddac9ab8415b", - "translation_date": "2026-01-16T07:02:45+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", - "language_code": "ta" - }, - "dog-from-unsplash.426f9fbca2febc93.webp": { - "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", - "translation_date": "2026-01-16T07:02:46+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", - "language_code": "ta" - }, - "features.6291f9c7ba3a0b95.webp": { - "original_hash": "e2727bfacc1156e045d1879bbe86e189", - "translation_date": "2026-01-16T07:02:50+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", - "language_code": "ta" - }, - "ideal-cat.203dd4597643d6b0.webp": { - "original_hash": "5b44760be530a91be18a5cceebbc2cc3", - "translation_date": "2026-01-16T07:02:50+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", - "language_code": "ta" - }, - "adversarial-dog.d9fc7773b0142b89.webp": { - "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", - "translation_date": "2026-01-16T07:02:51+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", - "language_code": "ta" - }, - "catsdogsdataset.a7aff8e6085fd3f0.webp": { - "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", - "translation_date": "2026-01-16T07:02:55+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", - "language_code": "ta" - }, - "original-dog.8f68a67d2fe0911f.webp": { - "original_hash": "3ed859629b4141f735fd0d3c1941f520", - "translation_date": "2026-01-16T07:02:55+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", - "language_code": "ta" - }, - "braille.341962ff76b1bd70.webp": { - "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", - "translation_date": "2026-01-16T07:02:56+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", - "language_code": "ta" - }, - "braille-symbols.0159185ab69d5339.webp": { - "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", - "translation_date": "2026-01-16T07:03:00+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", - "language_code": "ta" - }, - "frame-difference.706f805491a0883c.webp": { - "original_hash": "a141e72f08e1b8f7451392889af90072", - "translation_date": "2026-01-16T07:03:02+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", - "language_code": "ta" - }, - "braille-result.46530fea020b03c7.webp": { - "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", - "translation_date": "2026-01-16T07:03:03+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", - "language_code": "ta" - }, - "palm-movement.341495f0e9c47da3.webp": { - "original_hash": "100780b2e1d5adff2739adf58fc18404", - "translation_date": "2026-01-16T07:03:04+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", - "language_code": "ta" - }, - "optical.1f4a94464579a83a.webp": { - "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", - "translation_date": "2026-01-16T07:03:06+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", - "language_code": "ta" - }, "1200px-Girl_and_cat.89bd70951181e86a.webp": { "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", "translation_date": "2026-01-16T07:03:07+00:00", "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", "language_code": "ta" }, - "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { - "original_hash": "f31ea979f0ceabdf198899985ac84c37", - "translation_date": "2026-01-16T07:03:18+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", - "language_code": "ta" - }, - "naive-detection.e7f1ba220ccd08c6.webp": { - "original_hash": "4c96961c12a09f8e055546ed2e7de470", - "translation_date": "2026-01-16T07:03:24+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", - "language_code": "ta" - }, - "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { - "original_hash": "6704085c522f47ce42ad8402dafe6429", - "translation_date": "2026-01-16T07:03:29+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", - "language_code": "ta" - }, - "iou_equation.9a4751d40fff4e11.webp": { - "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", - "translation_date": "2026-01-16T07:03:33+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", - "language_code": "ta" - }, - "coco-examples.71bc60380fa6cceb.webp": { - "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", - "translation_date": "2026-01-16T07:03:36+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", - "language_code": "ta" - }, - "f-rcnn.3cda6d9bb4188875.webp": { - "original_hash": "fdafedad20701c95bdcf6bb923822ab1", - "translation_date": "2026-01-16T07:03:44+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", - "language_code": "ta" - }, - "rcnn1.cae407020dfb1d1f.webp": { - "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", - "translation_date": "2026-01-16T07:03:45+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", - "language_code": "ta" - }, - "faster-rcnn.8d46c099b87ef30a.webp": { - "original_hash": "067e2ca96344fd6d0490e0530a922b36", - "translation_date": "2026-01-16T07:03:56+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", - "language_code": "ta" - }, - "r-fcn.13eb88158b99a3da.webp": { - "original_hash": "38cd0e0105546e56fa17b711d445195f", - "translation_date": "2026-01-16T07:04:02+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", - "language_code": "ta" - }, - "yolo.a2648ec82ee8bb4e.webp": { - "original_hash": "e8835638234f5c21fcf36fdede6457f4", - "translation_date": "2026-01-16T07:04:06+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", - "language_code": "ta" - }, - "rcnn2.2d9530bb83516484.webp": { - "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", - "translation_date": "2026-01-16T07:04:15+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", - "language_code": "ta" - }, - "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { - "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", - "translation_date": "2026-01-16T07:04:30+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", - "language_code": "ta" - }, - "resnet-block.aba4ccbcc0944434.webp": { - "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", - "translation_date": "2026-01-16T07:04:34+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", - "language_code": "ta" - }, - "cnn-pyramid.85915455759ef0ce.webp": { - "original_hash": "7233ded4a920332806363d704bfb59a6", - "translation_date": "2026-01-16T07:04:53+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", - "language_code": "ta" - }, - "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { - "original_hash": "c9bde577c8b279b5199a8b294ee9494f", - "translation_date": "2026-01-16T07:04:56+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", - "language_code": "ta" - }, - "filter-horiz.59b80ed4feb946ef.webp": { - "original_hash": "b081df9e2042850983a46ff817b88d55", - "translation_date": "2026-01-16T07:04:58+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", - "language_code": "ta" - }, - "vgg-16-arch1.d901a5583b3a51ba.webp": { - "original_hash": "5b0f835d04dc20d097a0b89c88339966", - "translation_date": "2026-01-16T07:05:06+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", - "language_code": "ta" - }, - "vgg-16-arch.64ff2137f50dd49f.webp": { - "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", - "translation_date": "2026-01-16T07:05:12+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", - "language_code": "ta" - }, - "convolutionExample.634615d5ff7081e0.webp": { - "original_hash": "5412e092848cb3cd4fa527aba3be0545", - "translation_date": "2026-01-16T07:05:20+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", - "language_code": "ta" - }, - "inception.a6605b85bcbc6f52.webp": { - "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", - "translation_date": "2026-01-16T07:05:26+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", - "language_code": "ta" - }, - "filter-vert.b7148390ca0bc356.webp": { - "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", - "translation_date": "2026-01-16T07:05:31+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", - "language_code": "ta" - }, - "lmfilters.ea9e4868a82cf74c.webp": { - "original_hash": "aa029ea2c45afbac3026a0a558eeec43", - "translation_date": "2026-01-16T07:05:31+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", - "language_code": "ta" - }, - "data.50b2a9d5484bdbf0.webp": { - "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", - "translation_date": "2026-01-16T07:05:44+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", - "language_code": "ta" - }, - "NetLogo-ModelLib.efe023afb4763c05.webp": { - "original_hash": "edd5b28318e2f43274a4541408110fb9", - "translation_date": "2026-01-16T07:06:04+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", - "language_code": "ta" - }, - "NetLogo-Main.32653711ec1a01b3.webp": { - "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", - "translation_date": "2026-01-16T07:06:31+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", - "language_code": "ta" - }, - "cartpole.f52a67f27e058170.webp": { - "original_hash": "5399242e127ea1c18aa6ee405daecf51", - "translation_date": "2026-01-16T07:06:31+00:00", - "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", - "language_code": "ta" - }, - "mountaincar.f7b7a7f6d4f9933b.webp": { - "original_hash": "61c868cc389dc92bd2b402ea490cd162", - "translation_date": "2026-01-16T07:06:33+00:00", - "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", - "language_code": "ta" - }, - "ml-for-beginners.9e4fed176fd5817d.webp": { - "original_hash": "cd606a24083e039082b0486fc8382823", - "translation_date": "2026-01-16T07:06:36+00:00", - "source_file": "lessons/1-Intro/images/ml-for-beginners.png", - "language_code": "ta" - }, - "history-of-ai.7e83efa70b537f5a.webp": { - "original_hash": "644e648b98fcb10fb9713452ff02934d", - "translation_date": "2026-01-16T07:06:54+00:00", - "source_file": "lessons/1-Intro/images/history-of-ai.png", - "language_code": "ta" - }, - "photo-cat.8c8e8fb760ffe457.webp": { - "original_hash": "29d10fef28d240c48995ef9dd23e477a", - "translation_date": "2026-01-16T07:06:55+00:00", - "source_file": "lessons/1-Intro/images/photo-cat.jpg", - "language_code": "ta" - }, - "dsh_age.d212a30d4e54fb5f.webp": { - "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", - "translation_date": "2026-01-16T07:06:57+00:00", - "source_file": "lessons/1-Intro/images/dsh_age.png", - "language_code": "ta" - }, - "turing-test-evol.4184696701293ead.webp": { - "original_hash": "80d11b1074d61e5d6e4a207f72902e89", - "translation_date": "2026-01-16T07:07:06+00:00", - "source_file": "lessons/1-Intro/images/turing-test-evol.png", - "language_code": "ta" - }, - "knowledge-spectrum.b60df631852c0217.webp": { - "original_hash": "71b049ee26a22a68996034585436ca59", - "translation_date": "2026-01-16T07:07:22+00:00", - "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", - "language_code": "ta" - }, - "DIKW_Pyramid.94126f7d2bd8db5b.webp": { - "original_hash": "ad410ec7f25454482fd4516c4a46fc67", - "translation_date": "2026-01-16T07:07:28+00:00", - "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", - "language_code": "ta" - }, "AND-OR-Tree.5592d2c70187f283.webp": { "original_hash": "2674b6cf8f768491c6b5a167f272a002", "translation_date": "2026-01-16T07:08:15+00:00", "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", "language_code": "ta" }, - "triplet-complex.32094972c7b4441b.webp": { - "original_hash": "56a2e05839a141c311db52655b37f8ad", - "translation_date": "2026-01-16T07:08:36+00:00", - "source_file": "lessons/2-Symbolic/images/triplet-complex.png", - "language_code": "ta" - }, - "arch-human.5d4d35f1bba3ab1c.webp": { - "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", - "translation_date": "2026-01-16T07:08:44+00:00", - "source_file": "lessons/2-Symbolic/images/arch-human.png", - "language_code": "ta" - }, - "arch-kbs.3ec5c150b09fa8da.webp": { - "original_hash": "f470e6ec071db529cd3149052cfeb8ff", - "translation_date": "2026-01-16T07:08:51+00:00", - "source_file": "lessons/2-Symbolic/images/arch-kbs.png", - "language_code": "ta" - }, - "triplet.4b9b332587593298.webp": { - "original_hash": "302e53ea355ffb556d99e3962d0a6516", - "translation_date": "2026-01-16T07:09:03+00:00", - "source_file": "lessons/2-Symbolic/images/triplet.png", - "language_code": "ta" - }, - "protege.274177ceeac13b38.webp": { - "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", - "translation_date": "2026-01-16T07:09:55+00:00", - "source_file": "lessons/2-Symbolic/images/protege.png", - "language_code": "ta" - }, - "synapse-wikipedia.ed20a9e4726ea1c6.webp": { - "original_hash": "88212730ecd9b0c8b848c319951427d8", - "translation_date": "2026-01-16T07:10:02+00:00", - "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", - "language_code": "ta" - }, - "overfit2.131f5800ae10ca5e.webp": { - "original_hash": "eb04381b2f222518ec400b98ebf441b2", - "translation_date": "2026-01-16T07:10:04+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", - "language_code": "ta" - }, - "netout.1eb15eb76fd76731.webp": { - "original_hash": "187261e2b5036746ee9d9106b1f7df1b", - "translation_date": "2026-01-16T07:10:06+00:00", - "source_file": "lessons/3-NeuralNetworks/images/netout.png", - "language_code": "ta" - }, - "artneuron.1a5daa88d20ebe6f.webp": { - "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", - "translation_date": "2026-01-16T07:10:11+00:00", - "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", - "language_code": "ta" - }, - "Overfitting.408ad91cd90b4371.webp": { - "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", - "translation_date": "2026-01-16T07:10:19+00:00", - "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", - "language_code": "ta" - }, - "overfit1.f24b71c6f652e59e.webp": { - "original_hash": "76155698e85340d9dfff8e0a628d25c1", - "translation_date": "2026-01-16T07:10:22+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", - "language_code": "ta" - }, - "NeuroArch.4e17cdba5e445721.webp": { - "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", - "translation_date": "2026-01-16T07:10:27+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:10:43+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", "language_code": "ta" }, "ComputeGraphGrad.4626252c0de03507.webp": { @@ -515,66 +23,18 @@ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", "language_code": "ta" }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:13:25+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "ta" + }, "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { "original_hash": "11dd0fd77a272755d0ef5db9f71217da", "translation_date": "2026-01-16T07:10:41+00:00", "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", "language_code": "ta" }, - "ComputeGraph.463c9d8ebdcb2215.webp": { - "original_hash": "7af66742d6bede114f971689745bedf2", - "translation_date": "2026-01-16T07:10:43+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", - "language_code": "ta" - }, - "overfit.a0bd57f717c15769.webp": { - "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", - "translation_date": "2026-01-16T07:10:48+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", - "language_code": "ta" - }, - "Rosenblatt-wikipedia.294821b285ac796d.webp": { - "original_hash": "c21d9b47d0106208a0f35a920d6bff66", - "translation_date": "2026-01-16T07:10:50+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", - "language_code": "ta" - }, - "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { - "original_hash": "2cc48ff435c89ca1e162872a42b4813c", - "translation_date": "2026-01-16T07:10:52+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", - "language_code": "ta" - }, - "activation-func.b4924007c7ce7764.webp": { - "original_hash": "8d357884343ec923611a319d4e910b99", - "translation_date": "2026-01-16T07:10:55+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", - "language_code": "ta" - }, - "clip-class.3af42ef0b2b19369.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:11:02+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", - "language_code": "ta" - }, - "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { - "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", - "translation_date": "2026-01-16T07:11:04+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", - "language_code": "ta" - }, - "clip-arch.b3dbf20b4e8ed8be.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:11:11+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", - "language_code": "ta" - }, - "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { - "original_hash": "e300d75d78f6050bc7b83df091f95775", - "translation_date": "2026-01-16T07:11:14+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", - "language_code": "ta" - }, "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { "original_hash": "dd063fda04db937ab7210064af9d6151", "translation_date": "2026-01-16T07:11:15+00:00", @@ -587,10 +47,82 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", "language_code": "ta" }, - "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { - "original_hash": "ec89cbb600b14e86f353a347506554ba", - "translation_date": "2026-01-16T07:11:17+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:11:14+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "ta" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:07:28+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "ta" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:04:56+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "ta" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:10:52+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "ta" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:06:31+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "ta" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:06:04+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "ta" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:10:27+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "ta" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:03:29+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "ta" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:03:18+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "ta" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:10:19+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "ta" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:10:50+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "ta" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:04:30+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "ta" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:11:04+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", "language_code": "ta" }, "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { @@ -599,22 +131,88 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", "language_code": "ta" }, - "vqgan.5027fe05051dfa31.webp": { - "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", - "translation_date": "2026-01-16T07:11:21+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:11:17+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", "language_code": "ta" }, - "bag-of-words-example.606fc1738f1d7ba9.webp": { - "original_hash": "a8fa84622ff35939e498d06fac3fa515", - "translation_date": "2026-01-16T07:11:26+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:01:27+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", "language_code": "ta" }, - "bow.3811869cff59368d.webp": { - "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", - "translation_date": "2026-01-16T07:11:49+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:10:55+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "ta" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:02:51+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "ta" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T06:59:40+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "ta" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T06:59:46+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "ta" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:00:38+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "ta" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:01:05+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "ta" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T06:58:47+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "ta" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T07:00:08+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "ta" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T06:59:14+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "ta" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:08:44+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "ta" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:08:51+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "ta" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:10:11+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", "language_code": "ta" }, "ascii-character-map.18ed6aa7f3b0a7ff.webp": { @@ -623,34 +221,16 @@ "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", "language_code": "ta" }, - "multi-layer-lstm.dd975e29bb2a59fe.webp": { - "original_hash": "27b6355fd86c9e8e6d443015653be763", - "translation_date": "2026-01-16T07:12:02+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:01:18+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", "language_code": "ta" }, - "rnn-anatomy.79ee3f3920b3294b.webp": { - "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", - "translation_date": "2026-01-16T07:12:10+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", - "language_code": "ta" - }, - "rnn.27f5c29c53d727b5.webp": { - "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", - "translation_date": "2026-01-16T07:12:23+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", - "language_code": "ta" - }, - "encoder-decoder-attention.7a726296894fb567.webp": { - "original_hash": "e0546cbc8252d764df7f7212b371f0ed", - "translation_date": "2026-01-16T07:12:35+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", - "language_code": "ta" - }, - "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { - "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", - "translation_date": "2026-01-16T07:12:48+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:11:26+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", "language_code": "ta" }, "bahdanau-fig3.09ba2d37f202a6af.webp": { @@ -659,46 +239,100 @@ "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", "language_code": "ta" }, - "pos-embedding.e41ce9b6cf6078af.webp": { - "original_hash": "f0910082dcac063f3baae2e1f28b4e30", - "translation_date": "2026-01-16T07:13:05+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", - "language_code": "ta" - }, - "transformer-layer.905e14747ca4e7d5.webp": { - "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", - "translation_date": "2026-01-16T07:13:15+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", - "language_code": "ta" - }, - "CoreferenceResolution.861924d6d384a7d6.webp": { - "original_hash": "25b5719ec70aaa44858076c16f7c208f", - "translation_date": "2026-01-16T07:13:25+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", - "language_code": "ta" - }, "bot-ner.4b09235dbb0ad275.webp": { "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", "translation_date": "2026-01-16T07:13:42+00:00", "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", "language_code": "ta" }, - "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { - "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", - "translation_date": "2026-01-16T07:13:47+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:11:49+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", "language_code": "ta" }, - "rnn-generate.56c54afb52f9781d.webp": { - "original_hash": "67332ada2d0603921bba37c06956c70e", - "translation_date": "2026-01-16T07:13:52+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:03:03+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", "language_code": "ta" }, - "rnn-generate-inf.5168dc65e0370eea.webp": { - "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", - "translation_date": "2026-01-16T07:13:56+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:03:00+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "ta" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:02:56+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "ta" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:06:31+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "ta" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:02:55+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "ta" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:11:11+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "ta" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:11:02+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "ta" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:04:53+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "ta" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:03:36+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "ta" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:05:20+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "ta" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:05:44+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "ta" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:02:36+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "ta" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:02:46+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "ta" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:06:57+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", "language_code": "ta" }, "embedding-classifier-example.b77f021a7ee67eee.webp": { @@ -707,10 +341,10 @@ "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", "language_code": "ta" }, - "offset-sequence-representation.eb73fcefb29b46ee.webp": { - "original_hash": "52e7632a2b668957b903bb2607e953fe", - "translation_date": "2026-01-16T07:14:07+00:00", - "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:12:35+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", "language_code": "ta" }, "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { @@ -718,5 +352,371 @@ "translation_date": "2026-01-16T07:14:13+00:00", "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", "language_code": "ta" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:03:44+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "ta" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:03:56+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "ta" + }, + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T06:58:23+00:00", + "source_file": "images/favicon.png", + "language_code": "ta" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:02:50+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "ta" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:04:58+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "ta" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:05:31+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "ta" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:03:02+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "ta" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:02:28+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "ta" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:02:14+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "ta" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:06:54+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "ta" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:02:45+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "ta" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:02:50+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "ta" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:02:37+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "ta" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:02:17+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "ta" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:05:26+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "ta" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:01:35+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "ta" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:03:33+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "ta" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:12:48+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "ta" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:07:22+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "ta" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:05:31+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "ta" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:06:36+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "ta" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:06:33+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "ta" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:12:02+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "ta" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:03:24+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "ta" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:01:50+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "ta" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:10:06+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "ta" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:14:07+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "ta" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:03:06+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "ta" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:02:55+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "ta" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:10:48+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "ta" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:10:22+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "ta" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:10:04+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "ta" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:03:04+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "ta" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:06:55+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "ta" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:13:05+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "ta" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:09:55+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "ta" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:04:02+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "ta" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:03:45+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "ta" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:04:15+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "ta" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:04:34+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "ta" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:12:10+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "ta" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:13:56+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "ta" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:13:52+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "ta" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:12:23+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "ta" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:02:00+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "ta" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:02:06+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "ta" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:02:15+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "ta" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:10:02+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "ta" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:13:15+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "ta" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:08:36+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "ta" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:09:03+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "ta" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:07:06+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "ta" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:01:48+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "ta" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:13:47+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "ta" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:01:10+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "ta" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:01:11+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "ta" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:01:22+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "ta" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:05:12+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "ta" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:05:06+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "ta" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:11:21+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "ta" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:04:06+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "ta" } } \ No newline at end of file diff --git a/translated_images/te/.co-op-translator.json b/translated_images/te/.co-op-translator.json new file mode 100644 index 00000000..ed7ff667 --- /dev/null +++ b/translated_images/te/.co-op-translator.json @@ -0,0 +1,722 @@ +{ + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T07:38:28+00:00", + "source_file": "images/favicon.png", + "language_code": "te" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T07:38:46+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "te" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T07:39:12+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "te" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T07:39:34+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "te" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T07:39:40+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "te" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T07:40:00+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "te" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:40:25+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "te" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:40:49+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "te" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:40:53+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "te" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:40:55+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "te" + }, + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:40:58+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", + "language_code": "te" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:41:02+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "te" + }, + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:41:07+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", + "language_code": "te" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:41:13+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "te" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:41:27+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "te" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:41:29+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "te" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:41:38+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "te" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:41:43+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "te" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:41:51+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "te" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:41:53+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "te" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:41:54+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "te" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:42:05+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "te" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:42:12+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "te" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:42:13+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "te" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:42:19+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "te" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:42:20+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "te" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "te" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:42:24+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "te" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:42:25+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "te" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:42:31+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "te" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:42:31+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "te" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:42:32+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "te" + }, + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:42:35+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "te" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:42:38+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "te" + }, + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:42:38+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", + "language_code": "te" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:42:40+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "te" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:42:42+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "te" + }, + "1200px-Girl_and_cat.89bd70951181e86a.webp": { + "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", + "translation_date": "2026-01-16T07:42:43+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", + "language_code": "te" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:42:51+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "te" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:42:57+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "te" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:43:03+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "te" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:43:06+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "te" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:43:09+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "te" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:43:17+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "te" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:43:18+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "te" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:43:25+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "te" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:43:32+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "te" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:43:36+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "te" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:43:44+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "te" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:43:59+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "te" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:44:03+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "te" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:44:21+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "te" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:44:24+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "te" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:44:26+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "te" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:44:35+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "te" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:44:39+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "te" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:44:46+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "te" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:44:53+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "te" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:44:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "te" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:44:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "te" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:45:05+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "te" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:45:27+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "te" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:45:51+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "te" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:45:52+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "te" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:45:54+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "te" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:45:56+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "te" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:46:13+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "te" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:46:13+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "te" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:46:15+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", + "language_code": "te" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:46:27+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "te" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:46:43+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "te" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:46:49+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "te" + }, + "AND-OR-Tree.5592d2c70187f283.webp": { + "original_hash": "2674b6cf8f768491c6b5a167f272a002", + "translation_date": "2026-01-16T07:47:35+00:00", + "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", + "language_code": "te" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:47:55+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "te" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:48:04+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "te" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:48:11+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "te" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:48:24+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "te" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:49:02+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "te" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:49:08+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "te" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:49:11+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "te" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:49:12+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "te" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:49:17+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", + "language_code": "te" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:49:24+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "te" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:49:28+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "te" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:49:33+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "te" + }, + "ComputeGraphGrad.4626252c0de03507.webp": { + "original_hash": "b0bf679245a237b1e7785ae2357a5376", + "translation_date": "2026-01-16T07:49:38+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", + "language_code": "te" + }, + "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { + "original_hash": "11dd0fd77a272755d0ef5db9f71217da", + "translation_date": "2026-01-16T07:49:45+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", + "language_code": "te" + }, + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:49:48+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", + "language_code": "te" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:49:52+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "te" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:49:54+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "te" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:49:57+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "te" + }, + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:49:59+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "te" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:07+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "te" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:50:09+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", + "language_code": "te" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:50:16+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "te" + }, + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:50:18+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "te" + }, + "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { + "original_hash": "dd063fda04db937ab7210064af9d6151", + "translation_date": "2026-01-16T07:50:20+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.png", + "language_code": "te" + }, + "DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp": { + "original_hash": "2cc9ab0daf8e1af7071fbc9eaf84970b", + "translation_date": "2026-01-16T07:50:21+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", + "language_code": "te" + }, + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:50:22+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "language_code": "te" + }, + "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { + "original_hash": "7064cd71a562523998203c756842c96d", + "translation_date": "2026-01-16T07:50:23+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", + "language_code": "te" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:50:27+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "te" + }, + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:50:31+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "language_code": "te" + }, + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:50:53+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "language_code": "te" + }, + "ascii-character-map.18ed6aa7f3b0a7ff.webp": { + "original_hash": "afc5ff2601be320926d89f1ad897eda8", + "translation_date": "2026-01-16T07:51:02+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", + "language_code": "te" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:51:06+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "te" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:51:16+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "te" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:51:28+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "te" + }, + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:51:40+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", + "language_code": "te" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:51:53+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "te" + }, + "bahdanau-fig3.09ba2d37f202a6af.webp": { + "original_hash": "b5cfbb9cad3b0d3fbdcc63dcd2ed514f", + "translation_date": "2026-01-16T07:52:00+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", + "language_code": "te" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:52:10+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "te" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:52:20+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "te" + }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:52:29+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "te" + }, + "bot-ner.4b09235dbb0ad275.webp": { + "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", + "translation_date": "2026-01-16T07:52:46+00:00", + "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", + "language_code": "te" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:52:50+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "te" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:52:56+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "te" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:53:00+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "te" + }, + "embedding-classifier-example.b77f021a7ee67eee.webp": { + "original_hash": "0c4233111f66d9c6925af5b97f9519a0", + "translation_date": "2026-01-16T07:53:06+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", + "language_code": "te" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:53:11+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "te" + }, + "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { + "original_hash": "6e976f26b9bb4c7a021187e834132123", + "translation_date": "2026-01-16T07:53:16+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", + "language_code": "te" + } +} \ No newline at end of file diff --git a/translated_images/te/1200px-Girl_and_cat.89bd70951181e86a.webp b/translated_images/te/1200px-Girl_and_cat.89bd70951181e86a.webp new file mode 100644 index 00000000..47042c75 Binary files /dev/null and b/translated_images/te/1200px-Girl_and_cat.89bd70951181e86a.webp differ diff --git a/translated_images/te/AND-OR-Tree.5592d2c70187f283.webp b/translated_images/te/AND-OR-Tree.5592d2c70187f283.webp new file mode 100644 index 00000000..2abc464a Binary files /dev/null and b/translated_images/te/AND-OR-Tree.5592d2c70187f283.webp differ diff --git a/translated_images/te/ComputeGraph.463c9d8ebdcb2215.webp b/translated_images/te/ComputeGraph.463c9d8ebdcb2215.webp new file mode 100644 index 00000000..acdfde97 Binary files /dev/null and b/translated_images/te/ComputeGraph.463c9d8ebdcb2215.webp differ diff --git a/translated_images/te/ComputeGraphGrad.4626252c0de03507.webp b/translated_images/te/ComputeGraphGrad.4626252c0de03507.webp new file mode 100644 index 00000000..98e530c7 Binary files /dev/null and b/translated_images/te/ComputeGraphGrad.4626252c0de03507.webp differ diff --git a/translated_images/te/CoreferenceResolution.861924d6d384a7d6.webp b/translated_images/te/CoreferenceResolution.861924d6d384a7d6.webp new file mode 100644 index 00000000..66716038 Binary files /dev/null and b/translated_images/te/CoreferenceResolution.861924d6d384a7d6.webp differ diff --git a/translated_images/te/Cross-Entropy-Loss.dc7ba633d2467ef3.webp b/translated_images/te/Cross-Entropy-Loss.dc7ba633d2467ef3.webp new file mode 100644 index 00000000..23ec5f5f Binary files /dev/null and b/translated_images/te/Cross-Entropy-Loss.dc7ba633d2467ef3.webp differ diff --git a/translated_images/te/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp b/translated_images/te/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp new file mode 100644 index 00000000..222db344 Binary files /dev/null and b/translated_images/te/DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp differ diff --git a/translated_images/te/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp b/translated_images/te/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp new file mode 100644 index 00000000..f3b973c5 Binary files /dev/null and b/translated_images/te/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.081e8aed073e2fbf.webp differ diff --git a/translated_images/te/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp b/translated_images/te/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp new file mode 100644 index 00000000..b8f4286a Binary files /dev/null and b/translated_images/te/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp differ diff --git a/translated_images/te/DIKW_Pyramid.94126f7d2bd8db5b.webp b/translated_images/te/DIKW_Pyramid.94126f7d2bd8db5b.webp new file mode 100644 index 00000000..e8b93b3f Binary files /dev/null and b/translated_images/te/DIKW_Pyramid.94126f7d2bd8db5b.webp differ diff --git a/translated_images/te/FeatureExtractionCNN.d9b456cbdae7cb64.webp b/translated_images/te/FeatureExtractionCNN.d9b456cbdae7cb64.webp new file mode 100644 index 00000000..3f4482f4 Binary files /dev/null and b/translated_images/te/FeatureExtractionCNN.d9b456cbdae7cb64.webp differ diff --git a/translated_images/te/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp b/translated_images/te/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp new file mode 100644 index 00000000..35967a92 Binary files /dev/null and b/translated_images/te/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp differ diff --git a/translated_images/te/NetLogo-Main.32653711ec1a01b3.webp b/translated_images/te/NetLogo-Main.32653711ec1a01b3.webp new file mode 100644 index 00000000..c8a3c03a Binary files /dev/null and b/translated_images/te/NetLogo-Main.32653711ec1a01b3.webp differ diff --git a/translated_images/te/NetLogo-ModelLib.efe023afb4763c05.webp b/translated_images/te/NetLogo-ModelLib.efe023afb4763c05.webp new file mode 100644 index 00000000..d4fb2b97 Binary files /dev/null and b/translated_images/te/NetLogo-ModelLib.efe023afb4763c05.webp differ diff --git a/translated_images/te/NeuroArch.4e17cdba5e445721.webp b/translated_images/te/NeuroArch.4e17cdba5e445721.webp new file mode 100644 index 00000000..86af40ea Binary files /dev/null and b/translated_images/te/NeuroArch.4e17cdba5e445721.webp differ diff --git a/translated_images/te/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp b/translated_images/te/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp new file mode 100644 index 00000000..ddfe1cbe Binary files /dev/null and b/translated_images/te/ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp differ diff --git a/translated_images/te/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp b/translated_images/te/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp new file mode 100644 index 00000000..d25a03f5 Binary files /dev/null and b/translated_images/te/ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp differ diff --git a/translated_images/te/Overfitting.408ad91cd90b4371.webp b/translated_images/te/Overfitting.408ad91cd90b4371.webp new file mode 100644 index 00000000..bb297dd9 Binary files /dev/null and b/translated_images/te/Overfitting.408ad91cd90b4371.webp differ diff --git a/translated_images/te/Rosenblatt-wikipedia.294821b285ac796d.webp b/translated_images/te/Rosenblatt-wikipedia.294821b285ac796d.webp new file mode 100644 index 00000000..6337c83b Binary files /dev/null and b/translated_images/te/Rosenblatt-wikipedia.294821b285ac796d.webp differ diff --git a/translated_images/te/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp b/translated_images/te/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp new file mode 100644 index 00000000..86f4c0bd Binary files /dev/null and b/translated_images/te/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp differ diff --git a/translated_images/te/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp b/translated_images/te/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp new file mode 100644 index 00000000..ee032762 Binary files /dev/null and b/translated_images/te/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp differ diff --git a/translated_images/te/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp b/translated_images/te/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp new file mode 100644 index 00000000..52ce29a9 Binary files /dev/null and b/translated_images/te/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp differ diff --git a/translated_images/te/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp b/translated_images/te/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp new file mode 100644 index 00000000..fba04870 Binary files /dev/null and b/translated_images/te/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp differ diff --git a/translated_images/te/aae.9d418a990fc75bf9.webp b/translated_images/te/aae.9d418a990fc75bf9.webp new file mode 100644 index 00000000..b380509b Binary files /dev/null and b/translated_images/te/aae.9d418a990fc75bf9.webp differ diff --git a/translated_images/te/activation-func.b4924007c7ce7764.webp b/translated_images/te/activation-func.b4924007c7ce7764.webp new file mode 100644 index 00000000..624c726d Binary files /dev/null and b/translated_images/te/activation-func.b4924007c7ce7764.webp differ diff --git a/translated_images/te/adversarial-dog.d9fc7773b0142b89.webp b/translated_images/te/adversarial-dog.d9fc7773b0142b89.webp new file mode 100644 index 00000000..8816fc84 Binary files /dev/null and b/translated_images/te/adversarial-dog.d9fc7773b0142b89.webp differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5.et.png b/translated_images/transformer-layer.905e14747ca4e7d5.et.png deleted file mode 100644 index 14a78b9b..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5.et.png and /dev/null differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5.pcm.png b/translated_images/transformer-layer.905e14747ca4e7d5.pcm.png deleted file mode 100644 index c7002de2..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5.pcm.png and /dev/null differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5.te.png b/translated_images/transformer-layer.905e14747ca4e7d5.te.png deleted file mode 100644 index 3dd0604a..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5.te.png and /dev/null differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.et.png b/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.et.png deleted file mode 100644 index 14a78b9b..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.et.png and /dev/null differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.pcm.png b/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.pcm.png deleted file mode 100644 index c7002de2..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.pcm.png and /dev/null differ diff --git a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.te.png b/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.te.png deleted file mode 100644 index 3dd0604a..00000000 Binary files a/translated_images/transformer-layer.905e14747ca4e7d5cf1409e8bf8944c9b1d6e4f5ce3ab167918af65c4904d727.te.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b.et.png b/translated_images/triplet-complex.32094972c7b4441b.et.png deleted file mode 100644 index 73ac9755..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b.et.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b.pcm.png b/translated_images/triplet-complex.32094972c7b4441b.pcm.png deleted file mode 100644 index 4d0f37f8..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b.pcm.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b.te.png b/translated_images/triplet-complex.32094972c7b4441b.te.png deleted file mode 100644 index 239287e2..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b.te.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.et.png b/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.et.png deleted file mode 100644 index 73ac9755..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.et.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.pcm.png b/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.pcm.png deleted file mode 100644 index 4d0f37f8..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.pcm.png and /dev/null differ diff --git a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.te.png b/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.te.png deleted file mode 100644 index 239287e2..00000000 Binary files a/translated_images/triplet-complex.32094972c7b4441b844bd85e683ba8eedc08af12177160f11584452698f29ace.te.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298.et.png b/translated_images/triplet.4b9b332587593298.et.png deleted file mode 100644 index f3912955..00000000 Binary files a/translated_images/triplet.4b9b332587593298.et.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298.pcm.png b/translated_images/triplet.4b9b332587593298.pcm.png deleted file mode 100644 index 8382dbc1..00000000 Binary files a/translated_images/triplet.4b9b332587593298.pcm.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298.te.png b/translated_images/triplet.4b9b332587593298.te.png deleted file mode 100644 index f795d676..00000000 Binary files a/translated_images/triplet.4b9b332587593298.te.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.et.png b/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.et.png deleted file mode 100644 index f3912955..00000000 Binary files a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.et.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.pcm.png b/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.pcm.png deleted file mode 100644 index 8382dbc1..00000000 Binary files a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.pcm.png and /dev/null differ diff --git a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.te.png b/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.te.png deleted file mode 100644 index f795d676..00000000 Binary files a/translated_images/triplet.4b9b332587593298b31846eb5cf341d8f7e48da76e6692dbb7cf0fcf2fd5ab38.te.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead.et.png b/translated_images/turing-test-evol.4184696701293ead.et.png deleted file mode 100644 index 930dd1c9..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead.et.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead.pcm.png b/translated_images/turing-test-evol.4184696701293ead.pcm.png deleted file mode 100644 index 73980cdb..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead.pcm.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead.te.png b/translated_images/turing-test-evol.4184696701293ead.te.png deleted file mode 100644 index 939359f6..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead.te.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.et.png b/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.et.png deleted file mode 100644 index 930dd1c9..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.et.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.pcm.png b/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.pcm.png deleted file mode 100644 index 73980cdb..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.pcm.png and /dev/null differ diff --git a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.te.png b/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.te.png deleted file mode 100644 index 939359f6..00000000 Binary files a/translated_images/turing-test-evol.4184696701293ead6de6e6441a659c62f0b119b342456987f531005f43be0b6d.te.png and /dev/null differ diff --git a/translated_images/uk/.co-op-translator.json b/translated_images/uk/.co-op-translator.json index db9c4a9e..b342c7d9 100644 --- a/translated_images/uk/.co-op-translator.json +++ b/translated_images/uk/.co-op-translator.json @@ -1,512 +1,20 @@ { - "favicon.37b561214b36d454.webp": { - "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", - "translation_date": "2026-01-16T06:58:23+00:00", - "source_file": "images/favicon.png", - "language_code": "uk" - }, - "ai-nlp.b22dcb8ca4707cea.webp": { - "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", - "translation_date": "2026-01-16T06:58:30+00:00", - "source_file": "lessons/sketchnotes/ai-nlp.png", - "language_code": "uk" - }, - "ai-symbolic.715a30cb610411a6.webp": { - "original_hash": "69d3628566f680ac8543651aa6fd520c", - "translation_date": "2026-01-16T06:58:56+00:00", - "source_file": "lessons/sketchnotes/ai-symbolic.png", - "language_code": "uk" - }, - "ai-computervision.6506ebebac3fbf76.webp": { - "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", - "translation_date": "2026-01-16T06:59:23+00:00", - "source_file": "lessons/sketchnotes/ai-computervision.png", - "language_code": "uk" - }, - "ai-for-beginners.b354ca904b22cd70.webp": { - "original_hash": "4b6f076798ec72ec7736b2e9039730e3", - "translation_date": "2026-01-16T06:59:42+00:00", - "source_file": "lessons/sketchnotes/ai-for-beginners.png", - "language_code": "uk" - }, - "ai-overview.0857791951d19500.webp": { - "original_hash": "7206f99da5c2b99d21581f946a660235", - "translation_date": "2026-01-16T06:59:53+00:00", - "source_file": "lessons/sketchnotes/ai-overview.png", - "language_code": "uk" - }, - "ai-intro.bf28d1ac4235881c.webp": { - "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", - "translation_date": "2026-01-16T07:00:16+00:00", - "source_file": "lessons/sketchnotes/ai-intro.png", - "language_code": "uk" - }, - "ai-neuralnetworks.1c687ae40bc86e83.webp": { - "original_hash": "6426ed635d4beb0ee499d634dfb61d65", - "translation_date": "2026-01-16T07:00:48+00:00", - "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", - "language_code": "uk" - }, - "vae.464c465a5b6a9e25.webp": { - "original_hash": "0b658c7862077e139162c756bcb98071", - "translation_date": "2026-01-16T07:01:07+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", - "language_code": "uk" - }, - "vaemnist-diag.694315f775d5d666.webp": { - "original_hash": "0652f5a95005348c6b1533438103dfcf", - "translation_date": "2026-01-16T07:01:10+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", - "language_code": "uk" - }, - "autoencoder_schema.5e6fc9ad98a5eb61.webp": { - "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", - "translation_date": "2026-01-16T07:01:13+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", - "language_code": "uk" - }, - "vaemnist.cab9e602dc08dc50.webp": { - "original_hash": "8159b2f649e6dd8efa071455d6f222b6", - "translation_date": "2026-01-16T07:01:19+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", - "language_code": "uk" - }, - "aae.9d418a990fc75bf9.webp": { - "original_hash": "92f89b37641f659a7d25c91d13076f69", - "translation_date": "2026-01-16T07:01:23+00:00", - "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", - "language_code": "uk" - }, - "instance_vs_semantic.eee9812bebf8cd45.webp": { - "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", - "translation_date": "2026-01-16T07:01:30+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", - "language_code": "uk" - }, - "unet.3adb555bf39d3657.webp": { - "original_hash": "49a151c11708ee9a3e94d21448146bf8", - "translation_date": "2026-01-16T07:01:40+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", - "language_code": "uk" - }, - "navi.2f20b727910110ea.webp": { - "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", - "translation_date": "2026-01-16T07:01:49+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", - "language_code": "uk" - }, - "segm.92442f2cb42ff4fa.webp": { - "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", - "translation_date": "2026-01-16T07:01:54+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", - "language_code": "uk" - }, - "segnet.87377542aa5a8b76.webp": { - "original_hash": "fa6d2d499aa2ae589a14caede7534561", - "translation_date": "2026-01-16T07:02:02+00:00", - "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", - "language_code": "uk" - }, - "gan_architecture.8f3a5ab62b8d5d69.webp": { - "original_hash": "4993c22b32d24c9d2d087645c2a90d81", - "translation_date": "2026-01-16T07:02:09+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", - "language_code": "uk" - }, - "style.5293e85e077ab22c.webp": { - "original_hash": "f797246177c68cc33bcdf7abae8c9b68", - "translation_date": "2026-01-16T07:02:14+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", - "language_code": "uk" - }, - "image.896e8254a2c60d45.webp": { - "original_hash": "0033165481f191386403b85801811833", - "translation_date": "2026-01-16T07:02:16+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", - "language_code": "uk" - }, - "gan_arch_detail.46b95fd366f8e543.webp": { - "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", - "translation_date": "2026-01-16T07:02:20+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", - "language_code": "uk" - }, - "dcgan_generator.b500988ec2bc8ba5.webp": { - "original_hash": "a11642e50f68e41c69b1580c9b724ef1", - "translation_date": "2026-01-16T07:02:31+00:00", - "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", - "language_code": "uk" - }, - "ideal-zebra.7f70e8b54ee15a7a.webp": { - "original_hash": "6944fb46795f714f0ce8e856c405498a", - "translation_date": "2026-01-16T07:02:37+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", - "language_code": "uk" - }, - "ideal-cat-loop.999fbb8ff306e044.webp": { - "original_hash": "c54e983c591431338bf8ddac9ab8415b", - "translation_date": "2026-01-16T07:02:39+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", - "language_code": "uk" - }, - "dog-from-unsplash.426f9fbca2febc93.webp": { - "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", - "translation_date": "2026-01-16T07:02:46+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", - "language_code": "uk" - }, - "features.6291f9c7ba3a0b95.webp": { - "original_hash": "e2727bfacc1156e045d1879bbe86e189", - "translation_date": "2026-01-16T07:02:48+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", - "language_code": "uk" - }, - "ideal-cat.203dd4597643d6b0.webp": { - "original_hash": "5b44760be530a91be18a5cceebbc2cc3", - "translation_date": "2026-01-16T07:02:50+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", - "language_code": "uk" - }, - "adversarial-dog.d9fc7773b0142b89.webp": { - "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", - "translation_date": "2026-01-16T07:02:51+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", - "language_code": "uk" - }, - "catsdogsdataset.a7aff8e6085fd3f0.webp": { - "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", - "translation_date": "2026-01-16T07:02:52+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", - "language_code": "uk" - }, - "original-dog.8f68a67d2fe0911f.webp": { - "original_hash": "3ed859629b4141f735fd0d3c1941f520", - "translation_date": "2026-01-16T07:02:55+00:00", - "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", - "language_code": "uk" - }, - "braille.341962ff76b1bd70.webp": { - "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", - "translation_date": "2026-01-16T07:02:56+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", - "language_code": "uk" - }, - "braille-symbols.0159185ab69d5339.webp": { - "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", - "translation_date": "2026-01-16T07:02:57+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", - "language_code": "uk" - }, - "frame-difference.706f805491a0883c.webp": { - "original_hash": "a141e72f08e1b8f7451392889af90072", - "translation_date": "2026-01-16T07:03:01+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", - "language_code": "uk" - }, - "braille-result.46530fea020b03c7.webp": { - "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", - "translation_date": "2026-01-16T07:03:02+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", - "language_code": "uk" - }, - "palm-movement.341495f0e9c47da3.webp": { - "original_hash": "100780b2e1d5adff2739adf58fc18404", - "translation_date": "2026-01-16T07:03:03+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", - "language_code": "uk" - }, - "optical.1f4a94464579a83a.webp": { - "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", - "translation_date": "2026-01-16T07:03:05+00:00", - "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", - "language_code": "uk" - }, "1200px-Girl_and_cat.89bd70951181e86a.webp": { "original_hash": "aa8cdeaa9beaad5a06610236cf22f296", "translation_date": "2026-01-16T07:03:07+00:00", "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/1200px-Girl_and_cat.jpg", "language_code": "uk" }, - "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { - "original_hash": "f31ea979f0ceabdf198899985ac84c37", - "translation_date": "2026-01-16T07:03:11+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", - "language_code": "uk" - }, - "naive-detection.e7f1ba220ccd08c6.webp": { - "original_hash": "4c96961c12a09f8e055546ed2e7de470", - "translation_date": "2026-01-16T07:03:20+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", - "language_code": "uk" - }, - "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { - "original_hash": "6704085c522f47ce42ad8402dafe6429", - "translation_date": "2026-01-16T07:03:25+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", - "language_code": "uk" - }, - "iou_equation.9a4751d40fff4e11.webp": { - "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", - "translation_date": "2026-01-16T07:03:30+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", - "language_code": "uk" - }, - "coco-examples.71bc60380fa6cceb.webp": { - "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", - "translation_date": "2026-01-16T07:03:33+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", - "language_code": "uk" - }, - "f-rcnn.3cda6d9bb4188875.webp": { - "original_hash": "fdafedad20701c95bdcf6bb923822ab1", - "translation_date": "2026-01-16T07:03:38+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", - "language_code": "uk" - }, - "rcnn1.cae407020dfb1d1f.webp": { - "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", - "translation_date": "2026-01-16T07:03:45+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", - "language_code": "uk" - }, - "faster-rcnn.8d46c099b87ef30a.webp": { - "original_hash": "067e2ca96344fd6d0490e0530a922b36", - "translation_date": "2026-01-16T07:03:50+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", - "language_code": "uk" - }, - "r-fcn.13eb88158b99a3da.webp": { - "original_hash": "38cd0e0105546e56fa17b711d445195f", - "translation_date": "2026-01-16T07:03:58+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", - "language_code": "uk" - }, - "yolo.a2648ec82ee8bb4e.webp": { - "original_hash": "e8835638234f5c21fcf36fdede6457f4", - "translation_date": "2026-01-16T07:04:04+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", - "language_code": "uk" - }, - "rcnn2.2d9530bb83516484.webp": { - "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", - "translation_date": "2026-01-16T07:04:09+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", - "language_code": "uk" - }, - "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { - "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", - "translation_date": "2026-01-16T07:04:20+00:00", - "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", - "language_code": "uk" - }, - "resnet-block.aba4ccbcc0944434.webp": { - "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", - "translation_date": "2026-01-16T07:04:31+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", - "language_code": "uk" - }, - "cnn-pyramid.85915455759ef0ce.webp": { - "original_hash": "7233ded4a920332806363d704bfb59a6", - "translation_date": "2026-01-16T07:04:40+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", - "language_code": "uk" - }, - "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { - "original_hash": "c9bde577c8b279b5199a8b294ee9494f", - "translation_date": "2026-01-16T07:04:54+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", - "language_code": "uk" - }, - "filter-horiz.59b80ed4feb946ef.webp": { - "original_hash": "b081df9e2042850983a46ff817b88d55", - "translation_date": "2026-01-16T07:04:57+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", - "language_code": "uk" - }, - "vgg-16-arch1.d901a5583b3a51ba.webp": { - "original_hash": "5b0f835d04dc20d097a0b89c88339966", - "translation_date": "2026-01-16T07:05:01+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", - "language_code": "uk" - }, - "vgg-16-arch.64ff2137f50dd49f.webp": { - "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", - "translation_date": "2026-01-16T07:05:08+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", - "language_code": "uk" - }, - "convolutionExample.634615d5ff7081e0.webp": { - "original_hash": "5412e092848cb3cd4fa527aba3be0545", - "translation_date": "2026-01-16T07:05:15+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", - "language_code": "uk" - }, - "inception.a6605b85bcbc6f52.webp": { - "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", - "translation_date": "2026-01-16T07:05:22+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", - "language_code": "uk" - }, - "filter-vert.b7148390ca0bc356.webp": { - "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", - "translation_date": "2026-01-16T07:05:27+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", - "language_code": "uk" - }, - "lmfilters.ea9e4868a82cf74c.webp": { - "original_hash": "aa029ea2c45afbac3026a0a558eeec43", - "translation_date": "2026-01-16T07:05:31+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", - "language_code": "uk" - }, - "data.50b2a9d5484bdbf0.webp": { - "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", - "translation_date": "2026-01-16T07:05:38+00:00", - "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", - "language_code": "uk" - }, - "NetLogo-ModelLib.efe023afb4763c05.webp": { - "original_hash": "edd5b28318e2f43274a4541408110fb9", - "translation_date": "2026-01-16T07:05:49+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", - "language_code": "uk" - }, - "NetLogo-Main.32653711ec1a01b3.webp": { - "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", - "translation_date": "2026-01-16T07:06:12+00:00", - "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", - "language_code": "uk" - }, - "cartpole.f52a67f27e058170.webp": { - "original_hash": "5399242e127ea1c18aa6ee405daecf51", - "translation_date": "2026-01-16T07:06:31+00:00", - "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", - "language_code": "uk" - }, - "mountaincar.f7b7a7f6d4f9933b.webp": { - "original_hash": "61c868cc389dc92bd2b402ea490cd162", - "translation_date": "2026-01-16T07:06:32+00:00", - "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", - "language_code": "uk" - }, - "ml-for-beginners.9e4fed176fd5817d.webp": { - "original_hash": "cd606a24083e039082b0486fc8382823", - "translation_date": "2026-01-16T07:06:34+00:00", - "source_file": "lessons/1-Intro/images/ml-for-beginners.png", - "language_code": "uk" - }, - "history-of-ai.7e83efa70b537f5a.webp": { - "original_hash": "644e648b98fcb10fb9713452ff02934d", - "translation_date": "2026-01-16T07:06:41+00:00", - "source_file": "lessons/1-Intro/images/history-of-ai.png", - "language_code": "uk" - }, - "photo-cat.8c8e8fb760ffe457.webp": { - "original_hash": "29d10fef28d240c48995ef9dd23e477a", - "translation_date": "2026-01-16T07:06:54+00:00", - "source_file": "lessons/1-Intro/images/photo-cat.jpg", - "language_code": "uk" - }, - "dsh_age.d212a30d4e54fb5f.webp": { - "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", - "translation_date": "2026-01-16T07:06:55+00:00", - "source_file": "lessons/1-Intro/images/dsh_age.png", - "language_code": "uk" - }, - "turing-test-evol.4184696701293ead.webp": { - "original_hash": "80d11b1074d61e5d6e4a207f72902e89", - "translation_date": "2026-01-16T07:07:00+00:00", - "source_file": "lessons/1-Intro/images/turing-test-evol.png", - "language_code": "uk" - }, - "knowledge-spectrum.b60df631852c0217.webp": { - "original_hash": "71b049ee26a22a68996034585436ca59", - "translation_date": "2026-01-16T07:07:11+00:00", - "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", - "language_code": "uk" - }, - "DIKW_Pyramid.94126f7d2bd8db5b.webp": { - "original_hash": "ad410ec7f25454482fd4516c4a46fc67", - "translation_date": "2026-01-16T07:07:24+00:00", - "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", - "language_code": "uk" - }, "AND-OR-Tree.5592d2c70187f283.webp": { "original_hash": "2674b6cf8f768491c6b5a167f272a002", "translation_date": "2026-01-16T07:07:43+00:00", "source_file": "lessons/2-Symbolic/images/AND-OR-Tree.png", "language_code": "uk" }, - "triplet-complex.32094972c7b4441b.webp": { - "original_hash": "56a2e05839a141c311db52655b37f8ad", - "translation_date": "2026-01-16T07:08:22+00:00", - "source_file": "lessons/2-Symbolic/images/triplet-complex.png", - "language_code": "uk" - }, - "arch-human.5d4d35f1bba3ab1c.webp": { - "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", - "translation_date": "2026-01-16T07:08:39+00:00", - "source_file": "lessons/2-Symbolic/images/arch-human.png", - "language_code": "uk" - }, - "arch-kbs.3ec5c150b09fa8da.webp": { - "original_hash": "f470e6ec071db529cd3149052cfeb8ff", - "translation_date": "2026-01-16T07:08:46+00:00", - "source_file": "lessons/2-Symbolic/images/arch-kbs.png", - "language_code": "uk" - }, - "triplet.4b9b332587593298.webp": { - "original_hash": "302e53ea355ffb556d99e3962d0a6516", - "translation_date": "2026-01-16T07:08:55+00:00", - "source_file": "lessons/2-Symbolic/images/triplet.png", - "language_code": "uk" - }, - "protege.274177ceeac13b38.webp": { - "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", - "translation_date": "2026-01-16T07:09:18+00:00", - "source_file": "lessons/2-Symbolic/images/protege.png", - "language_code": "uk" - }, - "synapse-wikipedia.ed20a9e4726ea1c6.webp": { - "original_hash": "88212730ecd9b0c8b848c319951427d8", - "translation_date": "2026-01-16T07:09:57+00:00", - "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", - "language_code": "uk" - }, - "overfit2.131f5800ae10ca5e.webp": { - "original_hash": "eb04381b2f222518ec400b98ebf441b2", - "translation_date": "2026-01-16T07:10:03+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", - "language_code": "uk" - }, - "netout.1eb15eb76fd76731.webp": { - "original_hash": "187261e2b5036746ee9d9106b1f7df1b", - "translation_date": "2026-01-16T07:10:05+00:00", - "source_file": "lessons/3-NeuralNetworks/images/netout.png", - "language_code": "uk" - }, - "artneuron.1a5daa88d20ebe6f.webp": { - "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", - "translation_date": "2026-01-16T07:10:07+00:00", - "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", - "language_code": "uk" - }, - "Overfitting.408ad91cd90b4371.webp": { - "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", - "translation_date": "2026-01-16T07:10:14+00:00", - "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", - "language_code": "uk" - }, - "overfit1.f24b71c6f652e59e.webp": { - "original_hash": "76155698e85340d9dfff8e0a628d25c1", - "translation_date": "2026-01-16T07:10:20+00:00", - "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", - "language_code": "uk" - }, - "NeuroArch.4e17cdba5e445721.webp": { - "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", - "translation_date": "2026-01-16T07:10:24+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "ComputeGraph.463c9d8ebdcb2215.webp": { + "original_hash": "7af66742d6bede114f971689745bedf2", + "translation_date": "2026-01-16T07:10:42+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", "language_code": "uk" }, "ComputeGraphGrad.4626252c0de03507.webp": { @@ -515,66 +23,18 @@ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraphGrad.png", "language_code": "uk" }, + "CoreferenceResolution.861924d6d384a7d6.webp": { + "original_hash": "25b5719ec70aaa44858076c16f7c208f", + "translation_date": "2026-01-16T07:13:18+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", + "language_code": "uk" + }, "Cross-Entropy-Loss.dc7ba633d2467ef3.webp": { "original_hash": "11dd0fd77a272755d0ef5db9f71217da", "translation_date": "2026-01-16T07:10:35+00:00", "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/Cross-Entropy-Loss.png", "language_code": "uk" }, - "ComputeGraph.463c9d8ebdcb2215.webp": { - "original_hash": "7af66742d6bede114f971689745bedf2", - "translation_date": "2026-01-16T07:10:42+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/ComputeGraph.png", - "language_code": "uk" - }, - "overfit.a0bd57f717c15769.webp": { - "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", - "translation_date": "2026-01-16T07:10:45+00:00", - "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", - "language_code": "uk" - }, - "Rosenblatt-wikipedia.294821b285ac796d.webp": { - "original_hash": "c21d9b47d0106208a0f35a920d6bff66", - "translation_date": "2026-01-16T07:10:49+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", - "language_code": "uk" - }, - "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { - "original_hash": "2cc48ff435c89ca1e162872a42b4813c", - "translation_date": "2026-01-16T07:10:51+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", - "language_code": "uk" - }, - "activation-func.b4924007c7ce7764.webp": { - "original_hash": "8d357884343ec923611a319d4e910b99", - "translation_date": "2026-01-16T07:10:53+00:00", - "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", - "language_code": "uk" - }, - "clip-class.3af42ef0b2b19369.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:10:58+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", - "language_code": "uk" - }, - "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { - "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", - "translation_date": "2026-01-16T07:11:03+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", - "language_code": "uk" - }, - "clip-arch.b3dbf20b4e8ed8be.webp": { - "original_hash": "bdd1638453069a216e843e1a8fd70db0", - "translation_date": "2026-01-16T07:11:06+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", - "language_code": "uk" - }, - "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { - "original_hash": "e300d75d78f6050bc7b83df091f95775", - "translation_date": "2026-01-16T07:11:12+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", - "language_code": "uk" - }, "DALL·E 2023-06-20 15.56.56 - a closeup watercolor portrait of young male teacher of literature with a book.56499a0c282407c9.webp": { "original_hash": "dd063fda04db937ab7210064af9d6151", "translation_date": "2026-01-16T07:11:14+00:00", @@ -587,10 +47,82 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.57.43 - a closeup oil portrait of young female teacher of computer science with a computer.png", "language_code": "uk" }, - "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { - "original_hash": "ec89cbb600b14e86f353a347506554ba", - "translation_date": "2026-01-16T07:11:17+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", + "DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.534175cf58a361d9.webp": { + "original_hash": "e300d75d78f6050bc7b83df091f95775", + "translation_date": "2026-01-16T07:11:12+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/DALL·E 2023-06-20 15.58.42 - a closeup oil portrait of old male teacher of mathematics in front of blackboard.png", + "language_code": "uk" + }, + "DIKW_Pyramid.94126f7d2bd8db5b.webp": { + "original_hash": "ad410ec7f25454482fd4516c4a46fc67", + "translation_date": "2026-01-16T07:07:24+00:00", + "source_file": "lessons/2-Symbolic/images/DIKW_Pyramid.png", + "language_code": "uk" + }, + "FeatureExtractionCNN.d9b456cbdae7cb64.webp": { + "original_hash": "c9bde577c8b279b5199a8b294ee9494f", + "translation_date": "2026-01-16T07:04:54+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/FeatureExtractionCNN.png", + "language_code": "uk" + }, + "Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp": { + "original_hash": "2cc48ff435c89ca1e162872a42b4813c", + "translation_date": "2026-01-16T07:10:51+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Mark_I_perceptron_wikipedia.jpg", + "language_code": "uk" + }, + "NetLogo-Main.32653711ec1a01b3.webp": { + "original_hash": "83a9fe96394620fc703a5f2de2d15ed1", + "translation_date": "2026-01-16T07:06:12+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-Main.png", + "language_code": "uk" + }, + "NetLogo-ModelLib.efe023afb4763c05.webp": { + "original_hash": "edd5b28318e2f43274a4541408110fb9", + "translation_date": "2026-01-16T07:05:49+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/images/NetLogo-ModelLib.png", + "language_code": "uk" + }, + "NeuroArch.4e17cdba5e445721.webp": { + "original_hash": "5a3b1a4c04e6b6b5a65574d5ea92a272", + "translation_date": "2026-01-16T07:10:24+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/NeuroArch.png", + "language_code": "uk" + }, + "ObjDetectionPrecisionRecall.d2ef5b6081a0b094.webp": { + "original_hash": "6704085c522f47ce42ad8402dafe6429", + "translation_date": "2026-01-16T07:03:25+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecall.png", + "language_code": "uk" + }, + "ObjDetectionPrecisionRecallIoU.96b4116fcd30ce5a.webp": { + "original_hash": "f31ea979f0ceabdf198899985ac84c37", + "translation_date": "2026-01-16T07:03:11+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/ObjDetectionPrecisionRecallIoU.png", + "language_code": "uk" + }, + "Overfitting.408ad91cd90b4371.webp": { + "original_hash": "82c3203fefc4ef74609e8ab61c1c683b", + "translation_date": "2026-01-16T07:10:14+00:00", + "source_file": "lessons/3-NeuralNetworks/images/Overfitting.png", + "language_code": "uk" + }, + "Rosenblatt-wikipedia.294821b285ac796d.webp": { + "original_hash": "c21d9b47d0106208a0f35a920d6bff66", + "translation_date": "2026-01-16T07:10:49+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/Rosenblatt-wikipedia.jpg", + "language_code": "uk" + }, + "Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp": { + "original_hash": "456419e07e4f1b5ab90c6f6d36d9817a", + "translation_date": "2026-01-16T07:04:20+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/Screen_Shot_2016-11-17_at_11.14.54_AM.png", + "language_code": "uk" + }, + "a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp": { + "original_hash": "9c386a6fd2c04edbd78dc9d688b59872", + "translation_date": "2026-01-16T07:11:03+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_old_male_teacher_of_math.png", "language_code": "uk" }, "a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp": { @@ -599,22 +131,88 @@ "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png", "language_code": "uk" }, - "vqgan.5027fe05051dfa31.webp": { - "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", - "translation_date": "2026-01-16T07:11:19+00:00", - "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp": { + "original_hash": "ec89cbb600b14e86f353a347506554ba", + "translation_date": "2026-01-16T07:11:17+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png", "language_code": "uk" }, - "bag-of-words-example.606fc1738f1d7ba9.webp": { - "original_hash": "a8fa84622ff35939e498d06fac3fa515", - "translation_date": "2026-01-16T07:11:23+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", + "aae.9d418a990fc75bf9.webp": { + "original_hash": "92f89b37641f659a7d25c91d13076f69", + "translation_date": "2026-01-16T07:01:23+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/aae.png", "language_code": "uk" }, - "bow.3811869cff59368d.webp": { - "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", - "translation_date": "2026-01-16T07:11:36+00:00", - "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", + "activation-func.b4924007c7ce7764.webp": { + "original_hash": "8d357884343ec923611a319d4e910b99", + "translation_date": "2026-01-16T07:10:53+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/images/activation-func.png", + "language_code": "uk" + }, + "adversarial-dog.d9fc7773b0142b89.webp": { + "original_hash": "cf7a833a6f82bdf5049180a09f9bf8f6", + "translation_date": "2026-01-16T07:02:51+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/adversarial-dog.png", + "language_code": "uk" + }, + "ai-computervision.6506ebebac3fbf76.webp": { + "original_hash": "69793d04780af37a3f32c9aa5c2d1ad8", + "translation_date": "2026-01-16T06:59:23+00:00", + "source_file": "lessons/sketchnotes/ai-computervision.png", + "language_code": "uk" + }, + "ai-for-beginners.b354ca904b22cd70.webp": { + "original_hash": "4b6f076798ec72ec7736b2e9039730e3", + "translation_date": "2026-01-16T06:59:42+00:00", + "source_file": "lessons/sketchnotes/ai-for-beginners.png", + "language_code": "uk" + }, + "ai-intro.bf28d1ac4235881c.webp": { + "original_hash": "9d1e65416cc17cf9a373a1cff01f04a4", + "translation_date": "2026-01-16T07:00:16+00:00", + "source_file": "lessons/sketchnotes/ai-intro.png", + "language_code": "uk" + }, + "ai-neuralnetworks.1c687ae40bc86e83.webp": { + "original_hash": "6426ed635d4beb0ee499d634dfb61d65", + "translation_date": "2026-01-16T07:00:48+00:00", + "source_file": "lessons/sketchnotes/ai-neuralnetworks.png", + "language_code": "uk" + }, + "ai-nlp.b22dcb8ca4707cea.webp": { + "original_hash": "fc9259e7fd3bcbc2ce15909701a4c284", + "translation_date": "2026-01-16T06:58:30+00:00", + "source_file": "lessons/sketchnotes/ai-nlp.png", + "language_code": "uk" + }, + "ai-overview.0857791951d19500.webp": { + "original_hash": "7206f99da5c2b99d21581f946a660235", + "translation_date": "2026-01-16T06:59:53+00:00", + "source_file": "lessons/sketchnotes/ai-overview.png", + "language_code": "uk" + }, + "ai-symbolic.715a30cb610411a6.webp": { + "original_hash": "69d3628566f680ac8543651aa6fd520c", + "translation_date": "2026-01-16T06:58:56+00:00", + "source_file": "lessons/sketchnotes/ai-symbolic.png", + "language_code": "uk" + }, + "arch-human.5d4d35f1bba3ab1c.webp": { + "original_hash": "3b41c1a38a69fb1104f5ddc48163538d", + "translation_date": "2026-01-16T07:08:39+00:00", + "source_file": "lessons/2-Symbolic/images/arch-human.png", + "language_code": "uk" + }, + "arch-kbs.3ec5c150b09fa8da.webp": { + "original_hash": "f470e6ec071db529cd3149052cfeb8ff", + "translation_date": "2026-01-16T07:08:46+00:00", + "source_file": "lessons/2-Symbolic/images/arch-kbs.png", + "language_code": "uk" + }, + "artneuron.1a5daa88d20ebe6f.webp": { + "original_hash": "c2d8af8285e1eee1cf6c5ba4762f70ab", + "translation_date": "2026-01-16T07:10:07+00:00", + "source_file": "lessons/3-NeuralNetworks/images/artneuron.png", "language_code": "uk" }, "ascii-character-map.18ed6aa7f3b0a7ff.webp": { @@ -623,34 +221,16 @@ "source_file": "lessons/5-NLP/13-TextRep/images/ascii-character-map.png", "language_code": "uk" }, - "multi-layer-lstm.dd975e29bb2a59fe.webp": { - "original_hash": "27b6355fd86c9e8e6d443015653be763", - "translation_date": "2026-01-16T07:11:59+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "autoencoder_schema.5e6fc9ad98a5eb61.webp": { + "original_hash": "3fb68572368c18bc334ef8d6dec0fee5", + "translation_date": "2026-01-16T07:01:13+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/autoencoder_schema.jpg", "language_code": "uk" }, - "rnn-anatomy.79ee3f3920b3294b.webp": { - "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", - "translation_date": "2026-01-16T07:12:04+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", - "language_code": "uk" - }, - "rnn.27f5c29c53d727b5.webp": { - "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", - "translation_date": "2026-01-16T07:12:15+00:00", - "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", - "language_code": "uk" - }, - "encoder-decoder-attention.7a726296894fb567.webp": { - "original_hash": "e0546cbc8252d764df7f7212b371f0ed", - "translation_date": "2026-01-16T07:12:28+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", - "language_code": "uk" - }, - "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { - "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", - "translation_date": "2026-01-16T07:12:40+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "bag-of-words-example.606fc1738f1d7ba9.webp": { + "original_hash": "a8fa84622ff35939e498d06fac3fa515", + "translation_date": "2026-01-16T07:11:23+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bag-of-words-example.png", "language_code": "uk" }, "bahdanau-fig3.09ba2d37f202a6af.webp": { @@ -659,46 +239,100 @@ "source_file": "lessons/5-NLP/18-Transformers/images/bahdanau-fig3.png", "language_code": "uk" }, - "pos-embedding.e41ce9b6cf6078af.webp": { - "original_hash": "f0910082dcac063f3baae2e1f28b4e30", - "translation_date": "2026-01-16T07:12:58+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", - "language_code": "uk" - }, - "transformer-layer.905e14747ca4e7d5.webp": { - "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", - "translation_date": "2026-01-16T07:13:08+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", - "language_code": "uk" - }, - "CoreferenceResolution.861924d6d384a7d6.webp": { - "original_hash": "25b5719ec70aaa44858076c16f7c208f", - "translation_date": "2026-01-16T07:13:18+00:00", - "source_file": "lessons/5-NLP/18-Transformers/images/CoreferenceResolution.png", - "language_code": "uk" - }, "bot-ner.4b09235dbb0ad275.webp": { "original_hash": "5e61aca4f94182c7e7d509b8d2de3c9f", "translation_date": "2026-01-16T07:13:31+00:00", "source_file": "lessons/5-NLP/19-NER/images/bot-ner.png", "language_code": "uk" }, - "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { - "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", - "translation_date": "2026-01-16T07:13:44+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "bow.3811869cff59368d.webp": { + "original_hash": "bfcb38af6b1cbc8c2e86101127b642ac", + "translation_date": "2026-01-16T07:11:36+00:00", + "source_file": "lessons/5-NLP/13-TextRep/images/bow.png", "language_code": "uk" }, - "rnn-generate.56c54afb52f9781d.webp": { - "original_hash": "67332ada2d0603921bba37c06956c70e", - "translation_date": "2026-01-16T07:13:48+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "braille-result.46530fea020b03c7.webp": { + "original_hash": "7c069b6ddda38dcd0b535a840b954ee1", + "translation_date": "2026-01-16T07:03:02+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-result.png", "language_code": "uk" }, - "rnn-generate-inf.5168dc65e0370eea.webp": { - "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", - "translation_date": "2026-01-16T07:13:54+00:00", - "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "braille-symbols.0159185ab69d5339.webp": { + "original_hash": "5a7fddf66299dbb4eae490b631ee3a1c", + "translation_date": "2026-01-16T07:02:57+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/braille-symbols.png", + "language_code": "uk" + }, + "braille.341962ff76b1bd70.webp": { + "original_hash": "ef1d59d4fb17f1f019c18be162c5759a", + "translation_date": "2026-01-16T07:02:56+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/data/braille.jpeg", + "language_code": "uk" + }, + "cartpole.f52a67f27e058170.webp": { + "original_hash": "5399242e127ea1c18aa6ee405daecf51", + "translation_date": "2026-01-16T07:06:31+00:00", + "source_file": "lessons/6-Other/22-DeepRL/images/cartpole.png", + "language_code": "uk" + }, + "catsdogsdataset.a7aff8e6085fd3f0.webp": { + "original_hash": "3039ba35434f67e69ccbb44d9e6ee141", + "translation_date": "2026-01-16T07:02:52+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/catsdogsdataset.png", + "language_code": "uk" + }, + "clip-arch.b3dbf20b4e8ed8be.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:11:06+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-arch.png", + "language_code": "uk" + }, + "clip-class.3af42ef0b2b19369.webp": { + "original_hash": "bdd1638453069a216e843e1a8fd70db0", + "translation_date": "2026-01-16T07:10:58+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/clip-class.png", + "language_code": "uk" + }, + "cnn-pyramid.85915455759ef0ce.webp": { + "original_hash": "7233ded4a920332806363d704bfb59a6", + "translation_date": "2026-01-16T07:04:40+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/cnn-pyramid.png", + "language_code": "uk" + }, + "coco-examples.71bc60380fa6cceb.webp": { + "original_hash": "bcfe5693147ca18d88cf43b1d2d5d6d7", + "translation_date": "2026-01-16T07:03:33+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/coco-examples.jpg", + "language_code": "uk" + }, + "convolutionExample.634615d5ff7081e0.webp": { + "original_hash": "5412e092848cb3cd4fa527aba3be0545", + "translation_date": "2026-01-16T07:05:15+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/convolutionExample.png", + "language_code": "uk" + }, + "data.50b2a9d5484bdbf0.webp": { + "original_hash": "e501593d25b15c8f8860fe11e3f1c4a7", + "translation_date": "2026-01-16T07:05:38+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/images/data.png", + "language_code": "uk" + }, + "dcgan_generator.b500988ec2bc8ba5.webp": { + "original_hash": "a11642e50f68e41c69b1580c9b724ef1", + "translation_date": "2026-01-16T07:02:31+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/dcgan_generator.png", + "language_code": "uk" + }, + "dog-from-unsplash.426f9fbca2febc93.webp": { + "original_hash": "9669f6d7c9c8b74efdd1a82a262d1766", + "translation_date": "2026-01-16T07:02:46+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/dog-from-unsplash.jpg", + "language_code": "uk" + }, + "dsh_age.d212a30d4e54fb5f.webp": { + "original_hash": "61b9b2e2e29d9be9ae8f2edd8fa14ed4", + "translation_date": "2026-01-16T07:06:55+00:00", + "source_file": "lessons/1-Intro/images/dsh_age.png", "language_code": "uk" }, "embedding-classifier-example.b77f021a7ee67eee.webp": { @@ -707,10 +341,10 @@ "source_file": "lessons/5-NLP/14-Embeddings/images/embedding-classifier-example.png", "language_code": "uk" }, - "offset-sequence-representation.eb73fcefb29b46ee.webp": { - "original_hash": "52e7632a2b668957b903bb2607e953fe", - "translation_date": "2026-01-16T07:14:04+00:00", - "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "encoder-decoder-attention.7a726296894fb567.webp": { + "original_hash": "e0546cbc8252d764df7f7212b371f0ed", + "translation_date": "2026-01-16T07:12:28+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/encoder-decoder-attention.png", "language_code": "uk" }, "example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp": { @@ -718,5 +352,371 @@ "translation_date": "2026-01-16T07:14:09+00:00", "source_file": "lessons/5-NLP/14-Embeddings/images/example-algorithms-for-converting-words-to-vectors.png", "language_code": "uk" + }, + "f-rcnn.3cda6d9bb4188875.webp": { + "original_hash": "fdafedad20701c95bdcf6bb923822ab1", + "translation_date": "2026-01-16T07:03:38+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/f-rcnn.png", + "language_code": "uk" + }, + "faster-rcnn.8d46c099b87ef30a.webp": { + "original_hash": "067e2ca96344fd6d0490e0530a922b36", + "translation_date": "2026-01-16T07:03:50+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/faster-rcnn.png", + "language_code": "uk" + }, + "favicon.37b561214b36d454.webp": { + "original_hash": "228faa6584f8ba1f7e9a75e3200112e9", + "translation_date": "2026-01-16T06:58:23+00:00", + "source_file": "images/favicon.png", + "language_code": "uk" + }, + "features.6291f9c7ba3a0b95.webp": { + "original_hash": "e2727bfacc1156e045d1879bbe86e189", + "translation_date": "2026-01-16T07:02:48+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/features.png", + "language_code": "uk" + }, + "filter-horiz.59b80ed4feb946ef.webp": { + "original_hash": "b081df9e2042850983a46ff817b88d55", + "translation_date": "2026-01-16T07:04:57+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-horiz.png", + "language_code": "uk" + }, + "filter-vert.b7148390ca0bc356.webp": { + "original_hash": "bef527fda3ae7113ec9ebb3ab74a6298", + "translation_date": "2026-01-16T07:05:27+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/filter-vert.png", + "language_code": "uk" + }, + "frame-difference.706f805491a0883c.webp": { + "original_hash": "a141e72f08e1b8f7451392889af90072", + "translation_date": "2026-01-16T07:03:01+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/frame-difference.png", + "language_code": "uk" + }, + "gan_arch_detail.46b95fd366f8e543.webp": { + "original_hash": "ba3b25748ca02c3e725e9a1969ae5c5d", + "translation_date": "2026-01-16T07:02:20+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_arch_detail.png", + "language_code": "uk" + }, + "gan_architecture.8f3a5ab62b8d5d69.webp": { + "original_hash": "4993c22b32d24c9d2d087645c2a90d81", + "translation_date": "2026-01-16T07:02:09+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/gan_architecture.png", + "language_code": "uk" + }, + "history-of-ai.7e83efa70b537f5a.webp": { + "original_hash": "644e648b98fcb10fb9713452ff02934d", + "translation_date": "2026-01-16T07:06:41+00:00", + "source_file": "lessons/1-Intro/images/history-of-ai.png", + "language_code": "uk" + }, + "ideal-cat-loop.999fbb8ff306e044.webp": { + "original_hash": "c54e983c591431338bf8ddac9ab8415b", + "translation_date": "2026-01-16T07:02:39+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat-loop.png", + "language_code": "uk" + }, + "ideal-cat.203dd4597643d6b0.webp": { + "original_hash": "5b44760be530a91be18a5cceebbc2cc3", + "translation_date": "2026-01-16T07:02:50+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-cat.png", + "language_code": "uk" + }, + "ideal-zebra.7f70e8b54ee15a7a.webp": { + "original_hash": "6944fb46795f714f0ce8e856c405498a", + "translation_date": "2026-01-16T07:02:37+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/ideal-zebra.png", + "language_code": "uk" + }, + "image.896e8254a2c60d45.webp": { + "original_hash": "0033165481f191386403b85801811833", + "translation_date": "2026-01-16T07:02:16+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/image.jpg", + "language_code": "uk" + }, + "inception.a6605b85bcbc6f52.webp": { + "original_hash": "ebf0f6b0257fffb906b532d86fce2a9c", + "translation_date": "2026-01-16T07:05:22+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/inception.png", + "language_code": "uk" + }, + "instance_vs_semantic.eee9812bebf8cd45.webp": { + "original_hash": "f21d7fdd7090fd9f8a3c1178a8521076", + "translation_date": "2026-01-16T07:01:30+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/instance_vs_semantic.jpeg", + "language_code": "uk" + }, + "iou_equation.9a4751d40fff4e11.webp": { + "original_hash": "0a27f4ab37ead8d77cdf94a0bbc99e4a", + "translation_date": "2026-01-16T07:03:30+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/iou_equation.png", + "language_code": "uk" + }, + "jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp": { + "original_hash": "47f7de9ada12b89dcfa75d81eb0aaf15", + "translation_date": "2026-01-16T07:12:40+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/jalammarBERT-language-modeling-masked-lm.png", + "language_code": "uk" + }, + "knowledge-spectrum.b60df631852c0217.webp": { + "original_hash": "71b049ee26a22a68996034585436ca59", + "translation_date": "2026-01-16T07:07:11+00:00", + "source_file": "lessons/2-Symbolic/images/knowledge-spectrum.png", + "language_code": "uk" + }, + "lmfilters.ea9e4868a82cf74c.webp": { + "original_hash": "aa029ea2c45afbac3026a0a558eeec43", + "translation_date": "2026-01-16T07:05:31+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/lmfilters.jpg", + "language_code": "uk" + }, + "ml-for-beginners.9e4fed176fd5817d.webp": { + "original_hash": "cd606a24083e039082b0486fc8382823", + "translation_date": "2026-01-16T07:06:34+00:00", + "source_file": "lessons/1-Intro/images/ml-for-beginners.png", + "language_code": "uk" + }, + "mountaincar.f7b7a7f6d4f9933b.webp": { + "original_hash": "61c868cc389dc92bd2b402ea490cd162", + "translation_date": "2026-01-16T07:06:32+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/images/mountaincar.png", + "language_code": "uk" + }, + "multi-layer-lstm.dd975e29bb2a59fe.webp": { + "original_hash": "27b6355fd86c9e8e6d443015653be763", + "translation_date": "2026-01-16T07:11:59+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/multi-layer-lstm.jpg", + "language_code": "uk" + }, + "naive-detection.e7f1ba220ccd08c6.webp": { + "original_hash": "4c96961c12a09f8e055546ed2e7de470", + "translation_date": "2026-01-16T07:03:20+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/naive-detection.png", + "language_code": "uk" + }, + "navi.2f20b727910110ea.webp": { + "original_hash": "fd3a1b48f7317e152edb2d1d943da24e", + "translation_date": "2026-01-16T07:01:49+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/navi.png", + "language_code": "uk" + }, + "netout.1eb15eb76fd76731.webp": { + "original_hash": "187261e2b5036746ee9d9106b1f7df1b", + "translation_date": "2026-01-16T07:10:05+00:00", + "source_file": "lessons/3-NeuralNetworks/images/netout.png", + "language_code": "uk" + }, + "offset-sequence-representation.eb73fcefb29b46ee.webp": { + "original_hash": "52e7632a2b668957b903bb2607e953fe", + "translation_date": "2026-01-16T07:14:04+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/images/offset-sequence-representation.png", + "language_code": "uk" + }, + "optical.1f4a94464579a83a.webp": { + "original_hash": "1be97f7f2f58285c9960a90e5d5ae337", + "translation_date": "2026-01-16T07:03:05+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/optical.png", + "language_code": "uk" + }, + "original-dog.8f68a67d2fe0911f.webp": { + "original_hash": "3ed859629b4141f735fd0d3c1941f520", + "translation_date": "2026-01-16T07:02:55+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/images/original-dog.png", + "language_code": "uk" + }, + "overfit.a0bd57f717c15769.webp": { + "original_hash": "810408efec3fc8cb44a2b4bc53466a6b", + "translation_date": "2026-01-16T07:10:45+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/images/overfit.png", + "language_code": "uk" + }, + "overfit1.f24b71c6f652e59e.webp": { + "original_hash": "76155698e85340d9dfff8e0a628d25c1", + "translation_date": "2026-01-16T07:10:20+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit1.jpg", + "language_code": "uk" + }, + "overfit2.131f5800ae10ca5e.webp": { + "original_hash": "eb04381b2f222518ec400b98ebf441b2", + "translation_date": "2026-01-16T07:10:03+00:00", + "source_file": "lessons/3-NeuralNetworks/images/overfit2.jpg", + "language_code": "uk" + }, + "palm-movement.341495f0e9c47da3.webp": { + "original_hash": "100780b2e1d5adff2739adf58fc18404", + "translation_date": "2026-01-16T07:03:03+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/images/palm-movement.png", + "language_code": "uk" + }, + "photo-cat.8c8e8fb760ffe457.webp": { + "original_hash": "29d10fef28d240c48995ef9dd23e477a", + "translation_date": "2026-01-16T07:06:54+00:00", + "source_file": "lessons/1-Intro/images/photo-cat.jpg", + "language_code": "uk" + }, + "pos-embedding.e41ce9b6cf6078af.webp": { + "original_hash": "f0910082dcac063f3baae2e1f28b4e30", + "translation_date": "2026-01-16T07:12:58+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/pos-embedding.png", + "language_code": "uk" + }, + "protege.274177ceeac13b38.webp": { + "original_hash": "56d5a5aba9b9e89a927f7fdc42ba16f5", + "translation_date": "2026-01-16T07:09:18+00:00", + "source_file": "lessons/2-Symbolic/images/protege.png", + "language_code": "uk" + }, + "r-fcn.13eb88158b99a3da.webp": { + "original_hash": "38cd0e0105546e56fa17b711d445195f", + "translation_date": "2026-01-16T07:03:58+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/r-fcn.png", + "language_code": "uk" + }, + "rcnn1.cae407020dfb1d1f.webp": { + "original_hash": "9cf0ea86d9dadf06a31cd109efc49796", + "translation_date": "2026-01-16T07:03:45+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn1.png", + "language_code": "uk" + }, + "rcnn2.2d9530bb83516484.webp": { + "original_hash": "cc44ad151b6d88e2838db475e7ab5dff", + "translation_date": "2026-01-16T07:04:09+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/rcnn2.png", + "language_code": "uk" + }, + "resnet-block.aba4ccbcc0944434.webp": { + "original_hash": "cf2131c7cb1053d6d2559ef83df057a8", + "translation_date": "2026-01-16T07:04:31+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/resnet-block.png", + "language_code": "uk" + }, + "rnn-anatomy.79ee3f3920b3294b.webp": { + "original_hash": "cac3c7102f2bc410efd6230b3bc58c63", + "translation_date": "2026-01-16T07:12:04+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn-anatomy.png", + "language_code": "uk" + }, + "rnn-generate-inf.5168dc65e0370eea.webp": { + "original_hash": "d3ed5c87de90c01b0b77ca02580b3707", + "translation_date": "2026-01-16T07:13:54+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate-inf.png", + "language_code": "uk" + }, + "rnn-generate.56c54afb52f9781d.webp": { + "original_hash": "67332ada2d0603921bba37c06956c70e", + "translation_date": "2026-01-16T07:13:48+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/rnn-generate.png", + "language_code": "uk" + }, + "rnn.27f5c29c53d727b5.webp": { + "original_hash": "bed0f1884d1a2c2620e6ba741af994b8", + "translation_date": "2026-01-16T07:12:15+00:00", + "source_file": "lessons/5-NLP/16-RNN/images/rnn.png", + "language_code": "uk" + }, + "segm.92442f2cb42ff4fa.webp": { + "original_hash": "87d6cbfe87db8fd64b45fa75ba863e60", + "translation_date": "2026-01-16T07:01:54+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segm.png", + "language_code": "uk" + }, + "segnet.87377542aa5a8b76.webp": { + "original_hash": "fa6d2d499aa2ae589a14caede7534561", + "translation_date": "2026-01-16T07:02:02+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/segnet.png", + "language_code": "uk" + }, + "style.5293e85e077ab22c.webp": { + "original_hash": "f797246177c68cc33bcdf7abae8c9b68", + "translation_date": "2026-01-16T07:02:14+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/images/style.jpg", + "language_code": "uk" + }, + "synapse-wikipedia.ed20a9e4726ea1c6.webp": { + "original_hash": "88212730ecd9b0c8b848c319951427d8", + "translation_date": "2026-01-16T07:09:57+00:00", + "source_file": "lessons/3-NeuralNetworks/images/synapse-wikipedia.jpg", + "language_code": "uk" + }, + "transformer-layer.905e14747ca4e7d5.webp": { + "original_hash": "dc9e2e401fa5e5c36a322b6721476ccd", + "translation_date": "2026-01-16T07:13:08+00:00", + "source_file": "lessons/5-NLP/18-Transformers/images/transformer-layer.png", + "language_code": "uk" + }, + "triplet-complex.32094972c7b4441b.webp": { + "original_hash": "56a2e05839a141c311db52655b37f8ad", + "translation_date": "2026-01-16T07:08:22+00:00", + "source_file": "lessons/2-Symbolic/images/triplet-complex.png", + "language_code": "uk" + }, + "triplet.4b9b332587593298.webp": { + "original_hash": "302e53ea355ffb556d99e3962d0a6516", + "translation_date": "2026-01-16T07:08:55+00:00", + "source_file": "lessons/2-Symbolic/images/triplet.png", + "language_code": "uk" + }, + "turing-test-evol.4184696701293ead.webp": { + "original_hash": "80d11b1074d61e5d6e4a207f72902e89", + "translation_date": "2026-01-16T07:07:00+00:00", + "source_file": "lessons/1-Intro/images/turing-test-evol.png", + "language_code": "uk" + }, + "unet.3adb555bf39d3657.webp": { + "original_hash": "49a151c11708ee9a3e94d21448146bf8", + "translation_date": "2026-01-16T07:01:40+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/images/unet.png", + "language_code": "uk" + }, + "unreasonable-effectiveness-of-rnn.541ead816778f42d.webp": { + "original_hash": "2a37bd4e9b12bcc19e045eaf22fea4e5", + "translation_date": "2026-01-16T07:13:44+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/images/unreasonable-effectiveness-of-rnn.jpg", + "language_code": "uk" + }, + "vae.464c465a5b6a9e25.webp": { + "original_hash": "0b658c7862077e139162c756bcb98071", + "translation_date": "2026-01-16T07:01:07+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vae.png", + "language_code": "uk" + }, + "vaemnist-diag.694315f775d5d666.webp": { + "original_hash": "0652f5a95005348c6b1533438103dfcf", + "translation_date": "2026-01-16T07:01:10+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist-diag.png", + "language_code": "uk" + }, + "vaemnist.cab9e602dc08dc50.webp": { + "original_hash": "8159b2f649e6dd8efa071455d6f222b6", + "translation_date": "2026-01-16T07:01:19+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/images/vaemnist.png", + "language_code": "uk" + }, + "vgg-16-arch.64ff2137f50dd49f.webp": { + "original_hash": "9fc348503d0ec03875e4b46f896f3aa9", + "translation_date": "2026-01-16T07:05:08+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch.jpg", + "language_code": "uk" + }, + "vgg-16-arch1.d901a5583b3a51ba.webp": { + "original_hash": "5b0f835d04dc20d097a0b89c88339966", + "translation_date": "2026-01-16T07:05:01+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/images/vgg-16-arch1.jpg", + "language_code": "uk" + }, + "vqgan.5027fe05051dfa31.webp": { + "original_hash": "845e5593c927fd3c3c125a90d0f8eb87", + "translation_date": "2026-01-16T07:11:19+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/images/vqgan.png", + "language_code": "uk" + }, + "yolo.a2648ec82ee8bb4e.webp": { + "original_hash": "e8835638234f5c21fcf36fdede6457f4", + "translation_date": "2026-01-16T07:04:04+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/images/yolo.png", + "language_code": "uk" } } \ No newline at end of file diff --git a/translated_images/unet.3adb555bf39d3657.et.png b/translated_images/unet.3adb555bf39d3657.et.png deleted file mode 100644 index 586b882a..00000000 Binary files a/translated_images/unet.3adb555bf39d3657.et.png and /dev/null differ diff --git a/translated_images/unet.3adb555bf39d3657.pcm.png b/translated_images/unet.3adb555bf39d3657.pcm.png deleted file mode 100644 index 60682c16..00000000 Binary files a/translated_images/unet.3adb555bf39d3657.pcm.png and /dev/null differ diff --git a/translated_images/unet.3adb555bf39d3657.te.png b/translated_images/unet.3adb555bf39d3657.te.png deleted file mode 100644 index 4494556b..00000000 Binary files a/translated_images/unet.3adb555bf39d3657.te.png and /dev/null differ diff --git a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.et.png b/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.et.png deleted file mode 100644 index 586b882a..00000000 Binary files a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.et.png and /dev/null differ diff --git a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.pcm.png b/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.pcm.png deleted file mode 100644 index 60682c16..00000000 Binary files a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.pcm.png and /dev/null differ diff --git a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.te.png b/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.te.png deleted file mode 100644 index 4494556b..00000000 Binary files a/translated_images/unet.3adb555bf39d3657bf535321c7ee153dbdd32895189e915e014229a9c79cf1e3.te.png and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.et.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.et.jpg deleted file mode 100644 index a302f0da..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.et.jpg and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.pcm.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.pcm.jpg deleted file mode 100644 index 4193fe23..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.pcm.jpg and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.te.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.te.jpg deleted file mode 100644 index dd4e51e1..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.te.jpg and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.et.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.et.jpg deleted file mode 100644 index a302f0da..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.et.jpg and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.pcm.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.pcm.jpg deleted file mode 100644 index 4193fe23..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.pcm.jpg and /dev/null differ diff --git a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.te.jpg b/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.te.jpg deleted file mode 100644 index dd4e51e1..00000000 Binary files a/translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42dce6c42d8a56c184729aa2378d059b851be4ce12b993033df.te.jpg and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e25.et.png b/translated_images/vae.464c465a5b6a9e25.et.png deleted file mode 100644 index 0e49c651..00000000 Binary files a/translated_images/vae.464c465a5b6a9e25.et.png and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e25.pcm.png b/translated_images/vae.464c465a5b6a9e25.pcm.png deleted file mode 100644 index 8782785b..00000000 Binary files a/translated_images/vae.464c465a5b6a9e25.pcm.png and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e25.te.png b/translated_images/vae.464c465a5b6a9e25.te.png deleted file mode 100644 index 940370f2..00000000 Binary files a/translated_images/vae.464c465a5b6a9e25.te.png and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.et.png b/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.et.png deleted file mode 100644 index 0e49c651..00000000 Binary files a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.et.png and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.pcm.png b/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.pcm.png deleted file mode 100644 index 8782785b..00000000 Binary files a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.pcm.png and /dev/null differ diff --git a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.te.png b/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.te.png deleted file mode 100644 index 940370f2..00000000 Binary files a/translated_images/vae.464c465a5b6a9e253be65a8cb3be1724832cbde57ece3912ddc962b199472a89.te.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666.et.png b/translated_images/vaemnist-diag.694315f775d5d666.et.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666.et.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666.pcm.png b/translated_images/vaemnist-diag.694315f775d5d666.pcm.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666.pcm.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666.te.png b/translated_images/vaemnist-diag.694315f775d5d666.te.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666.te.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.et.png b/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.et.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.et.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.pcm.png b/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.pcm.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.pcm.png and /dev/null differ diff --git a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.te.png b/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.te.png deleted file mode 100644 index 6d15b15b..00000000 Binary files a/translated_images/vaemnist-diag.694315f775d5d666b02fb54f8fc7c64db65a9d126a16c2fdb8683cf9726f9ff5.te.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc50.et.png b/translated_images/vaemnist.cab9e602dc08dc50.et.png deleted file mode 100644 index e7914d32..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc50.et.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc50.pcm.png b/translated_images/vaemnist.cab9e602dc08dc50.pcm.png deleted file mode 100644 index 8c3a3b87..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc50.pcm.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc50.te.png b/translated_images/vaemnist.cab9e602dc08dc50.te.png deleted file mode 100644 index 24f8c2cd..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc50.te.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.et.png b/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.et.png deleted file mode 100644 index e7914d32..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.et.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.pcm.png b/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.pcm.png deleted file mode 100644 index 8c3a3b87..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.pcm.png and /dev/null differ diff --git a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.te.png b/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.te.png deleted file mode 100644 index 24f8c2cd..00000000 Binary files a/translated_images/vaemnist.cab9e602dc08dc5066ce14e005889d6b53ca5bcaf16e35c28dbf8cd40c304de1.te.png and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49f.et.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49f.et.jpg deleted file mode 100644 index 36292c1b..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49f.et.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49f.pcm.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49f.pcm.jpg deleted file mode 100644 index 54bac781..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49f.pcm.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49f.te.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49f.te.jpg deleted file mode 100644 index ef3c8187..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49f.te.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.et.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.et.jpg deleted file mode 100644 index 36292c1b..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.et.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.pcm.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.pcm.jpg deleted file mode 100644 index 54bac781..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.pcm.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.te.jpg b/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.te.jpg deleted file mode 100644 index ef3c8187..00000000 Binary files a/translated_images/vgg-16-arch.64ff2137f50dd49fdaa786e3f3a975b3f22615efd13efb19c5d22f12e01451a1.te.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51ba.et.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51ba.et.jpg deleted file mode 100644 index 629b7d27..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51ba.et.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51ba.pcm.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51ba.pcm.jpg deleted file mode 100644 index b916cfd5..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51ba.pcm.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51ba.te.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51ba.te.jpg deleted file mode 100644 index 49f10c6e..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51ba.te.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.et.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.et.jpg deleted file mode 100644 index 629b7d27..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.et.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.pcm.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.pcm.jpg deleted file mode 100644 index b916cfd5..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.pcm.jpg and /dev/null differ diff --git a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.te.jpg b/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.te.jpg deleted file mode 100644 index 49f10c6e..00000000 Binary files a/translated_images/vgg-16-arch1.d901a5583b3a51baeaab3e768567d921e5d54befa46e1e642616c5458c934028.te.jpg and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa31.et.png b/translated_images/vqgan.5027fe05051dfa31.et.png deleted file mode 100644 index d2a06270..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa31.et.png and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa31.pcm.png b/translated_images/vqgan.5027fe05051dfa31.pcm.png deleted file mode 100644 index 020fa9ab..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa31.pcm.png and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa31.te.png b/translated_images/vqgan.5027fe05051dfa31.te.png deleted file mode 100644 index 9d1cf950..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa31.te.png and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.et.png b/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.et.png deleted file mode 100644 index d2a06270..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.et.png and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.pcm.png b/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.pcm.png deleted file mode 100644 index 020fa9ab..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.pcm.png and /dev/null differ diff --git a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.te.png b/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.te.png deleted file mode 100644 index 9d1cf950..00000000 Binary files a/translated_images/vqgan.5027fe05051dfa3101950cfa930303f66e6478b9bd273e83766731796e462d9b.te.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4e.et.png b/translated_images/yolo.a2648ec82ee8bb4e.et.png deleted file mode 100644 index 7b8ea91f..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4e.et.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4e.pcm.png b/translated_images/yolo.a2648ec82ee8bb4e.pcm.png deleted file mode 100644 index 8a1ea1a0..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4e.pcm.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4e.te.png b/translated_images/yolo.a2648ec82ee8bb4e.te.png deleted file mode 100644 index c5ba5a43..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4e.te.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.et.png b/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.et.png deleted file mode 100644 index 7b8ea91f..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.et.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.pcm.png b/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.pcm.png deleted file mode 100644 index 8a1ea1a0..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.pcm.png and /dev/null differ diff --git a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.te.png b/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.te.png deleted file mode 100644 index c5ba5a43..00000000 Binary files a/translated_images/yolo.a2648ec82ee8bb4ea27537677adb482fd4b733ca1705c561b6a24a85102dced5.te.png and /dev/null differ diff --git a/translations/et/README.md b/translations/et/README.md index b32da925..45cbb1f4 100644 --- a/translations/et/README.md +++ b/translations/et/README.md @@ -1,8 +1,8 @@ [Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](./README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) -> **Eelistad kloonimist kohapeal?** +> **Eelistad kloonimist lokaalselt?** -> See repositoorium sisaldab üle 50 keele tõlget, mis suurendab oluliselt allalaadimise mahtu. Kui soovid kloonida ilma tõlgeteta, kasuta sparse checkout'i: +> See hoidla sisaldab üle 50 keele tõlkeid, mis suurendab oluliselt allalaaditava faili suurust. Tõlgeteta kloonimiseks kasuta sparse checkout funktsiooni: > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git > cd AI-For-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > ``` -> See annab sulle kõik vajaliku kursuse läbimiseks palju kiiremalt. +> See annab sulle kõik vajaliku kursuse lõpetamiseks palju kiiremalt. -**Kui soovid lisada täiustavaid tõlkekeeli, siis need on loetletud [siin](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** +**Kui soovid, et toetataks täiendavaid tõlkekeeli, siis need on loetletud [siin](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** ## Liitu kogukonnaga [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -## Mida sa õpid +## Mida sa õpib **[Kursuse mõttekaart](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** Selles õppekavas õpid: -* Erinevaid lähenemisviise tehisintellektile, kaasa arvatud "hea vana" sümboolse lähenemise koos **teadmisrepresentatsiooni** ja peegelustestamisega ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* **Närvivõrgud** ja **sügavõpe**, mis on moodsa AI süda. Selgitame nende oluliste teemade kontseptsioone koodinäidete abil kahes populaarsemas raamistikus - [TensorFlow](http://Tensorflow.org) ja [PyTorch](http://pytorch.org). -* **Närviarhitektuurid** piltide ja tekstiga töötamiseks. Katame uusi mudeleid, kuid võib veidi puududa kõige tipptasemel lahendusest. -* Vähem levinud AI lähenemisi, nagu **geneetilised algoritmid** ja **mitmeagendisüsteemid**. +* Erinevaid tehisintellekti lähenemisi, sealhulgas "head vananenud" sümboolset lähenemist koos **Teadmiste representeerimise** ja loogikaga ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* **Närvivõrke** ja **Sügavat õpet**, mis on kaasaegse AI tuum. Selgitame nende oluliste teemade taga olevaid kontseptsioone koodinäidete abil kahes populaarsemas raamistikus - [TensorFlow](http://Tensorflow.org) ja [PyTorch](http://pytorch.org). +* **Närviarhitektuure** piltide ja teksti töötlemiseks. Käsitleme uuemaid mudeleid, kuid võib-olla mitte täiesti uusimaid. +* Vähem populaarsed AI lähenemised, nagu **Geneetilised algoritmid** ja **Mitmeagendilised süsteemid**. -Mida me selles õppekavas ei hõlma: +Mida me selles õppekavas ei käsitle: -> [Leia kõik selle kursuse lisamaterjalid meie Microsoft Learni kogust](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) +> [Leia kõik täiendavad selle kursuse ressursid meie Microsoft Learn'i kogumis](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* Ärilistel juhtudel kasutatavat **AI äris**. Soovitame läbida [Sissejuhatus AI kasutamisse ärikasutajatele](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) õpitee Microsoft Learnis või [AI äri kool](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), mida arendati koostöös [INSEAD](https://www.insead.edu/)iga. -* **Klassikalist masinõpet**, mis on hästi kirjeldatud meie [Masinõppe algajate õppekavas](http://github.com/Microsoft/ML-for-Beginners). -* Praktilisi AI rakendusi, mis on ehitatud kasutades **[Kognitiivseid teenuseid](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Selleks soovitame alustada Microsoft Learni moodulitest nägemise ([vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum)), loomuliku keele töötlemise ([natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum)), **[Generative AI koos Azure OpenAI teenusega](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ja teised. -* Spetsiifilisi ML **pilve raamistikud**, nagu [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum) või [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Soovitame kasutada [Ehita ja halda masinõppe lahendusi Azure Machine Learninguga](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ja [Ehita ja halda masinõppe lahendusi Azure Databricksiga](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) õppeteid. -* **Vestlusliku AI** ja **vestlusrobotite (chatbotide)** teemasid. Selleks on eraldi [Loo vestluslike AI lahenduste](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) õpitee ja võid samuti vaadata [seda blogipostitust](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) üksikasjade jaoks. -* **Sügavat matemaatikat** sügavõppe taga. Soovitame selleks [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) raamatut autoritelt Ian Goodfellow, Yoshua Bengio ja Aaron Courville, mis on saadaval ka veebis aadressil [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). +* Ärilised juhtumid **AI kasutamiseks äris**. Mõtle võtta [Sissejuhatus tehisintellekti jaoks ärikasutajatele](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) õppeteek Microsoft Learn'is või [AI ärikool](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), mis on välja töötatud koostöös [INSEAD](https://www.insead.edu/) organisatsiooniga. +* **Klassikaline masinõpe**, mis on põhjalikult kirjeldatud meie [Algajate masinõppe õppekavas](http://github.com/Microsoft/ML-for-Beginners). +* Praktilised tehisintellekti rakendused, mis on ehitatud kasutades **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Soovitame alustada Microsoft Learni moodulitest [nägemi](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [loomuliku keele töötlemise](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generatiivse AI-ga Azure OpenAI Teenuse kaudu](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ja teised. +* Spetsiifilised ML **pilverahastused**, nagu [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum) või [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Võiksid kaaluda [Masinõppe lahenduste loomist ja kasutamist Azure Machine Learninguga](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ja [Masinõppe lahenduste loomist ja kasutamist Azure Databricksuga](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) õppeteid. +* **Vestlev AI** ja **vestlusbotid**. Selleks on olemas eraldi [Loo vestlusAI lahendusi](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) õppeteek ning saad lisaks vaadata [seda blogipostitust](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) detailsemalt. +* **Sügav matemaatika** sügava õppe taga. Selleks soovitame [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) raamatut autoritelt Ian Goodfellow, Yoshua Bengio ja Aaron Courville, mis on ka saadaval veebis aadressil [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -Lõdvestunud sissejuhatuse saamiseks _AI pilves_ teemades võid kaaluda [Alustamist tehisintellektiga Azure’is](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) õpiplaani. +Õrnema sissejuhatuse saamiseks _pilvetehisintellekti_ teemadesse võid kaaluda [Alustamist tehisintellektiga Azure'is](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) õppeteed. # Sisu -| | Õppetunni link | PyTorch/Keras/TensorFlow | Labor | +| | õppetunni link | PyTorch/Keras/TensorFlow | Labor | | :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | -| 0 | [Kursuse seadistamine](./lessons/0-course-setup/setup.md) | [Seadista oma arenduskeskkond](./lessons/0-course-setup/how-to-run.md) | | -| I | [**Sissejuhatus tehisintellekti**](./lessons/1-Intro/README.md) | | | -| 01 | [Sissejuhatus ja tehisintellekti ajalugu](./lessons/1-Intro/README.md) | - | - | +| 0 | [Kursuse seadistus](./lessons/0-course-setup/setup.md) | [Arenduskeskkonna seadistamine](./lessons/0-course-setup/how-to-run.md) | | +| I | [**Sissejuhatus AI-sse**](./lessons/1-Intro/README.md) | | | +| 01 | [AI sissejuhatus ja ajalugu](./lessons/1-Intro/README.md) | - | - | | II | **Sümboolne AI** | -| 02 | [Teadmisrepresentatsioon ja ekspertsüsteemid](./lessons/2-Symbolic/README.md) | [Ekspertsüsteemid](./lessons/2-Symbolic/Animals.ipynb) / [Ontoloogia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Kontseptsioonigraaf](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | +| 02 | [Teadmiste representeerimine ja ekspertsüsteemid](./lessons/2-Symbolic/README.md) | [Ekspertsüsteemid](./lessons/2-Symbolic/Animals.ipynb) / [Ontoloogia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Kontseptsioonigraafik](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | | III | [**Sissejuhatus närvivõrkudesse**](./lessons/3-NeuralNetworks/README.md) ||| | 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notebook](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Lab](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | -| 04 | [Mitmekihiline perceptron ja oma raamistu loomine](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | -| 05 | [Raamistike sissejuhatus (PyTorch/TensorFlow) ja üleõppimine](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | -| IV | [**Arvutinägemine**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Avasta arvutinägemine Microsoft Azure'is](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | -| 06 | [Sissejuhatus arvutinägemisesse. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | +| 04 | [Mitmekihiline percetron ja oma raamistik](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | +| 05 | [Sissejuhatus raamistikesse (PyTorch/TensorFlow) ja üleõppimine](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | +| IV | [**Arvutinägemine**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Uuri arvutinägemist Microsoft Azure'is](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | +| 06 | [Sissejuhatus arvutinägemisse. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | | 07 | [Konvolutsioonilised närvivõrgud](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN arhitektuurid](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) | -| 08 | [Eeltreenitud võrgud ja teadmiste ülekandmine](./lessons/4-ComputerVision/08-TransferLearning/README.md) ja [Treeningu trikid](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | -| 09 | [Autokodeerijad ja VAEd](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | | -| 10 | [Generatiivsed vastanduvad võrgud ja kunstilise stiili ülekandmine](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | -| 11 | [Objekti tuvastamine](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | +| 08 | [Eeltreenitud võrgud ja teadmiste ülekandmine](./lessons/4-ComputerVision/08-TransferLearning/README.md) ja [Treeningtrikid](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | +| 09 | [Automaatkodeerijad ja VAE-d](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | | +| 10 | [Generatiivsed vastanduvad võrgud & Kunstilise stiili ülekandmine](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | +| 11 | [Objektituvastus](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | | 12 | [Semantiline segmentimine. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | | -| V | [**Loodusliku keele töötlemine**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Avasta loodusliku keele töötlemine Microsoft Azure'is](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| -| 13 | [Teksti esitus. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | | -| 14 | [Semantilised sõna sisestused. Word2Vec ja GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | | -| 15 | [Keelemudel. Oma sisestuste treenimine](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | +| V | [**Loodusliku keele töötlemine**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Uuri loodusliku keele töötlemist Microsoft Azure'is](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| +| 13 | [Teksti representatsioon. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | | +| 14 | [Semantilised sõna manused. Word2Vec ja GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | | +| 15 | [Keelemudelid. Oma manuste treenimine](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | | 16 | [Korduvad närvivõrgud](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | | | 17 | [Generatiivsed korduvad võrgud](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) | | 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | | -| 19 | [Nimedatud üksuste tuvastamine](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) | -| 20 | [Suured keelemudelid, promptide programmeerimine ja vähese kogusega ülesanded](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | -| VI | **Muud tehisintellekti tehnoloogiad** || | +| 19 | [Nimetatud üksuste tuvastamine](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) | +| 20 | [Suuured keelemudelid, promptide programmeerimine ja vähese andmestikuga ülesanded](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | +| VI | **Muud tehisintellekti tehnikad** || | | 21 | [Geneetilised algoritmid](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | -| 22 | [Sügav tugevdamisõpe](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) | -| 23 | [Mitmeagendi süsteemid](./lessons/6-Other/23-MultiagentSystems/README.md) | | | -| VII | **AI eetika** | | | -| 24 | [AI eetika ja vastutustundlik AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Vastutustundliku AI põhimõtted](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | -| IX | **Lisaressursid** | | | -| 25 | [Mitmemodaalsed võrgud, CLIP ja VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | +| 22 | [Sügav tugevdatud õpe](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) | +| 23 | [Mitmeagendilised süsteemid](./lessons/6-Other/23-MultiagentSystems/README.md) | | | +| VII | **Tehisintellekti eetika** | | | +| 24 | [Eetika ja vastutustundlik tehisintellekt](./lessons/7-Ethics/README.md) | [Microsoft Learn: Vastutustundliku tehisintellekti põhimõtted](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | +| IX | **Lisad** | | | +| 25 | [Mitme-modaliga võrgud, CLIP ja VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | ## Iga õppetund sisaldab -* Eelnevat lugemismaterjali -* Täidetavaid Jupyteri märkmikke, mis on sageli seotud konkreetse raamistikuga (**PyTorch** või **TensorFlow**). Täidetav märkmik sisaldab ka palju teoreetilist materjali, seega teema mõistmiseks tuleb läbida vähemalt üks märkmiku versioon (kas PyTorch või TensorFlow). -* Mõne teema jaoks on saadaval **laborid**, mis annavad võimaluse proovida õpitud materjali rakendamist konkreetsele probleemile. -* Mõned sektsioonid sisaldavad linke [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moodulitele, mis käsitlevad seotud teemasid. +* Eelnev lugemismaterjal +* Käivitatavad Jupyteri märkmikud, mis on tihti spetsiifilised raamistikule (**PyTorch** või **TensorFlow**). Käivitatav märkmik sisaldab ka palju teoreetilist materjali, nii et teema mõistmiseks tuleb läbi töötada vähemalt üks märkmiku versioon (kas PyTorch või TensorFlow). +* Mõne teema jaoks on saadaval **Laborid**, mis annavad sulle võimaluse proovida õpitut rakendada konkreetsele probleemile. +* Mõned osad sisaldavad linke [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moodulitesse, mis käsitlevad seotud teemasid. -## Alustamiseks +## Alustamine -### 🎯 Oled AI's uus? Alusta siit! +### 🎯 Oled tehisintellektiga uus? Alusta siit! -Kui oled täiesti uus tehisintellekti valdkonnas ja soovid kiirelt praktilisi näiteid, vaata meie [**algajatele sõbralikke näiteid**](./examples/README.md)! Need sisaldavad: +Kui oled tehisintellektiga täiesti uus ja soovid kiireid, praktilisi näiteid, vaata meie [**Algajatele mõeldud näited**](./examples/README.md)! Need sisaldavad: -- 🌟 **Tere tulemast AI maailma** - Sinu esimene AI programm (mustrituvastus) +- 🌟 **Tere tulemast, AI maailm** - Sinu esimene tehisintellekti programm (mustriloendus) - 🧠 **Lihtne närvivõrk** - Ehita närvivõrk nullist -- 🖼️ **Pildiklassifikaator** - Klassifitseeri pilte üksikasjalike kommentaaridega -- 💬 **Teksti sentiment** - Analüüsi positiivset/negatiivset teksti +- 🖼️ **Pildiklassifikaator** - Klassifitseeri pilte põhjalike kommentaaridega +- 💬 **Teksti sentiment** - Anadüüsi positiivset/negatiivset teksti -Need näited on loodud selleks, et aidata sul mõista tehisintellekti kontseptsioone enne kogu õppekavasse sukeldumist. +Need näited on loodud selleks, et aidata teil mõista tehisintellekti kontseptsioone enne täielikku õppekava läbimist. ### 📚 Täieliku õppekava seadistamine -- Oleme loonud [seadistustunni](./lessons/0-course-setup/setup.md), mis aitab sind arenduskeskkonna seadistamisel. - Õpetajate jaoks oleme loonud ka [õppekava seadistustunni](./lessons/0-course-setup/for-teachers.md)! -- Kuidas [käivitada koodi VSCode'is või Codepace’is](./lessons/0-course-setup/how-to-run.md) +- Oleme loonud [seadistuse tunni](./lessons/0-course-setup/setup.md), et aidata teil arenduskeskkonda seadistada. - Õpetajatele oleme loonud ka [õppekava seadistuse tunni](./lessons/0-course-setup/for-teachers.md)! +- Kuidas [koodi käivitada VSCode’is või Codespaces](./lessons/0-course-setup/how-to-run.md) -Järgi neid samme: +Järgige neid samme: -Forka reposiit: Klõpsa selle lehe paremas ülanurgas nuppu "Fork". +Varu repository: Klõpsake selle lehe paremas ülanurgas nuppu "Fork". -Kopeeri reposiit: `git clone https://github.com/microsoft/AI-For-Beginners.git` +Klooni repository: `git clone https://github.com/microsoft/AI-For-Beginners.git` -Ära unusta sellele repo'le tähtpäikest (🌟) panna, et seda hiljem lihtsam leida. +Ärge unustage sellele reposiidile tärni (🌟) panna, et hiljem seda lihtsam üles leida. -## Kohtu teiste õppijatega +## Tutvuge teiste õppijatega -Liitu meie [ametliku AI Discordi serveriga](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum), et kohtuda ja suhelda teiste selle kursuse läbijatega ning saada tuge. +Liituge meie [ametliku AI Discordi serveriga](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum), et kohtuda ja suhelda teiste selle kursuse õppijatega ning saada tuge. -Kui sul on toote tagasisidet või küsimusi, külastage meie [Azure AI Foundry arendajate foorumit](https://aka.ms/foundry/forum). +Kui teil on toote tagasisidet või küsimusi ehitamise ajal, külastage meie [Azure AI Foundry arendajate foorumit](https://aka.ms/foundry/forum) -## Viktoriinid +## Testid -> **Märkus viktoriinide kohta**: Kõik viktoriinid asuvad Quiz-app kaustas teekonnas etc\quiz-app või [võrgus siin](https://ff-quizzes.netlify.app/). Need on lingitud tundidest, viktoriini rakendust saab käivitada lokaalselt või paigaldada Azure’i; järgi juhiseid `quiz-app` kaustas. Neid lokaliseeritakse järk-järgult. +> **Märkus testide kohta**: Kõik testid asuvad kaustas Quiz-app teekonnal etc\quiz-app või [Veebi kaudu siin](https://ff-quizzes.netlify.app/) Need on lingitud õppetundide sees; testi rakendust saab käivitada lokaalselt või paigaldada Azure’i; järgige juhiseid `quiz-app` kaustas. Neid kohandatakse järk-järgult erinevatele keeleversioonidele. ## Otsime abi -Kas sul on ettepanekuid või oled leidnud trüki- või koodivigu? Ava probleem või loo pull request. +Kas teil on ettepanekuid või olete leidnud õigekirja- või koodivigu? Tõstke esile probleem või looge tõmbepäring. -## Erilised tänud +## Eriti suur tänu -* **✍️ Peamiseks autoriks:** [Dmitry Soshnikov](http://soshnikov.com), PhD +* **✍️ Peaautor:** [Dmitry Soshnikov](http://soshnikov.com), PhD * **🔥 Toimetaja:** [Jen Looper](https://twitter.com/jenlooper), PhD -* **🎨 Sketchnote illustraator:** [Tomomi Imura](https://twitter.com/girlie_mac) -* **✅ Viktoriini looja:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) -* **🙏 Põhisisendajad:** [Evgenii Pishchik](https://github.com/Pe4enIks) +* **🎨 Sketšinote illustraator:** [Tomomi Imura](https://twitter.com/girlie_mac) +* **✅ Testide autor:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) +* **🙏 Põhikontribuudid:** [Evgenii Pishchik](https://github.com/Pe4enIks) -## Teised õppekavad +## Muud õppekavad -Meie meeskond toodab ka teisi õppekavasid! Tutvu: +Meie meeskond toodab ka teisi õppekavu! Vaadake: ### LangChain -[![LangChain4j for Beginners](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js for Beginners](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain4j algajatele](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![LangChain.js algajatele](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- ### Azure / Edge / MCP / Agentid -[![AZD for Beginners](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Edge AI for Beginners](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![MCP for Beginners](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents for Beginners](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AZD algajatele](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Edge AI algajatele](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![MCP algajatele](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI agentid algajatele](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- - -### Generatiivse AI sari -[![Generative AI for Beginners](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) + +### Generatiivne tehisintellekt seeria +[![Generatiivne AI algajatele](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Generatiivne AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![Generatiivne AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![Generatiivne AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- - -### Tuumikõpe -[![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) + +### Põhijõudude õppimine +[![Masinõpe algajatele](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Andmeteadus algajatele](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![AI algajatele](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Küberjulgeolek algajatele](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Veebiarendus algajatele](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT algajatele](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![XR arendus algajatele](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- - -### Copiloti sari -[![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) + +### Copilot seeria +[![Copilot AI paar-programmeerimiseks](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot C#/.NET jaoks](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![Copilot seiklus](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Abi saamine -Kui sa takerdud või sul on küsimusi AI rakenduste loomise kohta. Liitu teiste õppijate ja kogenud arendajatega MCP teemalistes aruteludes. See on toetav kogukond, kus küsimused on teretulnud ja teadmisi jagatakse vabalt. +Kui teil jääb midagi arusaamatuks või teil on AI rakenduste loomise kohta küsimusi, liituge teiste õppijate ja kogenud arendajatega MCP teemal aruteludes. See on toetav kogukond, kus küsimusi julgesti esitada ja teadmisi vabalt jagada. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Kui sul on toote tagasisidet või esineb vigu ehitamise ajal, külasta: +Kui teil on kestvatoote tagasisidet või veateateid, külastage: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**Eksitustekst**: -See dokument on tõlgitud AI tõlketeenuse [Co-op Translator](https://github.com/Azure/co-op-translator) abil. Kuigi me püüame täpsust, palun arvestage, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Originaaldokument oma emakeeles tuleks käsitleda autoriteetse allikana. Olulise teabe puhul soovitatakse professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste või valesti mõistmiste eest. +**Vastutusest loobumine**: +See dokument on tõlgitud kasutades tehisintellektil põhinevat tõlketeenust [Co-op Translator](https://github.com/Azure/co-op-translator). Kuigi püüame täpsust, olge teadlikud, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Originaaldokument oma emakeeles tuleb pidada autoriteetseks allikaks. Olulise teabe puhul soovitatakse kasutada professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste või valesti mõistmiste eest. \ No newline at end of file diff --git a/translations/et/lessons/0-course-setup/how-to-run.md b/translations/et/lessons/0-course-setup/how-to-run.md index be6ac35a..2e763815 100644 --- a/translations/et/lessons/0-course-setup/how-to-run.md +++ b/translations/et/lessons/0-course-setup/how-to-run.md @@ -1,21 +1,21 @@ -# Koodi käivitamine +# Kuidas Koodi Käivitada -See õppekava sisaldab palju käivitatavaid näiteid ja laboreid, mida soovite proovida. Selleks on teil vaja võimalust käivitada Python-koodi Jupyter Notebookides, mis on osa sellest õppekavast. Koodi käivitamiseks on mitu võimalust: +See õppekava sisaldab palju täidetavaid näiteid ja töötoad, mida soovite jooksutada. Selleks peate saama käivitada Python koodi Jupyter märkmikes, mis on selle õppekava osana esitatud. Koodi käivitamiseks on teil mitu võimalust: -## Käivita kohalikult oma arvutis +## Käivita lokaalselt oma arvutis -Koodi kohalikuks käivitamiseks oma arvutis peate olema installinud mõne Python'i versiooni. Soovitan isiklikult installida **[miniconda](https://conda.io/en/latest/miniconda.html)** - see on kerge paigaldus, mis toetab `conda` paketihaldurit erinevate Python'i **virtuaalsete keskkondade** jaoks. +Koodi käivitamiseks lokaalselt oma arvutis on vajalik Python'i paigaldus. Üks soovitus on installida **[miniconda](https://conda.io/en/latest/miniconda.html)** – see on üsna kerge paigaldus, mis toetab `conda` pakihaldurit erinevate Python'i **virtuaalsete keskkondade** jaoks. -Pärast miniconda installimist peate kloonima repositooriumi ja looma virtuaalse keskkonna, mida kasutatakse selle kursuse jaoks: +Pärast miniconda paigaldamist kloonige hoidla ja looge selle kursuse jaoks virtuaalne keskkond: ```bash git clone http://github.com/microsoft/ai-for-beginners @@ -24,55 +24,58 @@ conda env create --name ai4beg --file .devcontainer/environment.yml conda activate ai4beg ``` -### Visual Studio Code'i kasutamine koos Python'i laiendusega +### Kasutades Visual Studio Code koos Python laiendiga -Tõenäoliselt on parim viis õppekava kasutamiseks avada see [Visual Studio Code'is](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) koos [Python'i laiendusega](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste). +Seda õppekava on kõige parem kasutada, kui avate selle [Visual Studio Code’is](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) koos [Python laiendiga](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste). -> **Märkus**: Kui kloonite ja avate kataloogi VS Code'is, soovitab see automaatselt Python'i laienduste installimist. Samuti peate installima miniconda, nagu eespool kirjeldatud. +> **Märkus**: Kui kloonite ja avate kausta VS Code’is, soovitab see automaatselt paigaldada Python laiendused. Samuti peate paigaldama miniconda nagu eespool kirjeldatud. -> **Märkus**: Kui VS Code soovitab teil repositooriumi konteineris uuesti avada, peate selle tagasi lükkama, et kasutada kohalikku Python'i installatsiooni. +> **Märkus**: Kui VS Code soovitab teil hoidlale konteineris uuesti ligi pääseda, peaksite selle keelduma, et kasutada lokaalset Python'i paigaldust. -### Jupyter'i kasutamine brauseris +### Kasutades Jupyterit brauseris -Samuti saate kasutada Jupyter'i keskkonda otse brauseris oma arvutis. Tegelikult pakuvad nii klassikaline Jupyter kui ka Jupyter Hub üsna mugavat arenduskeskkonda automaatse täiendamise, koodi esiletõstmise jms funktsioonidega. +Võite kasutada ka Jupyter keskkonda brauserist oma arvutis. Nii klassikaline Jupyter kui ka JupyterHub pakuvad mugavat arenduskeskkonda automaatse täienduse, koodi esiletõstmise jms funktsioonidega. -Jupyter'i kohalikuks käivitamiseks minge kursuse kataloogi ja käivitage: +Jupyterit käivitamiseks lokaalselt minge kursuse kataloogi ning käivitage: ```bash jupyter notebook ``` -või + või ```bash jupyterhub ``` -Seejärel saate liikuda mis tahes `.ipynb` failini, avada selle ja alustada tööd. + +Seejärel saate minna mis tahes `.ipynb` faili juurde, avada selle ja alustada tööd. ### Käivitamine konteineris -Alternatiiv Python'i installatsioonile oleks koodi käivitamine konteineris. Kuna meie repositoorium sisaldab spetsiaalset `.devcontainer` kausta, mis juhendab, kuidas selle repositooriumi jaoks konteinerit ehitada, pakub VS Code teile võimalust avada kood konteineris. See nõuab Docker'i installimist ja on ka keerulisem, seega soovitame seda kogenumatele kasutajatele. +Üks alternatiiv Python'i paigaldamisele on koodi käivitamine konteineris. Kuna meie hoidla sisaldab spetsiaalset `.devcontainer` kausta, mis juhendab konteineri ehitamist selle hoidlaga, pakub VS Code võimalust hoidlale konteineris uuesti ligi pääseda. Selleks on vajalik Docker’i installatsioon ja see on ka keerulisem, seega soovitame seda rohkem kogenud kasutajatele. ## Käivitamine pilves -Kui te ei soovi Python'i kohalikult installida ja teil on juurdepääs mõnele pilveressursile, siis hea alternatiiv oleks koodi käivitamine pilves. Selleks on mitu võimalust: +Kui te ei soovi Pythonit lokaalselt paigaldada, kuid teil on ligipääs mõnele pilveteenusele, on hea alternatiiv koodi käivitamine pilvest. Seda saab teha mitmel viisil: -* Kasutades **[GitHub Codespaces](https://github.com/features/codespaces)**, mis on GitHub'is loodud virtuaalne keskkond, millele pääseb ligi VS Code'i brauseriliidese kaudu. Kui teil on juurdepääs Codespaces'ile, saate lihtsalt klõpsata repositooriumis **Code** nupul, käivitada Codespace'i ja alustada tööd hetkega. -* Kasutades **[Binder](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)**. [Binder](https://mybinder.org) pakub tasuta pilvearvutusressursse, et testida GitHub'is olevat koodi. Esilehel on nupp, mis avab repositooriumi Binder'is - see viib teid kiiresti Binder'i saidile, mis ehitab aluseks oleva konteineri ja käivitab Jupyter'i veebiliidese sujuvalt. +* Kasutades **[GitHub Codespaces](https://github.com/features/codespaces)**, mis on teile GitHubis loodav virtuaalne keskkond, mida pääseb ligi VS Code’i brauseri kaudu. Kui teil on Codespaces’i ligipääs, saate lihtsalt hoidla lehel vajutada nuppu **Code**, alustada codespace’i ning hakata kohe koodi jooksutama. +* Kasutades **[Binderit](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)**. [Binder](https://mybinder.org) pakub tasuta arvutusressursse pilves, mis võimaldab teil GitHubi koodi mugavalt testida. Esilehel on nupp, mis avab hoidla Binderis – see viib teid rapidamente Binderi lehele, mis ehitab taustal konteineri ja käivitab teie jaoks sujuvalt Jupyter veebiliidese. -> **Märkus**: Kuritarvituste vältimiseks on Binder'il juurdepääs mõnele veebiresursile blokeeritud. See võib takistada mõne koodi töötamist, mis laadib mudeleid ja/või andmekogumeid avalikust internetist. Võimalik, et peate leidma mõningaid lahendusi. Samuti on Binder'i pakutavad arvutusressursid üsna piiratud, mistõttu treenimine on aeglane, eriti hilisemates keerukamates tundides. +> **Märkus**: Kuritarvituste vältimiseks on Binderi ligipääs mõnele veebiallikale piiratud. See võib takistada mõnel koodil toimimast, mis alla laadib mudeleid ja/või andmestasid avalikust internetist. Võite vajada mõnda lahendust nende piirangute vältimiseks. Samuti on Binderi pakutavad arvutusressursid üsna piiratud, mistõttu treeningud võivad olla aeglased, eriti hilisemates keerulisemates õppetundides. -## Käivitamine pilves GPU-ga +## Käivitamine pilves koos GPU-toega -Mõned hilisemad õppetunnid selles õppekavas oleksid GPU toe korral palju tõhusamad, sest muidu on treenimine väga aeglane. Siin on mõned võimalused, mida saate kasutada, eriti kui teil on juurdepääs pilvele kas [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste) kaudu või oma asutuse kaudu: +Mõned õppetunnid selles õppekavas kasutaksid oluliselt GPU-d, mis muudab mudelite treenimise palju kiiremaks. GPU toe olemasolu on eriti kasulik. Mõned võimalused: -* Looge [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) ja ühendage sellega Jupyter'i kaudu. Seejärel saate repositooriumi otse masinasse kloonida ja õppimist alustada. NC-seeria virtuaalmasinatel on GPU tugi. +* Loo [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) ja ühenda sellega Jupyteri kaudu. Saate kloonida hoidla otse masinale ning alustada õppimist. NC-seeria VM-id toetavad GPU-d. -> **Märkus**: Mõned tellimused, sealhulgas Azure for Students, ei paku GPU tuge vaikimisi. Võimalik, et peate tehnilise toe kaudu taotlema täiendavaid GPU tuumasid. +> **Märkus**: Mõned tellimused, sh Azure for Students, ei paku vaikimisi GPU tuge. Võib-olla peate esitama tehnilise toe taotluse täiendavate GPU tuumade saamiseks. -* Looge [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) ja kasutage seal Notebook'i funktsiooni. [See video](https://azure-for-academics.github.io/quickstart/azureml-papers/) näitab, kuidas kloonida repositoorium Azure ML Notebook'i ja seda kasutama hakata. +* Loo [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) ja kasuta seal Jupyter märkmiku funktsiooni. [See video](https://azure-for-academics.github.io/quickstart/azureml-papers/) näitab, kuidas kloonida hoidla Azure ML märkmikku ja seda kasutada. -Samuti saate kasutada Google Colab'i, mis pakub mõningast tasuta GPU tuge, ja laadida sinna Jupyter Notebook'e, et neid ükshaaval käivitada. +Võite kasutada ka Google Colabit, mis pakub mõningast tasuta GPU tuge, ning üles laadida sinna Jupyteri märkmikud, mida sealt ükshaaval käivitada. --- -**Lahtiütlus**: -See dokument on tõlgitud AI tõlketeenuse [Co-op Translator](https://github.com/Azure/co-op-translator) abil. Kuigi püüame tagada täpsust, palume arvestada, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Algne dokument selle algses keeles tuleks pidada autoriteetseks allikaks. Olulise teabe puhul soovitame kasutada professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste või valesti tõlgenduste eest. \ No newline at end of file + +**Vastutusest loobumine**: +See dokument on tõlgitud kasutades AI tõlke teenust [Co-op Translator](https://github.com/Azure/co-op-translator). Kuigi püüame tagada täpsust, palun arvestage, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Algne dokument selle emakeeles tuleks pidada autoriteetseks allikaks. Olulise info puhul soovitatakse kasutada professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste ega valesti mõistmiste eest. + \ No newline at end of file diff --git a/translations/et/lessons/2-Symbolic/Animals.ipynb b/translations/et/lessons/2-Symbolic/Animals.ipynb index 0df546e6..57df3cf4 100644 --- a/translations/et/lessons/2-Symbolic/Animals.ipynb +++ b/translations/et/lessons/2-Symbolic/Animals.ipynb @@ -6,25 +6,25 @@ "collapsed": true }, "source": [ - "# Loomade ekspertsüsteemi rakendamine\n", + "# Loomaeksperdisüsteemi rakendamine\n", "\n", - "Näide [AI algajatele õppekavast](http://github.com/microsoft/ai-for-beginners).\n", + "Näide [AI for Beginners Curriculum](http://github.com/microsoft/ai-for-beginners).\n", "\n", - "Selles näites rakendame lihtsat teadmistepõhist süsteemi, et määrata loom füüsiliste omaduste põhjal. Süsteemi saab kujutada järgmise JA-VÕI puuna (see on osa kogu puust, reegleid saab hõlpsasti juurde lisada):\n", + "Selles näites rakendame lihtsat teadmistepõhist süsteemi, et tuvastada loom mõnede füüsikaliste omaduste põhjal. Süsteemi saab esitada järgmise JA-VÕI-puuna (see on osa kogu puust, me võime hõlpsasti lisada veel reegleid):\n", "\n", - "![](../../../../translated_images/et/AND-OR-Tree.5592d2c70187f283.webp)\n" + "![](../../../../../../translated_images/et/AND-OR-Tree.5592d2c70187f283.webp)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## Meie enda ekspertide süsteemi kest tagasipööratud järeldusega\n", + "## Meie oma eksperdisüsteemide kest tagurpidi järeldusega\n", "\n", - "Proovime defineerida lihtsa keele teadmiste esitamiseks tootmisreeglite põhjal. Kasutame Python'i klasse märksõnadena reeglite määratlemiseks. Põhimõtteliselt oleks kolm tüüpi klasse:\n", + "Proovime defineerida lihtsat teadmiste esindamise keelt, mis põhineb tootmisreeglitel. Kasutame reeglite määratlemiseks märksõnadena Python'i klasse. Tegelikkuses on kolm klassi tüüpi:\n", "* `Ask` esindab küsimust, mida tuleb kasutajalt küsida. See sisaldab võimalike vastuste komplekti.\n", - "* `If` esindab reeglit ja on lihtsalt süntaktiline mugavus reegli sisu salvestamiseks.\n", - "* `AND`/`OR` on klassid, mis esindavad AND/OR harusid puus. Need lihtsalt salvestavad argumentide loendi. Koodi lihtsustamiseks on kogu funktsionaalsus määratletud vanemklassis `Content`.\n" + "* `If` esindab reeglit ja on lihtsalt sünteetiline mugavus reegli sisu salvestamiseks\n", + "* `AND`/`OR` on klassid, mis esindavad puu JA/VOI harusid. Need salvestavad lihtsalt sisemuses argumentide nimekirja. Koodi lihtsustamiseks on kogu funktsionaalsus defineeritud vanemklassina `Content`\n" ] }, { @@ -66,7 +66,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Meie süsteemis sisaldab töömälu **faktide** loendit kui **atribuut-väärtus paare**. Teadmistebaasi saab defineerida kui suurt sõnastikku, mis seostab tegevusi (uued faktid, mis tuleks töömällu lisada) tingimustega, väljendatuna JA-VÕI avaldistena. Lisaks saab mõningaid fakte `Küsida`.\n" + "Meie süsteemis sisaldaks töömälus nimekirja **faktidest** kui **atribuudi-väärtuse paaridest**. Teadmusbaas võib olla defineeritud kui üks suur sõnastik, mis seostab tegevused (uued faktid, mis tuleks lisada töömällu) tingimustega, väljendatuna JA-VÕI avaldistena. Samuti võib mõned fakti `Küsimuse` alla panna.\n" ] }, { @@ -99,13 +99,13 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Tagasipööratud järelduse tegemiseks defineerime `Knowledgebase` klassi. See sisaldab:\n", - "* Töötavat `memory` - sõnastikku, mis seob atribuute väärtustega\n", - "* Teadmistebaasi `rules` reegleid eelnevalt määratletud formaadis\n", + "Tagurpidi järelduse tegemiseks määratleme klassi `Knowledgebase`. See sisaldab:\n", + "* Töömälu `memory` — sõnastik, mis seob atribuute väärtustega\n", + "* Teadmistebaasi reeglid `rules` eelpool määratletud vormingus\n", "\n", "Kaks peamist meetodit on:\n", - "* `get`, et saada atribuudi väärtus, tehes vajadusel järeldusi. Näiteks `get('color')` hangib värvi atribuudi väärtuse (küsib vajadusel ja salvestab väärtuse hilisemaks kasutamiseks töötavasse mällu). Kui küsime `get('color:blue')`, siis küsitakse värvi ja tagastatakse `y`/`n` väärtus sõltuvalt värvist.\n", - "* `eval` teostab tegeliku järelduse, st läbib AND/OR puu, hindab alam-eesmärke jne.\n" + "* `get`, mis tagastab atribuudi väärtuse, vajadusel tehes järeldusi. Näiteks `get('color')` tagastab värvi atribuudi väärtuse (küsib vajadusel ja salvestab väärtuse hilisemaks kasutamiseks töömällu). Kui küsime `get('color:blue')`, siis küsitakse värvi ja tagastatakse vastus `y`/`n` sõltuvalt värvist.\n", + "* `eval` teostab tegelikku järeldamist, s.t läbib JA/VOI puu, hindab alam-eesmärke jne.\n" ] }, { @@ -172,7 +172,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Nüüd määratleme oma loomade teadmistebaasi ja teostame konsultatsiooni. Pange tähele, et see päring esitab teile küsimusi. Saate vastata, sisestades `y`/`n` jah-ei küsimuste puhul või määrates numbri (0..N) pikemate valikvastustega küsimuste puhul.\n" + "Nüüd defineerime oma loomade teadmistebaasi ja teostame konsultatsiooni. Pange tähele, et see kõne esitab teile küsimusi. Võite vastata tippides `y`/`n` jah-ei küsimustele või määrates numbri (0..N) küsimustele, millel on pikemad mitmikvastuse valikud.\n" ] }, { @@ -229,11 +229,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## PyKnow kasutamine edasise järeldamise jaoks\n", + "## Eksperta kasutamine edasisuunalise tuletamise jaoks\n", "\n", - "Järgmises näites proovime rakendada edasist järeldamist, kasutades ühte teadmiste esitamise raamatukogudest, [PyKnow](https://github.com/buguroo/pyknow/). **PyKnow** on raamatukogu edasise järeldamise süsteemide loomiseks Pythonis, mis on loodud sarnanema klassikalise vana süsteemiga [CLIPS](http://www.clipsrules.net/index.html).\n", + "Järgmises näites proovime rakendada edasisuunalist tuletamist kasutades üht teadmiste esitamise teekidest, [Experta](https://github.com/nilp0inter/experta). **Experta** on teek edasisuunaliste tuletamissüsteemide loomiseks Pythonis, mis on loodud klassikalise vana süsteemi [CLIPS](http://www.clipsrules.net/index.html) sarnaseks.\n", "\n", - "Me oleksime võinud ka ise edasist järeldamist rakendada ilma suuremate probleemideta, kuid lihtsad rakendused ei ole tavaliselt väga tõhusad. Tõhusamaks reeglite sobitamiseks kasutatakse spetsiaalset algoritmi [Rete](https://en.wikipedia.org/wiki/Rete_algorithm).\n" + "Me oleksime võinud forward chaining moodustada ka ise ilma suuremate probleemideta, kuid lihtsad implementeeringud ei ole tavaliselt eriti tõhusad. Reeglite efektiivsemaks sobitamiseks kasutatakse spetsiaalset algoritmi [Rete](https://en.wikipedia.org/wiki/Rete_algorithm).\n" ] }, { @@ -247,32 +247,31 @@ "name": "stdout", "output_type": "stream", "text": [ - "Collecting git+https://github.com/buguroo/pyknow/\n", - " Cloning https://github.com/buguroo/pyknow/ to /tmp/pip-req-build-3cqeulyl\n", - " Running command git clone --filter=blob:none --quiet https://github.com/buguroo/pyknow/ /tmp/pip-req-build-3cqeulyl\n", - " Resolved https://github.com/buguroo/pyknow/ to commit 48818336f2e9a126f1964f2d8dc22d37ff800fe8\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting frozendict==1.2\n", - " Using cached frozendict-1.2.tar.gz (2.6 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting schema==0.6.7\n", - " Using cached schema-0.6.7-py2.py3-none-any.whl (14 kB)\n", - "Building wheels for collected packages: pyknow, frozendict\n", - " Building wheel for pyknow (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for pyknow: filename=pyknow-1.7.0-py3-none-any.whl size=34228 sha256=b7de5b09292c4007667c72f69b98d5a1b5f7324ff15f9dd8e077c3d5f7aade42\n", - " Stored in directory: /tmp/pip-ephem-wheel-cache-k7jpave7/wheels/81/1a/d3/f6c15dbe1955598a37755215f2a10449e7418500d7bd4b9508\n", - " Building wheel for frozendict (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for frozendict: filename=frozendict-1.2-py3-none-any.whl size=3148 sha256=2863d55c240d2409cddf05ccfe600591f8478681549fc97555c47c90dc6bb160\n", - " Stored in directory: /home/rg/.cache/pip/wheels/49/ac/f8/cb8120244e710bdb479c86198b03c7b08c3c2d3d2bf448fd6e\n", - "Successfully built pyknow frozendict\n", - "Installing collected packages: schema, frozendict, pyknow\n", - "Successfully installed frozendict-1.2 pyknow-1.7.0 schema-0.6.7\n" + "Collecting git+https://github.com/nilp0inter/experta\n", + " Cloning https://github.com/nilp0inter/experta to /tmp/pip-req-build-7qurtwk3\n", + " Running command git clone --filter=blob:none --quiet https://github.com/nilp0inter/experta /tmp/pip-req-build-7qurtwk3\n", + " Resolved https://github.com/nilp0inter/experta to commit c6d5834b123861f5ae09e7d07027dc98bec58741\n", + " Installing build dependencies ... \u001b[?25ldone\n", + "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n", + "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25hRequirement already satisfied: frozendict~=2.4.6 in /opt/conda/envs/ai4beg/lib/python3.12/site-packages (from experta==1.9.5.dev1) (2.4.7)\n", + "Collecting schema~=0.6.7 (from experta==1.9.5.dev1)\n", + " Downloading schema-0.6.8-py2.py3-none-any.whl.metadata (14 kB)\n", + "Downloading schema-0.6.8-py2.py3-none-any.whl (14 kB)\n", + "Building wheels for collected packages: experta\n", + " Building wheel for experta (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25h Created wheel for experta: filename=experta-1.9.5.dev1-py3-none-any.whl size=34804 sha256=888c459512a5e713f4b674caa9a0f96cfdf07ec0d6eb56cc318ce0653d218014\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-1eeii9zy/wheels/3d/e8/bb/22d7956359603fa8dd679aa09f5b8efb3f29991c3986fdc787\n", + "Successfully built experta\n", + "Installing collected packages: schema, experta\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [experta]\n", + "\u001b[1A\u001b[2KSuccessfully installed experta-1.9.5.dev1 schema-0.6.8\n" ] } ], "source": [ "import sys\n", - "!{sys.executable} -m pip install git+https://github.com/buguroo/pyknow/" + "!{sys.executable} -m pip install git+https://github.com/nilp0inter/experta" ] }, { @@ -283,15 +282,15 @@ }, "outputs": [], "source": [ - "from pyknow import *\n", - "#import pyknow" + "from experta import *\n", + "#import experta" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "Me määratleme oma süsteemi klassina, mis pärib `KnowledgeEngine`-i. Iga reegel on määratletud eraldi funktsioonina koos `@Rule` annotatsiooniga, mis määrab, millal reegel peaks käivituma. Reegli sees saame lisada uusi fakte, kasutades `declare` funktsiooni, ja nende faktide lisamine põhjustab edasijõudva järeldusmootori poolt veel mõnede reeglite käivitamise.\n" + "Me määratleme oma süsteemi klassina, mis pärib `KnowledgeEngine`. Iga reegel määratletakse eraldi funktsioonina koos `@Rule` annotatsiooniga, mis täpsustab, millal reegel peaks käivituma. Reegli sees saame uusi fakte lisada funktsiooni `declare` abil, ja nende faktide lisamine toob kaasa selle, et edasiviiva järeldusmootori poolt kutsutakse välja veel teisi reegleid.\n" ] }, { @@ -378,7 +377,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Kui oleme määratlenud teadmistebaasi, täidame oma töömälu mõningate algfaktidega ja seejärel kutsume `run()` meetodi, et teostada järeldamist. Tulemusena näete, et töömälu täiendatakse uute järeldatud faktidega, sealhulgas lõplik fakt looma kohta (kui oleme kõik algfaktid õigesti seadistanud).\n" + "Kui oleme määratlenud teadmistebaasi, täidame oma töömälu mõningate algandmetega ja seejärel kutsume välja meetodi `run()`, et teha järeldusi. Nagu tulemusena näete, lisatakse töömälu uued järeldatud faktid, sealhulgas lõplik fakt loomade kohta (kui oleme kõik algandmed õigesti seadistanud).\n" ] }, { @@ -440,7 +439,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "\n---\n\n**Lahtiütlus**: \nSee dokument on tõlgitud AI tõlketeenuse [Co-op Translator](https://github.com/Azure/co-op-translator) abil. Kuigi püüame tagada täpsust, palume arvestada, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Algne dokument selle algses keeles tuleks pidada autoriteetseks allikaks. Olulise teabe puhul soovitame kasutada professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste või valesti tõlgenduste eest.\n" + "---\n\n\n**Vastutusest loobumine**:\nSee dokument on tõlgitud kasutades tehisintellekti tõlketeenust [Co-op Translator](https://github.com/Azure/co-op-translator). Kuigi püüame täpsust, palun pidage meeles, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Originaaldokument selle emakeeles tuleks pidada autoriteetseks allikaks. Olulise info puhul soovitatakse kasutada professionaalset inimtõlget. Me ei vastuta ühegi arusaamatuse või valesti tõlgendamise eest, mis võivad tekkida selle tõlke kasutamisel.\n\n" ] } ], @@ -467,8 +466,8 @@ "version": "3.11.2" }, "coopTranslator": { - "original_hash": "ab2bd97b0453415b89a469284609a8ce", - "translation_date": "2025-10-11T12:35:46+00:00", + "original_hash": "8ef43db4b9182239fd150a76bd494fdb", + "translation_date": "2026-01-16T07:20:43+00:00", "source_file": "lessons/2-Symbolic/Animals.ipynb", "language_code": "et" } diff --git a/translations/et/lessons/2-Symbolic/README.md b/translations/et/lessons/2-Symbolic/README.md index ba03759f..904df6da 100644 --- a/translations/et/lessons/2-Symbolic/README.md +++ b/translations/et/lessons/2-Symbolic/README.md @@ -1,116 +1,116 @@ -# Teadmiste esitus ja ekspertsüsteemid +# Teadmus Representatsioon ja Ekspertsüsteemid -![Sümboolse AI sisu kokkuvõte](../../../../translated_images/et/ai-symbolic.715a30cb610411a6.webp) +![Sümboolse tehisintellekti sisu kokkuvõte](../../../../../../translated_images/et/ai-symbolic.715a30cb610411a6.webp) -> Sketchnote autorilt [Tomomi Imura](https://twitter.com/girlie_mac) +> Sketchnote autor [Tomomi Imura](https://twitter.com/girlie_mac) -Tehisintellekti otsing põhineb teadmiste otsimisel, et mõista maailma sarnaselt sellele, kuidas inimesed seda teevad. Aga kuidas seda saavutada? +Tehisintellekti otsing põhineb teadmiste otsimisel, et maailma mõtestada sarnaselt inimestega. Aga kuidas sellega alustada? -## [Loengu-eelne viktoriin](https://ff-quizzes.netlify.app/en/ai/quiz/3) +## [Eel-loengu test](https://ff-quizzes.netlify.app/en/ai/quiz/3) -AI varajastel päevadel oli populaarne ülalt-alla lähenemine intelligentsete süsteemide loomisele (arutatud eelmises tunnis). Idee seisnes selles, et teadmised inimestelt tuleb masinloetavasse vormi viia ja seejärel kasutada neid probleemide automaatseks lahendamiseks. See lähenemine põhines kahel suurel ideel: +Tehisintellekti algusaegadel oli populaarne ülalt-alla lähenemine intelligentsete süsteemide loomisele (kõnealusest eelmises peatükis). Idee seisnes teadmiste väljavõtmises inimestelt masinakõlblikuks vormiks ja selle automaatseks kasutamiseks probleemide lahendamisel. See lähenemine põhines kahel suurel ideel: -* Teadmiste esitus +* Teadmiste representatsioon * Järeldamine -## Teadmiste esitus +## Teadmiste Representatsioon -Üks sümboolse AI olulisi mõisteid on **teadmised**. Oluline on eristada teadmisi *informatsioonist* või *andmetest*. Näiteks võib öelda, et raamatud sisaldavad teadmisi, sest nende uurimine võib muuta inimese eksperdiks. Kuid tegelikult sisaldavad raamatud *andmeid*, ja raamatute lugemise ning nende andmete integreerimise kaudu meie maailmamudelisse muudame need andmed teadmiseks. +Sümboolse tehisintellekti üks tähtsamaid mõisteid on **teadmus**. Oluline on eristada teadmust *infost* või *andmetest*. Näiteks võib öelda, et raamatud sisaldavad teadmust, sest nende uurimisega saab ekspertiks. Kuid tegelikult sisaldavad raamatud *andmeid*, ja neid lugedes ning andmeid oma maailmamudelis integreerides muudame need teadmuseks. -> ✅ **Teadmised** on midagi, mis on meie peas ja esindab meie arusaamist maailmast. Need saadakse aktiivse **õppimise** protsessi kaudu, mis integreerib saadud informatsiooni meie aktiivsesse maailmamudelisse. +> ✅ **Teadmus** on midagi, mis asub meie peas ja peegeldab meie maailma mõistmist. Seda omandatakse aktiivse **õppimise** protsessi käigus, mis liidab saadud teabe meie aktiivse maailmamudeliga. -Enamasti me ei defineeri teadmisi rangelt, vaid seostame neid teiste seotud mõistetega, kasutades [DIKW püramiidi](https://en.wikipedia.org/wiki/DIKW_pyramid). See sisaldab järgmisi mõisteid: +Tihti ei defineerita teadmust täpselt, vaid kooskõlastatakse see teiste seotud mõistetega kasutades [DIKW püramiidi](https://en.wikipedia.org/wiki/DIKW_pyramid). See sisaldab järgmisi mõisteid: -* **Andmed** on midagi, mis on esitatud füüsilises meedias, nagu kirjutatud tekst või räägitud sõnad. Andmed eksisteerivad sõltumatult inimestest ja neid saab inimestele edasi anda. -* **Informatsioon** on see, kuidas me andmeid oma peas tõlgendame. Näiteks, kui kuuleme sõna *arvuti*, on meil mingi arusaam, mis see on. -* **Teadmised** on informatsioon, mis on integreeritud meie maailmamudelisse. Näiteks, kui õpime, mis on arvuti, hakkame mõistma, kuidas see töötab, kui palju see maksab ja milleks seda saab kasutada. See omavahel seotud mõistete võrgustik moodustab meie teadmised. -* **Tarkus** on veel üks tasand meie arusaamisest maailmast ja esindab *meta-teadmisi*, näiteks arusaama, kuidas ja millal teadmisi kasutada. +* **Andmed** on midagi, mis on esitatud füüsilises kandjas, nagu kirjutatud tekst või räägitud sõnad. Andmed eksisteerivad iseseisvalt inimestest ja neid võib üle anda. +* **Info** on see, kuidas me tõlgendame andmeid oma peas. Näiteks kui kuuleme sõna *arvuti*, siis meil on mingisugune arusaamine, mis see on. +* **Teadmus** on info, mis integreeritakse meie maailmamudelisse. Näiteks kui me õpime, mis on arvuti, hakkame teadvustama, kuidas see töötab, kui palju maksab ja milleks seda kasutatakse. See omavahel seotud mõistete võrgustik moodustab meie teadmus. +* **Tarkus** on veel üks tase meie maailmamõistmises, mis tähistab *meta-knowledge’i*, st teadmisi selle kohta, kuidas ja millal teadmust kasutada. -*Pilt [Wikipedia-st](https://commons.wikimedia.org/w/index.php?curid=37705247), autor Longlivetheux - Oma töö, CC BY-SA 4.0* +*Pilt [Vikipeediast](https://commons.wikimedia.org/w/index.php?curid=37705247), autor Longlivetheux - enda töö, CC BY-SA 4.0* -Seega on **teadmiste esitamise** probleem leida tõhus viis teadmiste esitamiseks arvutis andmete kujul, et neid automaatselt kasutada. Seda võib vaadelda spektrina: +Seega seisneb **teadmiste representatsiooni** probleem selles, et leida mõni tõhus viis teadmiste esindamiseks arvutis andmete kujul, et neid saaks automaatselt kasutada. Seda võib vaadelda spektrina: -![Teadmiste esitamise spekter](../../../../translated_images/et/knowledge-spectrum.b60df631852c0217.webp) +![Teadmiste representatsiooni spekter](../../../../../../translated_images/et/knowledge-spectrum.b60df631852c0217.webp) -> Pilt autorilt [Dmitry Soshnikov](http://soshnikov.com) +> Pilt autor Dmitry Soshnikov [http://soshnikov.com](http://soshnikov.com) -* Vasakul on väga lihtsad teadmiste esitamise tüübid, mida arvutid saavad tõhusalt kasutada. Lihtsaim neist on algoritmiline, kus teadmised esitatakse arvutiprogrammi kujul. See pole aga parim viis teadmiste esitamiseks, kuna see pole paindlik. Meie peas olevad teadmised on sageli mittealgoritmilised. -* Paremal on esitusviisid nagu loomulik tekst. See on kõige võimsam, kuid ei sobi automaatseks järeldamiseks. +* Vasakul on väga lihtsad teadmusrepresentatsiooni tüübid, mida arvutid efektiivselt kasutada saavad. Kõige lihtsam on algoritmiline, kus teadmus on esindatud arvutiprogrammina. Kuid see pole parim viis teadmiste esindamiseks, sest see pole paindlik. Meie peas olev teadmus on sageli mitte-algoritmiline. +* Paremal on esindused nagu loomulik tekst. See on kõige võimsam, kuid ei sobi automaatseks järeldamiseks. -> ✅ Mõtle hetkeks, kuidas sa esitad teadmisi oma peas ja muudad need märkmeteks. Kas on olemas konkreetne formaat, mis aitab sul paremini meelde jätta? +> ✅ Mõtle korra, kuidas sa esindad teadmust oma peas ja kanaldate seda märkmeteks. Kas on mingi formaat, mis sulle hästi aitab teadmiste meeldejätmisel? -## Arvutite teadmiste esitamise klassifikatsioon +## Arvuti Teadmiste Representatsiooni Klassifitseerimine -Erinevaid arvutite teadmiste esitamise meetodeid saab klassifitseerida järgmistesse kategooriatesse: +Võime erinevaid arvuti teadmusrepresentatsiooni meetodeid liigitada järgmisteks kategooriateks: -* **Võrguesitused** põhinevad faktil, et meie peas on omavahel seotud mõistete võrgustik. Me võime proovida luua sama võrgustikku graafina arvutis - nn **semantiline võrgustik**. +* **Võrgu esindused** põhinevad tõsiasjal, et meie peas on omavahel seotud mõistete võrgustik. Saame proovida sama võrku arvutis graafikuna taastada - nn **semantiline võrk**. -1. **Objekt-atribuut-väärtus kolmikud** või **atribuut-väärtus paarid**. Kuna graafi saab arvutis esitada sõlmede ja servade loendina, saame semantilist võrgustikku esitada kolmikute loendina, mis sisaldavad objekte, atribuute ja väärtusi. Näiteks loome järgmised kolmikud programmeerimiskeelte kohta: +1. **Objekt-atribuut-väärtus tripletid** ehk **atribuut-väärtus paarid**. Kuna graafikut saab arvutis esitada sõlmede ja servade nimekirjana, saame semantilise võrgu esindada tripletite nimekirjana, mis sisaldab objekte, atribuute ja väärtusi. Näiteks koostame järgmised tripletid programmeerimiskeelte kohta: Objekt | Atribuut | Väärtus --------|----------|------- +-------|-----------|------ Python | on | Tüübita keel -Python | leiutatud | Guido van Rossum -Python | ploki süntaks | taanded -Tüübita keel | ei sisalda | tüübimääratlusi +Python | leiutas | Guido van Rossum +Python | plokisüntaks | taandumine +Tüübita keel | ei oma | tüübimääratlusi -> ✅ Mõtle, kuidas kolmikuid saab kasutada teiste teadmiste tüüpide esitamiseks. +> ✅ Mõtle, kuidas tripleteid saab kasutada teiste teadmiste esindamiseks. -2. **Hierarhilised esitused** rõhutavad fakti, et me loome sageli oma peas objektide hierarhia. Näiteks teame, et kanaarilind on lind ja kõik linnud omavad tiibu. Samuti on meil mingi ettekujutus, mis värvi kanaarilinnud tavaliselt on ja milline on nende lennukiirus. +2. **Hierarhilised esindused** rõhutavad, et me loome sageli oma peas objektide hierarhia. Näiteks teame, et kanarilind on lind ja kõik linnud omavad tiibu. Samuti on meil aimu, mis värvi kanarilind tavaliselt on ja kui kiiresti nad lendavad. - - **Raamiesitus** põhineb iga objekti või objektiklassi esitamisel **raamina**, mis sisaldab **pesi**. Pesadel on võimalikud vaikimisi väärtused, väärtuste piirangud või salvestatud protseduurid, mida saab kasutada pesa väärtuse saamiseks. Kõik raamid moodustavad hierarhia, mis sarnaneb objektide hierarhiaga objektorienteeritud programmeerimiskeeltes. - - **Stsenaariumid** on eriline raamide tüüp, mis esindab keerulisi olukordi, mis võivad aja jooksul areneda. + - **Raamistiku representatsioon** põhineb iga objekti või objekti klassi kujutamisel **raamistikuna**, mis sisaldab **pesasid**. Pesad võivad omada vaikeväärtusi, väärtusepiiranguid või salvestatud protseduure, mida saab kutsuda pesa väärtuse saamiseks. Kõik raamistikud moodustavad hierarhia, mis sarnaneb objektihierarhiaga objektorienteeritud programmeerimiskeeltes. + - **Stsenaariumid** on eriliik raamistikke, mis esindavad keerulisi olukordi, mis võivad ajas areneda. **Python** -Pesa | Väärtus | Vaikimisi väärtus | Intervall | ------|--------|-------------------|----------| +Pesa | Väärtus | Vaikeväärtus | Vahemik | +-----|----------|--------------|---------| Nimi | Python | | | -On | Tüübita keel | | | -Muutuja vorm | | CamelCase | | -Programmi pikkus | | | 5-5000 rida | -Ploki süntaks | Taanded | | | +On-Tüüpi | Tüübita keel | | | +Muutuja Kirjutus | | CamelCase | | +Programmi Pikkus | | | 5–5000 rida | +Ploki Süntaks | Taandumine | | | -3. **Protseduurilised esitused** põhinevad teadmiste esitamisel tegevuste loendina, mida saab teatud tingimuse korral täita. - - Tootmisreeglid on if-then laused, mis võimaldavad meil järeldusi teha. Näiteks võib arstil olla reegel, mis ütleb, et **KUI** patsiendil on kõrge palavik **VÕI** kõrge C-reaktiivse valgu tase vereanalüüsis, **SIIS** tal on põletik. Kui kohtame ühte tingimustest, saame teha järelduse põletiku kohta ja kasutada seda edasiseks järeldamiseks. - - Algoritme võib pidada teiseks protseduurilise esituse vormiks, kuigi neid peaaegu kunagi ei kasutata otse teadmistepõhistes süsteemides. +3. **Proceduurilised esindused** põhinevad teadmiste kujutamisel tegevuste nimekirjana, mida saab käivitada, kui mingi tingimus täitub. + - Tootmisreeglid on kui-siis laused, mis võimaldavad järeldusi teha. Näiteks võib arst omada reeglit, mis ütleb, et **KUI** patsiendil on kõrge palavik **VÕI** kõrge C-reaktiivse valgu tase vereanalüüsis, **SIIS** on tal põletik. Kui kohtame üht tingimust, saame järeldada põletiku olemasolu ja kasutada seda edasises järeldamises. + - Algoritme võib pidada teiseks vormiks proceduurilise representatsiooni puhul, kuigi neid peaaegu kunagi teadmistepõhistes süsteemides otse ei kasutata. -4. **Loogika** pakkus algselt välja Aristoteles universaalsete inimteadmiste esitamise viisina. - - Predikaatloogika kui matemaatiline teooria on liiga rikkalik, et olla arvutatav, seetõttu kasutatakse tavaliselt selle alamhulka, näiteks Horni klausleid, mida kasutatakse Prologis. - - Kirjeldav loogika on loogikasüsteemide perekond, mida kasutatakse objektide hierarhiate ja hajutatud teadmiste esituste, näiteks *semantilise veebi*, esitamiseks ja järeldamiseks. +4. **Loogika** pakkus Aristoteles algselt universaliseeritud inimese teadmiste esindamise vahendina. + - Predikaatloogika kui matemaatiline teooria on liiga lai, et olla kõikehõlmav, seega kasutatakse enamasti selle alamkomplekte, näiteks Horn'-klausleid Prologis. + - Kirjeldav loogika on loogikasüsteemide perekond, mida kasutatakse objektide hierarhiate ja jaotatud teadmiste representatsioonide nagu *semantilise veebina* esindamiseks ja nende üle järeldamiseks. ## Ekspertsüsteemid -Sümboolse AI varajased edusammud olid nn **ekspertsüsteemid** - arvutisüsteemid, mis olid loodud tegutsema eksperdina mõnes piiratud probleemivaldkonnas. Need põhinesid **teadmistebaasil**, mis oli saadud ühelt või mitmelt inimeksperdilt, ja sisaldasid **järeldusmootorit**, mis tegi selle põhjal järeldusi. +Üks sümboolse tehisintellekti varajasi edusamme olid nn **ekspertsüsteemid** — arvutisüsteemid, mis olid loodud käituma nagu ekspert kitsas probleemivaldkonnas. Need põhinesid **teadmistebaasil**, mis oli kogutud ühelt või mitmelt inimeselt, ja sisaldasid **järeldusmootorit**, mis teostas järeldamist selle põhjal. -![Inimese arhitektuur](../../../../translated_images/et/arch-human.5d4d35f1bba3ab1c.webp) | ![Teadmistepõhise süsteemi arhitektuur](../../../../translated_images/et/arch-kbs.3ec5c150b09fa8da.webp) +![Inimese arhitektuur](../../../../../../translated_images/et/arch-human.5d4d35f1bba3ab1c.webp) | ![Teadmistepõhise süsteemi arhitektuur](../../../../../../translated_images/et/arch-kbs.3ec5c150b09fa8da.webp) ---------------------------------------------|------------------------------------------------ -Lihtsustatud inimese närvisüsteemi struktuur | Teadmistepõhise süsteemi arhitektuur +Inimese närvisüsteemi lihtsustatud struktuur | Teadmistepõhise süsteemi arhitektuur -Ekspertsüsteemid on ehitatud nagu inimese järeldussüsteem, mis sisaldab **lühiajalist mälu** ja **pikaajalist mälu**. Samamoodi eristame teadmistepõhistes süsteemides järgmisi komponente: +Ekspertsüsteemid on üles ehitatud inimese mõtlemise süsteemile sarnaselt, mis sisaldab **lühimälu** ja **pikaajalist mälu**. Samamoodi eristame teadmistepõhistes süsteemides järgmisi komponente: -* **Probleemimälu**: sisaldab teadmisi praegu lahendatavast probleemist, nt patsiendi temperatuur või vererõhk, kas tal on põletik või mitte jne. Neid teadmisi nimetatakse ka **staatilisteks teadmiseks**, kuna need sisaldavad hetkeolukorra teadmist - nn *probleemi seisundit*. -* **Teadmistebaas**: esindab pikaajalisi teadmisi probleemivaldkonna kohta. See saadakse käsitsi inimekspertidelt ja ei muutu konsultatsioonist konsultatsioonini. Kuna see võimaldab meil liikuda ühest probleemiseisundist teise, nimetatakse seda ka **dünaamiliseks teadmiseks**. -* **Järeldusmootor**: korraldab kogu protsessi probleemiseisundi ruumis otsimiseks, vajadusel kasutajalt küsimuste küsimiseks. See vastutab ka iga seisundi jaoks sobivate reeglite leidmise eest. +* **Probleemimälu**: sisaldab teadmisi praegu lahendatava probleemi kohta, nt patsiendi temperatuuri või vererõhku, kas tal on põletik või mitte jne. Seda nimetatakse ka **staatiliseks teadmuseks**, sest see sisaldab hetkepilti sellest, mida me probleemist parasjagu teame – nn *probleemitilanne*. +* **Teadmistebaas**: esindab pikaajalisi teadmisi antud probleemivaldkonnas. See on käsitsi kogutud inimekspertidelt ja ei muutu konsultatsioonide vahel. Kuna see võimaldab navigeerida ühest probleemistilast teise, nimetatakse seda ka **dünaamiliseks teadmuseks**. +* **Järeldusmootor**: juhib kogu protsessi probleemitilanne ruumis otsides, küsides kasutajalt vajadusel küsimusi. See vastutab ka õigete reeglite leidmise eest igas etapis. -Näiteks vaatame järgmist ekspertsüsteemi, mis määrab looma füüsiliste omaduste põhjal: +Näiteks oluline ekspert­süsteemi näide on looma määramine füüsiliste omaduste põhjal: -![AND-OR puu](../../../../translated_images/et/AND-OR-Tree.5592d2c70187f283.webp) +![JA-VÕI puu](../../../../../../translated_images/et/AND-OR-Tree.5592d2c70187f283.webp) -> Pilt autorilt [Dmitry Soshnikov](http://soshnikov.com) +> Pilt autor Dmitry Soshnikov [http://soshnikov.com](http://soshnikov.com) -See diagramm on nn **AND-OR puu**, ja see on tootmisreeglite graafiline esitus. Puu joonistamine on kasulik eksperdilt teadmiste hankimise alguses. Teadmiste esitamiseks arvutis on mugavam kasutada reegleid: +See diagramm on nimetatud **JA-VÕI puuks** ja see on tootmisreeglite kogumi graafiline kujutis. Puu joonistamine on kasulik alguses teadmiste väljatöötamisel eksperdilt. Teadmisi arvutis esindamiseks on mugavam kasutada reegleid: ``` IF the animal eats meat @@ -120,79 +120,79 @@ OR (animal has sharp teeth ) THEN the animal is a carnivore ``` + +Võid märgata, et iga vasakpoolse tingimuse ja tegevuse osa reeglites on sisuliselt objekt-atribuut-väärtus kolmikud (OAV). **Töömälus** hoitakse komplekti OAV kolmikutest, mis vastavad hetkel lahendatavale probleemile. **Reeglimootor** otsib reegleid, mille tingimus on rahuldatud, ja rakendab neid, lisades uue kolmiku töömällu. -Võite märgata, et iga tingimus reegli vasakul küljel ja tegevus on sisuliselt objekt-atribuut-väärtus (OAV) kolmikud. **Töömälus** on OAV kolmikute komplekt, mis vastab praegu lahendatavale probleemile. **Reeglimootor** otsib reegleid, mille tingimus on täidetud, ja rakendab neid, lisades töömällu uue kolmiku. +> ✅ Kirjuta oma JA-VÕI puu mõnel sulle huvipakkuval teemal! -> ✅ Joonista oma AND-OR puu teemal, mis sulle meeldib! +### Edasi- ja Tagasi-Järeldamine -### Edasi- ja tagasijäreldamine +Ülal kirjeldatud protsessi nimetatakse **edasi-järeldamiseks**. See algab esialgsete andmetega, mis on töömälus olemas ja teeb järgmise järeldusliku tsükli: -Ülal kirjeldatud protsessi nimetatakse **edasi järeldamiseks**. See algab mõne algandmega probleemi kohta, mis on töömälus, ja seejärel täidab järgmise järeldamisringi: +1. Kui sihtatribuut on töömälus olemas – peatu ja anna tulemus +2. Otsi välja kõik reeglid, mille tingimus on täidetud – moodusta **konfliktikomplekt**. +3. Tee **konfliktilahendus** – vali üks reegel, mida käesoleval sammul rakendada. Konfliktilahendusstrateegiaid on mitmeid: + - vali teadmistebaasist esimene rakendatav reegel + - vali juhuslik reegel + - vali *täpsem* reegel, mis vastab kõige rohkem tingimustele vasakul pool +4. Rakenda valitud reegel ja lisa uus teadmus probleemitilanne'i +5. Korda kõiki samme alates 1 -1. Kui sihtatribuut on töömälus olemas - peatu ja anna tulemus -2. Otsi kõik reeglid, mille tingimus on praegu täidetud - moodusta **konfliktikomplekt** reeglitest. -3. Teosta **konfliktide lahendamine** - vali üks reegel, mida sellel sammul täidetakse. Võib olla erinevaid konfliktide lahendamise strateegiaid: - - Vali esimene rakendatav reegel teadmistebaasis - - Vali juhuslik reegel - - Vali *spetsiifilisem* reegel, st see, mis vastab kõige rohkem tingimustele reegli "vasakul küljel" (LHS) -4. Rakenda valitud reegel ja lisa uus teadmistükk probleemiseisundisse -5. Korda alates sammust 1. +Mõnikord soovime aga alustada probleemist väheste teadmistega ja esitada küsimusi, mis aitavad jõuda järeldusele. Näiteks meditsiinilise diagnoosi puhul ei tee tavaliselt kohe kõiki analüüse enne patsiendi uurimist, vaid teevad vajalikke analüüse arvestades diagnoosimist. -Kuid mõnel juhul võime soovida alustada probleemist teadmata ja esitada küsimusi, mis aitavad meil järelduseni jõuda. Näiteks meditsiinilise diagnoosi tegemisel ei tee me tavaliselt kõiki meditsiinilisi analüüse ette enne patsiendi diagnoosimist. Pigem tahame analüüse teha, kui otsus tuleb langetada. +Seda protsessi saab modelleerida **tagasi-järeldamisega**. See algab **eesmärgist** – otsitu atribuudi väärtusest: -Seda protsessi saab modelleerida **tagasijäreldamise** abil. Seda juhib **eesmärk** - atribuudi väärtus, mida me otsime: +1. Vali kõik reeglid, mis võivad anda eesmärgi väärtuse (st mille “paremapoolsel” ehk RHS-l on eesmärk) – konfliktikomplekt +1. Kui selle atribuudi kohta reegleid pole või on reegel, mis ütleb, et kasutajalt tuleb küsida, küsige väärtust kasutajalt, muul juhul: +1. Kasuta konfliktilahendust ühe hüpoteesi valimiseks – püüa seda tõestada +1. Korda seda protsessi kõikide reegli vasaku poole (LHS) atribuutide puhul, püüdes neid tõestada eesmärkidena +1. Kui protsess ebaõnnestub – proovi valida muu reegel sammus 3. -1. Vali kõik reeglid, mis võivad anda meile eesmärgi väärtuse (st eesmärk reegli paremal küljel (RHS)) - konfliktikomplekt -1. Kui selle atribuudi jaoks pole reegleid või on reegel, mis ütleb, et peaksime kasutajalt väärtust küsima - küsi seda, muidu: -1. Kasuta konfliktide lahendamise strateegiat, et valida üks reegel, mida me kasutame *hüpoteesina* - proovime seda tõestada -1. Korda protsessi rekursiivselt kõigi reegli vasakul küljel olevate atribuutide jaoks, püüdes neid eesmärkidena tõestada -1. Kui protsess mingil hetkel ebaõnnestub - kasuta sammus 3 teist reeglit. +> ✅ Millistes olukordades on edasi-järeldamine sobivam? Kuidas tagasi-järeldamine? -> ✅ Millistes olukordades on edasi järeldamine sobivam? Aga tagasijäreldamine? +### Ekspertsüsteemide Rakendamine -### Ekspertsüsteemide rakendamine +Ekspertsüsteemid saab rakendada erinevatel viisidel: -Ekspertsüsteeme saab rakendada erinevate tööriistade abil: +* Otse programmeerides kõrgema taseme programmeerimiskeeles. See pole parim valik, sest teadmistepõhise süsteemi peamine eelis on teadmistest ja järeldamisest eraldamine ning probleemi eksperdil võiks olla võimalik kirjutada reegleid ilma järeldamisprotsessi detailideta mõistmata. +* Kasutades **ekspertsüsteemi kestat**, st süsteemi, mis on spetsiaalselt loodud teadmiste sisestamiseks mingis teadmusrepresentatsiooni keeles. -* Programmeerides neid otse mõnes kõrgetasemelises programmeerimiskeeles. See pole parim idee, kuna teadmistepõhise süsteemi peamine eelis on see, et teadmised on järeldusest eraldatud ja potentsiaalselt peaks probleemivaldkonna ekspert suutma reegleid kirjutada ilma järeldusprotsessi üksikasju mõistmata. -* Kasutades **ekspertsüsteemi kesta**, st süsteemi, mis on spetsiaalselt loodud teadmiste täitmiseks, kasutades mõnda teadmiste esitamise keelt. +## ✍️ Harjutus: Loomade Järeldamine -## ✍️ Harjutus: Loomade järeldamine +Näide edasi- ja tagasi-järeldamise ekspert­süsteemi loomise kohta leiad failist [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb). -Vaata [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb) näidet edasi- ja tagasijäreldamise ekspertsüsteemi rakendamisest. +> **Märkus**: See näide on suhteliselt lihtne ja annab idee, kuidas ekspert­süsteem välja näeb. Süsteemi loomisel märkad, et *intelligentne* käitumine ilmneb alles reeglite arvu jõudes ligikaudu 200+ juurde. Sel hetkel muutuvad reeglid liiga keerukaks meelde jätta ja tekib küsimus, miks süsteem teatud otsuseid teeb. Kuid oluline iseärasus teadmusbaasilistel süsteemidel on see, et nende otsuseid saab alati *selgitada* täpselt, kuidas need tehti. -> **Märkus**: See näide on üsna lihtne ja annab ainult ettekujutuse, kuidas ekspertsüsteem välja näeb. Kui hakkate sellist süsteemi looma, märkate *intelligentset* käitumist alles siis, kui jõuate teatud arvu reegliteni, umbes 200+. Mingil hetkel muutuvad reeglid liiga keerukaks, et kõiki neid meeles pidada, ja siis võite hakata mõtlema, miks süsteem teeb teatud otsuseid. Kuid teadmistepõhiste süsteemide oluline omadus on see, et saate alati *selgitada*, kuidas ükskõik milline otsus tehti. +## Ontoloogiad ja Semantiline Veeb -## Ontoloogiad ja semantiline veeb +20. sajandi lõpus algatati teadmiste representatsiooni kasutamine interneti ressursside märgistamiseks, et oleks võimalik leida ressursse väga spetsiifiliste päringute jaoks. Seda algatust kutsuti **semantiliseks veebiks** ja see toetus mitmele mõistele: -20. sajandi lõpus oli algatus kasutada teadmiste esitamist Interneti ressursside märgistamiseks, et oleks võimalik leida ressursse, mis vastavad väga spetsiifilistele päringutele. Seda liikumist nimetati **semantiliseks veebiks**, ja see tugines mitmele kontseptsioonile: +- Eriline teadmiste esindus, mis tugineb **[kirjeldavatele loogikatele](https://en.wikipedia.org/wiki/Description_logic)** (DL). See on sarnane raamistike esindamisega, sest loob objektide hierarhia omadustega, kuid omab formaalset loogilist semantikat ja järeldamist. DL-id on erineva väljendusvõime ja järeldamisalgoritmi keerukusega süsteemide perekond. +- Hajutatud teadmiste representatsioon, kus kõik mõisted on esindatud globaalse URI identifikaatoriga, võimaldades luua teadmiste hierarhiaid, mis ulatuvad üle interneti. +- Perekond XML-põhistest keeltest teadmiste kirjeldamiseks: RDF (Resource Description Framework), RDFS (RDF Schema), OWL (Ontology Web Language). -- Eriline teadmiste esitus, mis põhineb **[kirjeldusloogikal](https://en.wikipedia.org/wiki/Description_logic)** (DL). See sarnaneb raamiesitusega, kuna loob objektide hierarhia omadustega, kuid sellel on formaalne loogiline semantika ja järeldus. DL-de perekond tasakaalustab väljendusrikkuse ja järelduse algoritmilise keerukuse vahel. -- Hajutatud teadmiste esitus, kus kõik mõisted esitatakse globaalse URI identifikaatoriga, võimaldades luua teadmiste hierarhiaid, mis ulatuvad üle interneti. -- XML-põhiste keelte perekond teadmiste kirjeldamiseks: RDF (Resource Description Framework), RDFS (RDF Schema), OWL (Ontology Web Language). +Semantilises veebis on keskne mõiste **Ontoloogia**. See viitab probleemitsooni selgele spetsifikatsioonile, kasutades mõnda formaalset teadmiste esitamise meetodit. Lihtsaim ontoloogia võib olla lihtsalt objektide hierarhia probleemitsoonis, kuid keerukamad ontoloogiad sisaldavad reegleid, mida saab kasutada järeldamiseks. -Semantilise veebi keskne mõiste on **ontoloogia**. See viitab probleemivaldkonna selgesõnalisele spetsifikatsioonile, kasutades mõnda formaalset teadmiste esitusviisi. Lihtsaim ontoloogia võib olla lihtsalt objektide hierarhia probleemivaldkonnas, kuid keerukamad ontoloogiad sisaldavad reegleid, mida saab kasutada järelduste tegemiseks. - -Semantilises veebis põhinevad kõik esitusviisid kolmikutel. Iga objekt ja iga seos on unikaalselt identifitseeritud URI abil. Näiteks, kui soovime väita, et see AI õppekava on koostanud Dmitry Soshnikov 1. jaanuaril 2022, siis siin on kolmikud, mida saame kasutada: +Semantilises veebis põhinevad kõik esitlused triplettidel. Iga objekt ja iga seos on unikaalselt identifitseeritud URI-ga. Näiteks, kui tahame väita fakti, et see AI õppekava töötas Dmitry Soshnikov välja 1. jaanuaril 2022 - siin on tripletid, mida saame kasutada: ``` -http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 13, 2007” +http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 1, 2022” http://github.com/microsoft/ai-for-beginners http://purl.org/dc/elements/1.1/creator http://soshnikov.com ``` -> ✅ Siin `http://www.example.com/terms/creation-date` ja `http://purl.org/dc/elements/1.1/creator` on mõned tuntud ja universaalselt aktsepteeritud URI-d, et väljendada *looja* ja *loomiskuupäeva* mõisteid. +> ✅ Siin on `http://www.example.com/terms/creation-date` ja `http://purl.org/dc/elements/1.1/creator` tuntud ja üldtunnustatud URI-d, mis väljendavad mõisteid *looja* ja *loomise kuupäev*. -Keerukamal juhul, kui soovime määratleda loojate nimekirja, saame kasutada RDF-is määratletud andmestruktuure. +Keerukamas olukorras, kui tahame määratleda loojate nimekirja, võime kasutada mõnda RDF-is määratletud andmestruktuuri. -> Ülaltoodud diagrammid: [Dmitry Soshnikov](http://soshnikov.com) +> Ülaltoodud diagrammid autorilt [Dmitry Soshnikov](http://soshnikov.com) -Semantilise veebi arendamine aeglustus mingil määral otsingumootorite ja loomuliku keele töötlemise tehnikate edu tõttu, mis võimaldavad tekstist struktureeritud andmeid välja võtta. Kuid mõnes valdkonnas tehakse endiselt märkimisväärseid jõupingutusi ontoloogiate ja teadmistebaaside säilitamiseks. Mõned tähelepanuväärsed projektid: +Semantilise veebiga seotud arendust on mingil määral aeglustanud otsingumootorite ja loomuliku keele töötlemise tehnoloogiate edu, mis võimaldavad tekstist struktureeritud andmeid eraldada. Kuid mõnes valdkonnas tehakse jätkuvalt olulist tööd ontoloogiate ja teadmistebaaside haldamiseks. Mõned silmapaistvad projektid: -* [WikiData](https://wikidata.org/) on masinloetavate teadmistebaaside kogum, mis on seotud Wikipediaga. Enamik andmeid on kaevandatud Wikipedia *InfoBoxidest*, struktureeritud sisust Wikipedia lehtedel. Wikidatat saab [pärida](https://query.wikidata.org/) SPARQL-i abil, mis on semantilise veebi jaoks mõeldud päringukeel. Siin on näidis päring, mis kuvab inimeste seas populaarseimad silmavärvid: +* [WikiData](https://wikidata.org/) on masinloetavate teadmistebaaside kogum, mis on seotud Vikipeediaga. Enamik andmeid on otsitud Vikipeedia *InfoBoxidest*, mis on Vikipeedia lehtede sees olevad struktureeritud sisutükid. WikiData-s saab SPARQL-iga, semantilise veebipäringu keelega, [päringuid esitada](https://query.wikidata.org/). Siin on näide päringust, mis kuvab inimeste seas kõige populaarsemad silmavärvid: ```sparql #defaultView:BubbleChart @@ -206,49 +206,51 @@ WHERE GROUP BY ?eyeColorLabel ``` -* [DBpedia](https://www.dbpedia.org/) on sarnane projekt WikiDataga. +* [DBpedia](https://www.dbpedia.org/) on veel üks sarnane ettevõtmine nagu WikiData. -> ✅ Kui soovite katsetada oma ontoloogiate loomist või olemasolevate avamist, on suurepärane visuaalne ontoloogia redaktor nimega [Protégé](https://protege.stanford.edu/). Laadige see alla või kasutage seda veebis. +> ✅ Kui soovid katsetada oma ontoloogiate loomist või olemasolevate avamist, on olemas suurepärane visuaalne ontoloogia redaktor nimega [Protégé](https://protege.stanford.edu/). Laadi see alla või kasuta veebis. -*Web Protégé redaktor avatud Romanovite perekonna ontoloogiaga. Ekraanipilt: Dmitry Soshnikov* +*Veebiredaktor Protégé avatud Romanovi perekonna ontoloogiaga. Ekraanipilt Dmitry Soshnikovilt* ## ✍️ Harjutus: Perekonna ontoloogia -Vaadake [FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb) näidet semantilise veebi tehnikate kasutamisest perekondlike suhete analüüsimiseks. Võtame perekonna puu, mis on esitatud tavalises GEDCOM formaadis, ja perekondlike suhete ontoloogia ning loome graafi kõigist perekondlikest suhetest antud isikute komplekti jaoks. +Vaata [FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb), mis on näide semantilise veebi tehnikate kasutamisest perekonna suhete järeldamiseks. Võtame perekonnaseisu puu, mis on esitatud tavalises GEDCOM formaadis, ja perekondlike suhete ontoloogiaga ehitame graafi kõigi antud isikute suhete kohta. -## Microsofti kontseptsioonigraaf +## Microsoft Concept Graph -Enamasti luuakse ontoloogiad hoolikalt käsitsi. Kuid ontoloogiaid on võimalik ka **kaevandada** struktureerimata andmetest, näiteks loomuliku keele tekstidest. +Enamikul juhtudel luuakse ontoloogiad hoolikalt käsitsi. Kuid on võimalik ka ontoloogiate **kaevandamine** struktureerimata andmetest, näiteks loomulikus keeles tekstidest. -Üks selline katse tehti Microsoft Researchi poolt ja tulemuseks oli [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste). +Üks selline katse tehti Microsoft Researchi poolt, mille tulemuseks oli [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste). -See on suur kogum entiteete, mis on rühmitatud `is-a` pärilikkussuhete abil. See võimaldab vastata küsimustele nagu "Mis on Microsoft?" - vastus oleks midagi sellist nagu "ettevõte tõenäosusega 0.87 ja bränd tõenäosusega 0.75". +See on suur üksuste kogum, mis on grupeeritud pärandumissuhtes `is-a`. See võimaldab vastata küsimustele nagu "Mis on Microsoft?" - vastus oleks midagi sarnast "ettevõte tõenäosusega 0.87 ja bränd tõenäosusega 0.75". -Graaf on saadaval kas REST API-na või suure allalaaditava tekstifailina, mis loetleb kõik entiteetide paarid. +See graafik on saadaval kas REST API-na või suurena allalaaditava tekstifailina, mis loetleb kõik üksuste paarid. -## ✍️ Harjutus: Kontseptsioonigraaf +## ✍️ Harjutus: Kontseptsioonide graafik -Proovige [MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) märkmikku, et näha, kuidas saame kasutada Microsofti kontseptsioonigraafi uudisteartiklite rühmitamiseks mitmesse kategooriasse. +Proovi [MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) märkmikku, et näha, kuidas Microsoft Concept Graphi saab kasutada uudisteartiklite rühmitamiseks mitmesse kategooriasse. ## Kokkuvõte -Tänapäeval peetakse AI-d sageli *masinõppe* või *närvivõrkude* sünonüümiks. Kuid inimene näitab ka selgesõnalist arutlemist, mis on midagi, mida närvivõrgud praegu ei käsitle. Päriselu projektides kasutatakse selgesõnalist arutlemist endiselt ülesannete täitmiseks, mis nõuavad selgitusi või süsteemi käitumise kontrollitud viisil muutmist. +Tänapäeval peetakse AI-d sageli masinõppe või närvivõrkude sünonüümiks. Kuid inimene näitab ka otsest järeldamist, mida närvivõrgud praegu ei käsitle. Reaalsetes projektides kasutatakse otsest järeldamist endiselt ülesannete lahendamiseks, mis vajavad selgitusi või süsteemi käitumise muutmise võimalust kontrollitud viisil. ## 🚀 Väljakutse -Perekonna ontoloogia märkmikus, mis on seotud selle õppetunniga, on võimalus katsetada teiste perekondlike suhetega. Proovige avastada uusi seoseid inimeste vahel perekonna puus. +Selle õppetüki perekonna ontoloogia märkmikus on võimalus katsetada muid perekondlikke suhteid. Proovi leida uusi ühendusi inimeste vahel perekonna puus. -## [Loengu järgne viktoriin](https://ff-quizzes.netlify.app/en/ai/quiz/4) +## [Loengu järeltest](https://ff-quizzes.netlify.app/en/ai/quiz/4) ## Ülevaade ja iseseisev õpe -Tehke internetis uurimistööd, et avastada valdkondi, kus inimesed on püüdnud teadmisi kvantifitseerida ja kodeerida. Vaadake Bloom'i taksonoomiat ja minge ajaloos tagasi, et õppida, kuidas inimesed püüdsid oma maailma mõista. Uurige Linnaeuse tööd organismide taksonoomia loomiseks ja jälgige, kuidas Dmitri Mendelejev lõi viisi keemiliste elementide kirjeldamiseks ja rühmitamiseks. Milliseid huvitavaid näiteid veel leiate? +Uuri internetist, kus valdkondades on inimesed püüdnud teadmisi kvantifitseerida ja kodeerida. Vaata Bloom'i taksonoomiat ja mine ajas tagasi, et õppida, kuidas inimesed on püüdnud maailma mõista. Uuri Linnaeuse tööd organismide taksonoomia loomiseks ning jälgi, kuidas Dmitri Mendelejev lõi keemilistelementide kirjeldamiseks ja rühmitamiseks süsteemi. Milliseid teisi huvitavaid näiteid suudad leida? -**Ülesanne**: [Loo ontoloogia](assignment.md) +**Kodutöö**: [Loo ontoloogia](assignment.md) --- -**Lahtiütlus**: -See dokument on tõlgitud tehisintellekti tõlketeenuse [Co-op Translator](https://github.com/Azure/co-op-translator) abil. Kuigi püüame tagada tõlke täpsuse, palume arvestada, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Algne dokument selle algses keeles tuleks lugeda autoriteetseks allikaks. Olulise teabe puhul soovitame kasutada professionaalset inimtõlget. Me ei vastuta selle tõlke kasutamisest tulenevate arusaamatuste või valede tõlgenduste eest. \ No newline at end of file + +**Ärge usaldage täielikult**: +See dokument on tõlgitud kasutades tehisintellekti tõlketeenust [Co-op Translator](https://github.com/Azure/co-op-translator). Kuigi püüame täpsust, palun pidage meeles, et automaatsed tõlked võivad sisaldada vigu või ebatäpsusi. Originaaldokument oma algkeeles loetakse usaldusväärseks allikaks. Olulise teabe puhul soovitatakse kasutada professionaalset inimtõlget. Me ei vastuta mis tahes arusaamatuste või valesti mõistmiste eest, mis võivad sellest tõlkest tuleneda. + \ No newline at end of file diff --git a/translations/pcm/README.md b/translations/pcm/README.md index c7246d76..116021c9 100644 --- a/translations/pcm/README.md +++ b/translations/pcm/README.md @@ -1,8 +1,8 @@ -**If you want additional translation language dem wey dey supported dey listed [here](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** +**If you want make dem add extra translation languages, dem list dey [here](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** -## Join the Community +## Join di Community [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) ## Wetin you go learn **[Mindmap of the Course](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** -For dis curriculum, you go learn: +For this curriculum, you go learn: -* Different ways to take do Artificial Intelligence, including di "good old" symbolic style wit **Knowledge Representation** and reasoning ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* **Neural Networks** and **Deep Learning**, wey be di core of modern AI. We go show di concepts behind dem important topics using code for two top framework - [TensorFlow](http://Tensorflow.org) and [PyTorch](http://pytorch.org). -* **Neural Architectures** wey dey work with images and text. We go cover recent models but small kind lack latest state-of-the-art. -* Less common AI methods, like **Genetic Algorithms** and **Multi-Agent Systems**. +* Different ways to do Artificial Intelligence, including di "good old" symbolic way wit **Knowledge Representation** and reasoning ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* **Neural Networks** and **Deep Learning**, wey be di main tin for modern AI. We go show di concepts behind these important topics wit code for two popular frameworks - [TensorFlow](http://Tensorflow.org) and [PyTorch](http://pytorch.org). +* **Neural Architectures** for work wit images and text. We go cover recent models but e fit no too strong for the newest ones. +* Less popular AI ways, like **Genetic Algorithms** and **Multi-Agent Systems**. -Wetin we no go cover for dis curriculum: +Wetin we no go talk for dis curriculum: > [Find all additional resources for this course in our Microsoft Learn collection](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* Business cases of using **AI in Business**. Abeg consider take [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) learning path for Microsoft Learn, or [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), wey dem develop for cooperation wit [INSEAD](https://www.insead.edu/). +* Business tins wey dey use **AI for Business**. Try check [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) learning path for Microsoft Learn, or [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), wey dem develop together wit [INSEAD](https://www.insead.edu/). * **Classic Machine Learning**, wey well explain for our [Machine Learning for Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners). -* Practical AI applications wey dem build using **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. For dis one, we recommend make you start with Microsoft Learn modules for [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generative AI with Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** and others. -* Specific ML **Cloud Frameworks**, like [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), or [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Abeg try [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) and [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) learning paths. -* **Conversational AI** and **Chat Bots**. E get separate [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) learning path, and you fit also check [dis blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for more detail. -* **Deep Mathematics** behind deep learning. For dis one, we go recommend [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) by Ian Goodfellow, Yoshua Bengio and Aaron Courville, wey e also dey online for [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). +* Practical AI work wey build using **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. For these, we advise say start wit Microsoft Learn modules for [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generative AI with Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** and others. +* Specific ML **Cloud Frameworks**, like [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), or [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Try use [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) and [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) learning paths. +* **Conversational AI** and **Chat Bots**. Dem get separate [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) learning path, plus you fit also check [dis blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for more info. +* **Deep Mathematics** behind deep learning. For this one, we recommend [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) by Ian Goodfellow, Yoshua Bengio and Aaron Courville, wey also dey online at [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -For soft introduction to _AI for Cloud_ topics you fit consider take the [Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) Learning Path. +For soft soft introduction to _AI in the Cloud_ topics, you fit try di [Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) Learning Path. # Content @@ -119,49 +119,49 @@ For soft introduction to _AI for Cloud_ topics you fit consider take the [Get st ## Each lesson contains * Pre-reading material -* Executable Jupyter Notebooks, wey dey often special for di framework (**PyTorch** or **TensorFlow**). Di executable notebook get plenti theoretical material too, so to understand di topic, you go need run at least one version of di notebook (either PyTorch or TensorFlow). -* **Labs** wey dey available for some topics, wey go give you chance to try apply di material wey you don learn for particular problem. -* Some sections dey get links to [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) modules wey dey cover related topics. +* Executable Jupyter Notebooks, wey dey often specific to the framework (**PyTorch** or **TensorFlow**). The executable notebook sef get plenty theoretical material, so to understand the topic you need to go through at least one version of the notebook (either PyTorch or TensorFlow). +* **Labs** wey dey available for some topics, wey go give you chance to try apply wetin you don learn for a specific problem. +* Some sections get links to [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) modules wey cover related topics. ## Getting Started ### 🎯 New to AI? Start Here! -If you never sabi AI at all and you want quick, hands-on examples, check out our [**Beginner-Friendly Examples**](./examples/README.md)! Dem get: +If you dey completely new to AI and you want quick, hands-on examples, check out our [**Beginner-Friendly Examples**](./examples/README.md)! Dem include: - 🌟 **Hello AI World** - Your first AI program (pattern recognition) - 🧠 **Simple Neural Network** - Build neural network from scratch -- 🖼️ **Image Classifier** - Classify images with detailed comments -- 💬 **Text Sentiment** - Analyze positive/negative text +- 🖼️ **Image Classifier** - Classify images wit detailed comments +- 💬 **Text Sentiment** - Analyse positive/negative text -Dem design dis examples to help you sabi AI concepts before you dive inside the full curriculum. +Dem examples dem design to help you sabi AI concepts before you go enter the full curriculum. ### 📚 Full Curriculum Setup -- We don create one [setup lesson](./lessons/0-course-setup/setup.md) to help you set up your development environment. - For Educators, we don create one [curricula setup lesson](./lessons/0-course-setup/for-teachers.md) for you too! -- How to [Run di code for VSCode or Codepace](./lessons/0-course-setup/how-to-run.md) +- We don create [setup lesson](./lessons/0-course-setup/setup.md) to help you setup your development environment. - For Educators, we don create [curricula setup lesson](./lessons/0-course-setup/for-teachers.md) for una too! +- How to [Run the code for VSCode or Codespace](./lessons/0-course-setup/how-to-run.md) Follow these steps: -Fork the Repository: Click on di "Fork" button wey dey top-right corner of dis page. +Fork the Repository: Click the "Fork" button for the top-right corner of dis page. Clone the Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git` -No forget to star (🌟) dis repo make e easy for you to find am later. +No forget to star (🌟) dis repo so e go easy for you to find am later. ## Meet other Learners -Join our [official AI Discord server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) to meet and network with other learners wey dey do dis course and get support. +Join our [official AI Discord server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) to meet and network wit other learners wey dey do dis course and get help. -If you get product feedback or questions while you dey build visit our [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) +If you get product feedback or questions as you dey build, visit our [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) ## Quizzes -> **A note about quizzes**: All quizzes dey inside di Quiz-app folder for etc\quiz-app, or [Online Here](https://ff-quizzes.netlify.app/) Dem link dem from inside the lessons. Di quiz app fit run locally or you fit deploy am go Azure; follow di instruction for di `quiz-app` folder. Dem dey slowly dey localize am. +> **A note about quizzes**: All quizzes dey inside the Quiz-app folder for etc\quiz-app, or [Online Here](https://ff-quizzes.netlify.app/) Dem link from inside the lessons, the quiz app fit run locally or fit deploy for Azure; follow instruction wey dey the `quiz-app` folder. Dem dey slowly dey localize. ## Help Wanted -You get suggestions or you see any spelling or code mistakes? Make you raise issue or create pull request. +You get suggestions or you see spelling or code errors? Raise issue or create pull request. ## Special Thanks @@ -217,7 +217,7 @@ Our team dey produce other curricula! Check am out: ## Getting Help -If you jam problem or you get any question about building AI apps. Join fellow learners and experienced developers for discussions about MCP. Na supportive community wey questions dey welcome and knowledge dey share free. +If you jam wall or get any question about building AI apps. Join other learners and experienced devs for talks about MCP. Na supportive community wey questions dey welcome and dem dey share knowledge freely. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) @@ -229,5 +229,5 @@ If you get product feedback or errors while you dey build, visit: **Disclaimer**: -Dis document don translate wit AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator). Even though we dey try make am accurate, abeg sabi say automated translation fit get some mistakes or no too correct. Di original document for im own language be di correct main source. For important info, e better make person wey sabi human translation do am. We no go take any blame if person misunderstand or misuse dis translation. +Dis document na so AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator) translate am. Even though we dey try make am correct, abeg sabi say automated translations fit get errors or wahala. Make you always trust the original document wey dey the original language as the real correct source. If na important info, e better make person wey sabi do human translation help you. We no go take responsibility if any misunderstanding or wrong meaning show because of this translation. \ No newline at end of file diff --git a/translations/pcm/lessons/0-course-setup/how-to-run.md b/translations/pcm/lessons/0-course-setup/how-to-run.md index 7d667dcc..5681ce39 100644 --- a/translations/pcm/lessons/0-course-setup/how-to-run.md +++ b/translations/pcm/lessons/0-course-setup/how-to-run.md @@ -1,21 +1,21 @@ -# How to Run di Code +# How to Run the Code -Dis curriculum get plenty examples wey you fit run and labs wey you go wan try. To fit do am, you need di ability to run Python code inside Jupyter Notebooks wey dem provide as part of dis curriculum. You get different ways wey you fit take run di code: +Dis curriculum get plenti executable examples and labs wey you go like run. To fit do dis, you need beta skill to execute Python code for Jupyter Notebooks wey dem provide as part of dis curriculum. You get plenty ways to run the code: -## Run am for your computer +## Run locally on your computer -To run di code for your computer, you go need make Python dey installed. I go recommend make you install **[miniconda](https://conda.io/en/latest/miniconda.html)** - e no heavy and e dey support `conda` package manager for different Python **virtual environments**. +To run the code for your computer, you need to get Python installation. One wey we fit recommend na to install **[miniconda](https://conda.io/en/latest/miniconda.html)** - e light well well and e support `conda` package manager for different Python **virtual environments**. -After you don install miniconda, you go need clone di repository and create virtual environment wey you go use for dis course: +After you don install miniconda, clone the repository and create one virtual environment to use for dis course: ```bash git clone http://github.com/microsoft/ai-for-beginners @@ -24,19 +24,19 @@ conda env create --name ai4beg --file .devcontainer/environment.yml conda activate ai4beg ``` -### Use Visual Studio Code with Python Extension +### Using Visual Studio Code with Python Extension -Di best way to use dis curriculum na to open am for [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) with [Python Extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste). +Dis curriculum better pass if you use am inside [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) with [Python Extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste). -> **Note**: Once you don clone and open di directory for VS Code, e go suggest make you install Python extensions. You go also need install miniconda as I don talk before. +> **Note**: Once you clone and open the directory for VS Code, e go automatically remind you to install Python extensions. You go still need to install miniconda as we describe for top. -> **Note**: If VS Code suggest make you re-open di repository inside container, no gree. Use di local Python installation instead. +> **Note**: If VS Code tell you make you re-open the repository for inside container, you suppose no do am, make you fit use local Python installation. -### Use Jupyter for Browser +### Using Jupyter in the Browser -You fit also use Jupyter environment directly from your browser for your computer. Di classical Jupyter and Jupyter Hub dey provide better development environment wey get auto-completion, code highlighting, and di rest. +You fit still use Jupyter environment from your browser for your own computer. Both classical Jupyter and JupyterHub dey provide correct development environment with auto-completion, code highlighting, etc. -To start Jupyter locally, go di directory of di course, then run: +To start Jupyter locally, waka go the directory wey hold the course, then run: ```bash jupyter notebook @@ -45,36 +45,36 @@ or ```bash jupyterhub ``` -You fit then navigate go any `.ipynb` file, open am and start work. +You fit then waka go anybody `.ipynb` files, open dem and start to work. -### Run am inside container +### Running in container -Another way wey you fit run di code na to use container. Since di repository get special `.devcontainer` folder wey dey show how to build container for di repo, VS Code go suggest make you re-open di code inside container. Dis one go need Docker installation, and e dey more complex, so we dey recommend am for people wey don sabi well. +One other way to still run the code no be to install Python, na to run the code inside container. Because our repository get special `.devcontainer` folder wey talk how to build container for dis repo, VS Code go fit help you re-open the code inside container. Dis one require say you get Docker installed, and e still dey complex pass, so we recommend am only to people wey sabi well well. -## Run am for Cloud +## Running in the Cloud -If you no wan install Python for your computer, and you get access to cloud resources - one better option na to run di code for cloud. You get different ways wey you fit do am: +If you no want install Python for your own computer, and you get access to cloud resources - one better way na to run the code for cloud. You get plenty ways to do am: -* Use **[GitHub Codespaces](https://github.com/features/codespaces)**, wey be virtual environment wey GitHub go create for you, wey you fit access through VS Code browser interface. If you get access to Codespaces, just click **Code** button for di repo, start codespace, and begin dey run am sharp sharp. -* Use **[Binder](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)**. [Binder](https://mybinder.org) na free computing resources wey dey cloud for people wey wan test code for GitHub. You go see button for di front page to open di repository for Binder - e go carry you go di Binder site, wey go build di container and start Jupyter web interface for you without wahala. +* Use **[GitHub Codespaces](https://github.com/features/codespaces)**, wey be virtual environment wey dem create for you on top GitHub, and you fit use VS Code browser interface take access am. If you fit use Codespaces, you fit just click **Code** button for the repo, start codespace, and run am sharp sharp. +* Use **[Binder](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)**. [Binder](https://mybinder.org) dey offer free computer resources for cloud so people like you fit try run code from GitHub. For the front page, dem get button wey make you fit open the repo for Binder - dis one go take you go the binder site quick, wey go build container and start Jupyter web interface for you without wahala. -> **Note**: To stop misuse, Binder dey block access to some web resources. Dis fit make some code wey dey fetch models and/or datasets from public Internet no work. You go need find workaround. Also, di compute resources wey Binder dey provide no too strong, so training go slow, especially for di later lessons wey dey more complex. +> **Note**: To stop misuse, Binder block some web resources. Dis one fit make some code no work, especially if the code dey fetch models and/or datasets from public Internet. You fit need find way workaround. Also, the compute resources wey Binder get, simple, so training go slow, especially for the later, more complex lessons. -## Run am for Cloud with GPU +## Running in the Cloud with GPU -Some of di later lessons for dis curriculum go need GPU support, because if GPU no dey, training go slow well well. You get some options wey you fit follow, especially if you get access to cloud through [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste), or through your institution: +Some of the later lessons for dis curriculum go beta if dem get GPU support. Model training fit slow no GPU. You fit follow some options if you get cloud access through [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste), or from your school: -* Create [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) and connect am through Jupyter. You fit then clone di repo directly for di machine, and start dey learn. NC-series VMs get GPU support. +* Create [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) and connect to am through Jupyter. You fit then clone the repo enter inside the machine, and start to learn. NC-series VMs get GPU support. -> **Note**: Some subscriptions, including Azure for Students, no dey provide GPU support straight. You fit need request extra GPU cores through technical support. +> **Note**: Some subscriptions, including Azure for Students, no dey come with GPU support straight. You go need check to add GPU cores with technical support request. -* Create [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) and use di Notebook feature wey dey there. [Dis video](https://azure-for-academics.github.io/quickstart/azureml-papers/) dey show how to clone repository into Azure ML notebook and start dey use am. +* Create [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste), then use Notebook feature for there. [Dis video](https://azure-for-academics.github.io/quickstart/azureml-papers/) show how to clone repository enter Azure ML notebook and start to use am. -You fit also use Google Colab, wey dey come with free GPU support, and upload Jupyter Notebooks there to run dem one by one. +You fit still use Google Colab, wey get some free GPU support, and upload Jupyter Notebooks there take run dem one by one. --- -**Disclaimer**: -Dis dokyument don use AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator) do di translation. Even as we dey try make am accurate, abeg sabi say automated translations fit get mistake or no dey correct well. Di original dokyument for im native language na di main source wey you go fit trust. For important information, e good make professional human translation dey use. We no go fit take blame for any misunderstanding or wrong interpretation wey fit happen because you use dis translation. +**Warning**: +Dis document na translation wey AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator) do. Even though we try make am correct, make you sabi say automated translation fit get some mistakes or wahala. Di original document wey dey dia own language na di correct one. For important matter, e better make professional human person translate am. We no go responsible for any wrong understand or mix-up wey fit happen because of dis translation. \ No newline at end of file diff --git a/translations/pcm/lessons/1-Intro/README.md b/translations/pcm/lessons/1-Intro/README.md index 7b8306b9..3dcc69a1 100644 --- a/translations/pcm/lessons/1-Intro/README.md +++ b/translations/pcm/lessons/1-Intro/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Introduction to AI -![Summary of Introduction of AI content in a doodle](../../../../translated_images/ai-intro.bf28d1ac4235881c.pcm.png) +![Summary of Introduction of AI content in a doodle](../../../../translated_images/pcm/ai-intro.bf28d1ac4235881c.webp) > Sketchnote by [Tomomi Imura](https://twitter.com/girlie_mac) @@ -19,7 +19,7 @@ CO_OP_TRANSLATOR_METADATA: Before before, na [Charles Babbage](https://en.wikipedia.org/wiki/Charles_Babbage) invent computer to dey work with numbers follow one clear process - wey dem dey call algorithm. Modern computer don advance pass the one wey dem propose for 19th century, but e still dey follow the same idea of controlled calculations. So e possible to program computer to do something if we sabi the exact steps wey we need to follow to reach the goal. -![Photo of a person](../../../../translated_images/dsh_age.d212a30d4e54fb5f.pcm.png) +![Photo of a person](../../../../translated_images/pcm/dsh_age.d212a30d4e54fb5f.webp) > Photo by [Vickie Soshnikova](http://twitter.com/vickievalerie) @@ -45,7 +45,7 @@ For more information check **[Artificial General Intelligence](https://en.wikipe One problem wey dey when we dey talk about **[Intelligence](https://en.wikipedia.org/wiki/Intelligence)** na say we no get clear definition of the word. Some people fit talk say intelligence dey connected to **abstract thinking**, or **self-awareness**, but we no fit define am well. -![Photo of a Cat](../../../../translated_images/photo-cat.8c8e8fb760ffe457.pcm.jpg) +![Photo of a Cat](../../../../translated_images/pcm/photo-cat.8c8e8fb760ffe457.webp) > [Photo](https://unsplash.com/photos/75715CVEJhI) by [Amber Kipp](https://unsplash.com/@sadmax) from Unsplash @@ -97,13 +97,13 @@ Another way na to model the simplest part of our brain – neuron. We fit build > | Wetin about ML? | | > |--------------|-----------| -> | Part of Artificial Intelligence wey dey base on computer learning to solve problem from data na **Machine Learning**. We no go talk about classical machine learning for this course - we dey refer you to separate [Machine Learning for Beginners](http://aka.ms/ml-beginners) curriculum. | ![ML for Beginners](../../../../translated_images/ml-for-beginners.9e4fed176fd5817d.pcm.png) | +> | Part of Artificial Intelligence wey dey base on computer learning to solve problem from data na **Machine Learning**. We no go talk about classical machine learning for this course - we dey refer you to separate [Machine Learning for Beginners](http://aka.ms/ml-beginners) curriculum. | ![ML for Beginners](../../../../translated_images/pcm/ml-for-beginners.9e4fed176fd5817d.webp) | ## A Brief History of AI Artificial Intelligence start as field for middle of twentieth century. At first, symbolic reasoning na the main approach, and e lead to some important success, like expert systems – computer programs wey fit act like expert for small problem areas. But e later clear say this approach no dey scale well. To take knowledge from expert, put am inside computer, and keep the knowledgebase correct dey very hard, and e too expensive for many cases. This lead to [AI Winter](https://en.wikipedia.org/wiki/AI_winter) for 1970s. -Brief History of AI +Brief History of AI > Image by [Dmitry Soshnikov](http://soshnikov.com) @@ -123,7 +123,7 @@ Same way, we fit see how approach for creating “talking programs” (wey fit p * Modern assistants like Cortana, Siri or Google Assistant na hybrid systems wey dey use Neural networks to change speech to text and understand wetin we want, then use reasoning or direct algorithms to do wetin we need. * For future, we fit expect complete neural-based model wey go handle talk by itself. The recent GPT and [Turing-NLG](https://www.microsoft.com/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft) family of neural networks dey show big success for this. -the Turing test's evolution +the Turing test's evolution > Foto by Dmitry Soshnikov, [foto](https://unsplash.com/photos/r8LmVbUKgns) by [Marina Abrosimova](https://unsplash.com/@abrosimova_marina_foto), Unsplash ## Recent AI Research diff --git a/translations/pcm/lessons/2-Symbolic/Animals.ipynb b/translations/pcm/lessons/2-Symbolic/Animals.ipynb index 7d819059..270b3088 100644 --- a/translations/pcm/lessons/2-Symbolic/Animals.ipynb +++ b/translations/pcm/lessons/2-Symbolic/Animals.ipynb @@ -6,13 +6,13 @@ "collapsed": true }, "source": [ - "# How to Make Animal Expert System\n", + "# Implementing an Animal Expert System\n", "\n", - "Example wey come from [AI for Beginners Curriculum](http://github.com/microsoft/ai-for-beginners).\n", + "An example from [AI for Beginners Curriculum](http://github.com/microsoft/ai-for-beginners).\n", "\n", - "For dis sample, we go make one simple knowledge-based system wey go fit tell which animal e be based on some physical characteristics. Dis system fit dey show as dis AND-OR tree (na just part of the whole tree, we fit add more rules join am):\n", + "For dis sample, we go implement one simple knowledge-based system wey go fit know animal based on some physical characteristics. Di system fit show for dis AND-OR tree wey dey below (dis na part of di whole tree, we fit easily add some more rules):\n", "\n", - "![](../../../../translated_images/AND-OR-Tree.5592d2c70187f283.pcm.png)\n" + "![](../../../../../../translated_images/pcm/AND-OR-Tree.5592d2c70187f283.webp)\n" ] }, { @@ -21,10 +21,10 @@ "source": [ "## Our own expert systems shell wit backward inference\n", "\n", - "Make we try define one simple language wey go represent knowledge based on production rules. We go use Python classes as keywords to take define rules. E go get basically 3 types of classes:\n", - "* `Ask` na question wey we go need ask user. E get di set of possible answers.\n", - "* `If` na rule, and e just be like syntactic sugar to store di content of di rule\n", - "* `AND`/`OR` na classes to represent AND/OR branches for di tree. Dem just dey store di list of arguments inside. To make code simple, all di functionality dey defined for di parent class `Content`\n" + "Make we try define simple language for knowledge representation based on production rules. We go use Python classes as keywords to define rules. E go basically get 3 kain classes:\n", + "* `Ask` mean question wey you need ask user. E get set of possible answers inside.\n", + "* `If` mean rule, and e just be syntactic sugar to store wetin dey inside the rule\n", + "* `AND`/`OR` na classes to represent AND/OR branches of the tree. Dem just dey store list of arguments wey dem get inside. To make code simple, all functionality dey defined for parent class `Content`\n" ] }, { @@ -66,7 +66,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "For our system, di working memory go contain di list of **facts** as **attribute-value pairs**. Di knowledgebase fit be define as one big dictionary wey dey map actions (new facts wey suppose enter di working memory) to conditions, wey dem dey express as AND-OR expressions. Also, some facts fit be `Ask`-ed.\n" + "For we system, working memory go get list of **facts** as **attribute-value pairs**. The knowledgebase fit be defined as one big dictionary wey dey map actions (new facts wey suppose enter working memory) to conditions, wey dem express as AND-OR expressions. Also, some facts fit dey `Ask`-ed.\n" ] }, { @@ -99,13 +99,13 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "To do backward inference, we go define `Knowledgebase` class. E go get:\n", + "To perform the backward inference, we go define `Knowledgebase` class. E go contain:\n", "* Working `memory` - na dictionary wey dey map attributes to values\n", - "* Knowledgebase `rules` for di format wey we don define before\n", + "* Knowledgebase `rules` for the format wey dem don define above\n", "\n", "Two main methods na:\n", - "* `get` to fit collect di value of one attribute, e go do inference if e need am. For example, `get('color')` go collect di value of one color slot (e go ask if e need am, and e go keep di value for later use for di working memory). If we ask `get('color:blue')`, e go ask for color, then e go return `y`/`n` value based on di color.\n", - "* `eval` dey do di main inference work, e dey waka through AND/OR tree, dey check sub-goals, etc.\n" + "* `get` to obtain the value of an attribute, dey perform inference if e necessary. For example, `get('color')` go get value of color slot (e go ask if e necessary, then e go store the value for later use inside the working memory). If we ask `get('color:blue')`, e go ask for color, then e go return `y`/`n` value depending on the color.\n", + "* `eval` dey perform the real inference, like dey waka inside AND/OR tree, dey evaluate sub-goals, etc.\n" ] }, { @@ -172,7 +172,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Make we define our animal knowledgebase and do di consultation. Note say dis call go ask you questions. You fit answer by typing `y`/`n` for yes-no questions, or by giving number (0..N) for questions wey get longer multiple-choice answers.\n" + "Now make we define our animal knowledgebase and perform the consultation. Note say dis call go ask you questions. You fit answer by typing `y`/`n` for yes-no questions, or by specifying number (0..N) for questions wey get longer multiple-choice answers.\n" ] }, { @@ -229,11 +229,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## How to Use PyKnow for Forward Inference\n", + "## Using Experta for Forward Inference\n", "\n", - "For dis next example, we go try use one library wey dey for knowledge representation, [PyKnow](https://github.com/buguroo/pyknow/). **PyKnow** na one library wey dey help us create forward inference systems for Python, and e dey work like one old classical system wey dem dey call [CLIPS](http://www.clipsrules.net/index.html).\n", + "For di next example, we go try implement forward inference using one of di libraries for knowledge representation, [Experta](https://github.com/nilp0inter/experta). **Experta** na library for creating forward inference systems for Python, wey dem design to be similar to classical old system [CLIPS](http://www.clipsrules.net/index.html).\n", "\n", - "We fit don do forward chaining by ourselves without too much wahala, but di simple way wey person go do am no dey too efficient. To make rule matching better, dem dey use one special algorithm wey dem dey call [Rete](https://en.wikipedia.org/wiki/Rete_algorithm).\n" + "We fit don implement forward chaining by ourself without many wahala, but naive implementations na usually no too efficient. For more better rule matching, one special algorithm [Rete](https://en.wikipedia.org/wiki/Rete_algorithm) dey used.\n" ] }, { @@ -247,32 +247,31 @@ "name": "stdout", "output_type": "stream", "text": [ - "Collecting git+https://github.com/buguroo/pyknow/\n", - " Cloning https://github.com/buguroo/pyknow/ to /tmp/pip-req-build-3cqeulyl\n", - " Running command git clone --filter=blob:none --quiet https://github.com/buguroo/pyknow/ /tmp/pip-req-build-3cqeulyl\n", - " Resolved https://github.com/buguroo/pyknow/ to commit 48818336f2e9a126f1964f2d8dc22d37ff800fe8\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting frozendict==1.2\n", - " Using cached frozendict-1.2.tar.gz (2.6 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting schema==0.6.7\n", - " Using cached schema-0.6.7-py2.py3-none-any.whl (14 kB)\n", - "Building wheels for collected packages: pyknow, frozendict\n", - " Building wheel for pyknow (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for pyknow: filename=pyknow-1.7.0-py3-none-any.whl size=34228 sha256=b7de5b09292c4007667c72f69b98d5a1b5f7324ff15f9dd8e077c3d5f7aade42\n", - " Stored in directory: /tmp/pip-ephem-wheel-cache-k7jpave7/wheels/81/1a/d3/f6c15dbe1955598a37755215f2a10449e7418500d7bd4b9508\n", - " Building wheel for frozendict (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for frozendict: filename=frozendict-1.2-py3-none-any.whl size=3148 sha256=2863d55c240d2409cddf05ccfe600591f8478681549fc97555c47c90dc6bb160\n", - " Stored in directory: /home/rg/.cache/pip/wheels/49/ac/f8/cb8120244e710bdb479c86198b03c7b08c3c2d3d2bf448fd6e\n", - "Successfully built pyknow frozendict\n", - "Installing collected packages: schema, frozendict, pyknow\n", - "Successfully installed frozendict-1.2 pyknow-1.7.0 schema-0.6.7\n" + "Collecting git+https://github.com/nilp0inter/experta\n", + " Cloning https://github.com/nilp0inter/experta to /tmp/pip-req-build-7qurtwk3\n", + " Running command git clone --filter=blob:none --quiet https://github.com/nilp0inter/experta /tmp/pip-req-build-7qurtwk3\n", + " Resolved https://github.com/nilp0inter/experta to commit c6d5834b123861f5ae09e7d07027dc98bec58741\n", + " Installing build dependencies ... \u001b[?25ldone\n", + "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n", + "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25hRequirement already satisfied: frozendict~=2.4.6 in /opt/conda/envs/ai4beg/lib/python3.12/site-packages (from experta==1.9.5.dev1) (2.4.7)\n", + "Collecting schema~=0.6.7 (from experta==1.9.5.dev1)\n", + " Downloading schema-0.6.8-py2.py3-none-any.whl.metadata (14 kB)\n", + "Downloading schema-0.6.8-py2.py3-none-any.whl (14 kB)\n", + "Building wheels for collected packages: experta\n", + " Building wheel for experta (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25h Created wheel for experta: filename=experta-1.9.5.dev1-py3-none-any.whl size=34804 sha256=888c459512a5e713f4b674caa9a0f96cfdf07ec0d6eb56cc318ce0653d218014\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-1eeii9zy/wheels/3d/e8/bb/22d7956359603fa8dd679aa09f5b8efb3f29991c3986fdc787\n", + "Successfully built experta\n", + "Installing collected packages: schema, experta\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [experta]\n", + "\u001b[1A\u001b[2KSuccessfully installed experta-1.9.5.dev1 schema-0.6.8\n" ] } ], "source": [ "import sys\n", - "!{sys.executable} -m pip install git+https://github.com/buguroo/pyknow/" + "!{sys.executable} -m pip install git+https://github.com/nilp0inter/experta" ] }, { @@ -283,15 +282,15 @@ }, "outputs": [], "source": [ - "from pyknow import *\n", - "#import pyknow" + "from experta import *\n", + "#import experta" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "We go define our system as one class wey dey subclass `KnowledgeEngine`. Each rule go dey defined by one separate function wey get `@Rule` annotation, wey go specify when the rule go fire. Inside the rule, we fit add new facts using `declare` function, and as we add those facts, e go make some more rules dey called by forward inference engine.\n" + "We go define our system as a class wey dey subclass `KnowledgeEngine`. Every rule na another function wey get `@Rule` annotation, wey show when the rule suppose fire. Inside the rule, we fit add new facts using `declare` function, and wen we add those facts, e go make some more rules call by forward inference engine.\n" ] }, { @@ -378,7 +377,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Once we don define di knowledgebase, we go put some initial facts for our working memory, den we go call `run()` method to do di inference. You fit see say new facts wey dem infer go dey add to di working memory, including di final fact about di animal (if we set all di initial facts correct).\n" + "Once we don define one knowledgebase, we go put some initial facts for our working memory, then we go call `run()` method to carry out the inference. You go fit see as result say new inferred facts don add join the working memory, including the final fact about the animal (if we set up all the initial facts correct).\n" ] }, { @@ -440,7 +439,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "---\n\n\n**Disclaimer**: \nDis dokyument don use AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator) do di translation. Even as we dey try make am accurate, abeg make you sabi say automated translations fit get mistake or no dey correct well. Di original dokyument for di language wey dem write am first na di main source wey you go fit trust. For important information, e good make professional human translation dey use. We no go fit take blame for any misunderstanding or wrong interpretation wey fit happen because you use dis translation.\n\n" + "---\n\n\n**Disclaimer**: \nDis document don translate wit AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator). Even though we try make e accurate, abeg make you sabi say automated translations fit get mistakes or wrong meaning. Di original document wey e dey for im own language na di main one wey get authority. If na serious information, make you use professional human translator. We no go hold ourselves responsible if misunderstanding or wrong interpretation happen because of dis translation.\n\n" ] } ], @@ -467,8 +466,8 @@ "version": "3.11.2" }, "coopTranslator": { - "original_hash": "ab2bd97b0453415b89a469284609a8ce", - "translation_date": "2025-11-18T19:21:58+00:00", + "original_hash": "8ef43db4b9182239fd150a76bd494fdb", + "translation_date": "2026-01-16T07:21:06+00:00", "source_file": "lessons/2-Symbolic/Animals.ipynb", "language_code": "pcm" } diff --git a/translations/pcm/lessons/2-Symbolic/README.md b/translations/pcm/lessons/2-Symbolic/README.md index cf69b830..58f50a18 100644 --- a/translations/pcm/lessons/2-Symbolic/README.md +++ b/translations/pcm/lessons/2-Symbolic/README.md @@ -1,62 +1,62 @@ # Knowledge Representation and Expert Systems -![Summary of Symbolic AI content](../../../../translated_images/ai-symbolic.715a30cb610411a6.pcm.png) +![Summary of Symbolic AI content](../../../../../../translated_images/pcm/ai-symbolic.715a30cb610411a6.webp) > Sketchnote by [Tomomi Imura](https://twitter.com/girlie_mac) -Di waka for artificial intelligence na di search for knowledge, to sabi di world like how humans dey do am. But how pesin go fit do dis one? +Di waka wey dem de find for artificial intelligence na based on search for knowledge, to make sense of di world like how humans de do am. But how you fit take do am? ## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/3) -For di early days of AI, di top-down way to create intelligent systems (we talk am for di last lesson) dey popular. Di idea na to collect di knowledge wey dey people head put am for machine-readable form, den use am solve problems automatically. Dis way dey base on two big ideas: +For di early days of AI, di top-down way of making intelligent systems (wey we talk for di previous lesson) de popular. Di idea na to comot knowledge from people enter some machine-readable form, then use am to automatically solve problems. Dis approach get two big ideas: * Knowledge Representation * Reasoning ## Knowledge Representation -One important thing for Symbolic AI na **knowledge**. E dey important to sabi di difference between knowledge and *information* or *data*. For example, pesin fit talk say books get knowledge, because pesin fit study di books become expert. But wetin dey inside books na actually *data*, and as we dey read di books and put di data for our world model, na so we dey turn di data to knowledge. +One of di important tins for Symbolic AI na **knowledge**. E important to know di difference between knowledge and *information* or *data*. For example, you fit talk sey books get knowledge, because person fit study books and become expert. But wetin books get na *data*, and by reading books and add dis data to our world model, we dey convert dat data to knowledge. -> ✅ **Knowledge** na wetin dey our head wey show how we sabi di world. We dey get am through active **learning** process, wey dey join di information wey we collect into di model of di world wey dey our head. +> ✅ **Knowledge** na wetin dey inside our head wey represent how we understand di world. E dey come through active **learning** process, wey join pieces of information wey we receive into our active model of di world. -Most times, we no dey define knowledge strictly, but we dey align am with other related ideas using [DIKW Pyramid](https://en.wikipedia.org/wiki/DIKW_pyramid). Di pyramid get di following ideas: +Most times, we no define knowledge sharp-sharp, but we dey relate am to other related concepts using [DIKW Pyramid](https://en.wikipedia.org/wiki/DIKW_pyramid). E get dis tins: -* **Data** na wetin dey physical media, like written text or spoken words. Data dey exist on its own, e no need human beings and e fit pass from one pesin to another. -* **Information** na how we dey understand di data for our head. For example, if we hear di word *computer*, we go get some idea of wetin e mean. -* **Knowledge** na di information wey don enter our world model. For example, once we sabi wetin computer be, we go start get idea of how e dey work, how much e go cost, and wetin we fit use am do. Dis network of connected ideas na di knowledge wey we get. -* **Wisdom** na di next level of how we sabi di world, e dey represent *meta-knowledge*, like how and when we suppose use di knowledge. +* **Data** na tins wey dem represent for physical media, like written text or spoken words. Data dey exist independent from people and fit pass from one person to another. +* **Information** na how we take interpret data for our head. For example, when we hear di word *computer*, we get some understanding of wetin e be. +* **Knowledge** na information wey don join our world model. For example, once we learn wetin computer be, we dey get some idea about how e dey work, how much e dey cost, and wetin e fit dey used for. Dis network of related concepts na our knowledge. +* **Wisdom** na another level of our understanding of di world, and e mean *meta-knowledge*, eg. some understanding of how and when knowledge suppose dey used. - + *Image [from Wikipedia](https://commons.wikimedia.org/w/index.php?curid=37705247), By Longlivetheux - Own work, CC BY-SA 4.0* -So, di problem of **knowledge representation** na to find better way to represent knowledge inside computer as data, so e go fit dey useful automatically. We fit see am as spectrum: +So, di problem of **knowledge representation** na to find how to effectively represent knowledge inside computer as data, to make am automatically usable. E fit be like spectrum: -![Knowledge representation spectrum](../../../../translated_images/knowledge-spectrum.b60df631852c0217.pcm.png) +![Knowledge representation spectrum](../../../../../../translated_images/pcm/knowledge-spectrum.b60df631852c0217.webp) > Image by [Dmitry Soshnikov](http://soshnikov.com) -* For di left side, we get very simple types of knowledge representations wey computers fit use well. Di simplest one na algorithmic, where knowledge dey represented by computer program. But dis one no be di best way to represent knowledge, because e no dey flexible. Knowledge for our head no dey always follow algorithm. -* For di right side, we get representations like natural text. E strong well, but e no fit dey used for automatic reasoning. +* For di left, na simple types of knowledge representations wey computer fit use well. Di simplest one na algorithmic, wey mean knowledge dey inside computer program. But dis no be di best way to represent knowledge because e no flexible. Knowledge inside our head no too get algorithm. +* For di right, na representations like natural text. E powerful pass, but you no fit use am for automatic reasoning. -> ✅ Think small about how you dey represent knowledge for your head and turn am to notes. You get any format wey dey work well for you to help you remember? +> ✅ Think small about how you de represent knowledge inside your head and how you take turn am to notes. You get one particular format wey dey help you remember well? ## Classifying Computer Knowledge Representations -We fit divide di different computer knowledge representation methods into di following categories: +We fit classify different computer knowledge representation methods into dis categories: -* **Network representations** dey base on di fact say we get network of connected ideas for our head. We fit try reproduce di same network as graph inside computer - di one wey dem dey call **semantic network**. +* **Network representations** dey based on di fact sey we get network of related concepts inside our head. We fit try reproduce di same networks as graph inside computer - na so called **semantic network**. -1. **Object-Attribute-Value triplets** or **attribute-value pairs**. Since graph fit dey represented inside computer as list of nodes and edges, we fit represent semantic network as list of triplets, wey get objects, attributes, and values. For example, we fit build di following triplets about programming languages: +1. **Object-Attribute-Value triplets** or **attribute-value pairs**. Because graph fit represent inside computer as list of nodes and edges, we fit represent semantic network by list of triplets, wey get objects, attributes, and values. For example, we go build dis triplets on programming languages: Object | Attribute | Value -------|-----------|------ @@ -65,12 +65,12 @@ Python | invented-by | Guido van Rossum Python | block-syntax | indentation Untyped-Language | doesn't have | type definitions -> ✅ Think how triplets fit dey used to represent other types of knowledge. +> ✅ Think how triplets fit take represent other kinds of knowledge. -2. **Hierarchical representations** dey show say we dey often create hierarchy of objects for our head. For example, we sabi say canary na bird, and all birds get wings. We also get idea of di colour wey canary dey usually be, and di speed wey dem dey fly. +2. **Hierarchical representations** emphasize sey we dey create hierarchy of objects inside our head. For example, we know sey canary na bird, and all birds get wings. We also get idea about wetin color canary usually be, and wetin their flight speed be. - - **Frame representation** dey base on di idea say we fit represent each object or class of objects as **frame** wey get **slots**. Slots fit get default values, value restrictions, or stored procedures wey fit dey called to get di value of di slot. All di frames dey form hierarchy like object hierarchy for object-oriented programming languages. - - **Scenarios** na special type of frames wey dey represent complex situations wey fit happen over time. + - **Frame representation** na to represent each object or class of object as **frame** wey get **slots**. Slots fit get default values, value restrictions, or stored procedures wey you fit call to get di slot value. All frames make hierarchy like object hierarchy for object-oriented programming languages. + - **Scenarios** na special frames wey represent complex situations wey fit happen over time. **Python** @@ -82,35 +82,35 @@ Variable Case | | CamelCase | | Program Length | | | 5-5000 lines | Block Syntax | Indent | | | -3. **Procedural representations** dey base on di idea say we fit represent knowledge as list of actions wey fit dey executed when certain condition happen. - - Production rules na if-then statements wey dey allow us draw conclusions. For example, doctor fit get rule wey talk say **IF** patient get high fever **OR** high level of C-reactive protein for blood test **THEN** e get inflammation. Once we see one of di conditions, we fit conclude say e get inflammation, and use am for further reasoning. - - Algorithms fit dey considered as another type of procedural representation, but dem no dey almost ever used directly for knowledge-based systems. +3. **Procedural representations** dey based on representing knowledge as list of actions wey you fit do when condition happen. + - Production rules na if-then statements wey dey allow us draw conclusion. For example, doctor fit get rule sey **IF** patient get high fever **OR** high level of C-reactive protein for blood test **THEN** e get inflammation. Once one of condition show, we fit conclude inflammation dey, then use am for further reasoning. + - Algorithms fit be another kind procedural representation, although dem no dey use am direct for knowledge-based systems. -4. **Logic** na wetin Aristotle propose as way to represent universal human knowledge. - - Predicate Logic as mathematical theory too rich to dey computable, so dem dey usually use subset of am, like Horn clauses wey dem dey use for Prolog. - - Descriptive Logic na family of logical systems wey dem dey use to represent and reason about hierarchies of objects distributed knowledge representations like *semantic web*. +4. **Logic** Aristotle originally propose am as way to represent universal human knowledge. + - Predicate Logic as mathematical theory too rich to be computable, so dem dey use subset of am, like Horn clauses wey dem dey use for Prolog. + - Descriptive Logic na family of logical systems used to represent and reason about hierarchies of objects inside distributed knowledge representations like *semantic web*. ## Expert Systems -One of di early success of symbolic AI na di **expert systems** - computer systems wey dem design to act like expert for some small problem area. Dem dey base on **knowledge base** wey dem collect from one or more human experts, and dem get **inference engine** wey dey perform reasoning on top. +One of early successes of symbolic AI na the so-called **expert systems** - computer systems wey dem design to act like expert inside limited problem domain. Dem dey based on **knowledge base** wey dem comot from one or more human experts, and e get **inference engine** wey dey reason on top am. -![Human Architecture](../../../../translated_images/arch-human.5d4d35f1bba3ab1c.pcm.png) | ![Knowledge-Based System](../../../../translated_images/arch-kbs.3ec5c150b09fa8da.pcm.png) +![Human Architecture](../../../../../../translated_images/pcm/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../../../translated_images/pcm/arch-kbs.3ec5c150b09fa8da.webp) ---------------------------------------------|------------------------------------------------ Simplified structure of a human neural system | Architecture of a knowledge-based system -Expert systems dey build like human reasoning system, wey get **short-term memory** and **long-term memory**. For knowledge-based systems, we dey divide di components like dis: +Expert systems be like human reasoning system, wey get **short-term memory** and **long-term memory**. Same way, for knowledge-based systems we get these components: -* **Problem memory**: e dey hold di knowledge about di problem wey we dey solve now, like di temperature or blood pressure of patient, whether e get inflammation or not, etc. Dis knowledge na **static knowledge**, because e dey show snapshot of wetin we sabi about di problem - di *problem state*. -* **Knowledge base**: e dey represent long-term knowledge about di problem area. Dem dey collect am manually from human experts, and e no dey change from one consultation to another. Because e dey help us move from one problem state to another, dem dey call am **dynamic knowledge**. -* **Inference engine**: e dey control di whole process of searching di problem state space, dey ask user questions when e need. E dey also find di correct rules to apply for each state. +* **Problem memory**: get knowledge about di problem wey dem dey try solve now, like temperature or blood pressure of patient, whether e get inflammation or no, etc. Dis knowledge also dey called **static knowledge**, because e show wetin we currently know about di problem - di so-called *problem state*. +* **Knowledge base**: represent long-term knowledge about problem domain. E dey come from human experts manual, and no dey change from consultation to consultation. Because e allow us shift from one problem state to another, e also dey called **dynamic knowledge**. +* **Inference engine**: na e dey control di whole process of searching problem state space, dey ask questions to user when necessary. E also dey responsible to find right rules to apply to each state. -Example, make we look di expert system wey dey determine animal based on di physical characteristics: +Example, make we check dis expert system for identifying animal based on physical characteristics: -![AND-OR Tree](../../../../translated_images/AND-OR-Tree.5592d2c70187f283.pcm.png) +![AND-OR Tree](../../../../../../translated_images/pcm/AND-OR-Tree.5592d2c70187f283.webp) > Image by [Dmitry Soshnikov](http://soshnikov.com) -Dis diagram na **AND-OR tree**, e dey show di graphical representation of set of production rules. To draw tree dey useful for di beginning when we dey collect knowledge from di expert. To represent di knowledge inside computer, e better to use rules: +Dis diagram na **AND-OR tree**, and e be graphical representation of production rules set. To draw tree na better way when you dey comot knowledge from expert. But to represent knowledge inside computer, better to use rules: ``` IF the animal eats meat @@ -121,78 +121,78 @@ OR (animal has sharp teeth THEN the animal is a carnivore ``` -You fit notice say each condition for di left-hand-side of di rule and di action na basically object-attribute-value (OAV) triplets. **Working memory** dey hold di set of OAV triplets wey match di problem we dey solve now. **Rules engine** dey look for rules wey condition dey satisfied and apply dem, dey add another triplet to di working memory. +You fit see sey each condition for left side of rule and action na object-attribute-value (OAV) triplets. **Working memory** get OAV triplets wey represent problem wey dem dey solve. **Rules engine** dey find rules wey condition don satisfy and e dey apply dem, dey add new triplet to working memory. -> ✅ Try write your own AND-OR tree for any topic wey you like! +> ✅ Make your own AND-OR tree on any topic wey you like! ### Forward vs. Backward Inference -Di process wey we describe above na **forward inference**. E dey start with some initial data about di problem wey dey di working memory, den e dey follow dis reasoning loop: +The process wey we talk about na **forward inference**. E start with initial data about problem wey dey working memory, then e dey do dis reasoning loop: -1. If di target attribute dey di working memory - stop and give di result -2. Look for all di rules wey condition dey satisfied - get **conflict set** of rules. -3. Do **conflict resolution** - choose one rule wey go dey executed for dis step. Different conflict resolution strategies dey: - - Choose di first rule wey fit work for di knowledge base - - Choose random rule - - Choose di *more specific* rule, wey dey meet di most conditions for di "left-hand-side" (LHS) -4. Apply di rule wey you choose and add new knowledge to di problem state +1. If target attribute dey working memory - stop and give result +2. Find all rules wey condition don satisfy - get **conflict set** of rules. +3. Do **conflict resolution** - pick one rule wey go run now. Different conflict resolution strategies fit dey: + - Pick first applicable rule inside knowledge base + - Pick rule randomly + - Pick *more specific* rule, i.e. one wey meet most conditions for left side (LHS) +4. Apply selected rule and add new knowledge to problem state 5. Repeat from step 1. -But sometimes we fit want start with empty knowledge about di problem, and dey ask questions wey go help us reach di conclusion. For example, for medical diagnosis, we no dey do all di medical tests before we start diagnose di patient. We go prefer do di tests when decision need to dey made. +But sometimes, we fit wan start with empty knowledge about problem, then ask questions to help reach conclusion. For example, for medical diagnosis, we no dey do all medical tests before we start diagnosis. We like do test when decision must make. -Dis process fit dey modeled using **backward inference**. E dey driven by di **goal** - di attribute value wey we dey find: +Dis process fit model as **backward inference**. E dey driven by **goal** - di attribute value wey we want find: -1. Choose all di rules wey fit give us di value of di goal (i.e. di goal dey di RHS ("right-hand-side")) - conflict set -1. If no rules dey for dis attribute, or rule dey wey talk say we suppose ask di user - ask di user, if not: -1. Use conflict resolution strategy to choose one rule wey we go use as *hypothesis* - we go try prove am -1. Repeat di process for all di attributes for di LHS of di rule, dey try prove dem as goals -1. If di process fail at any point - use another rule for step 3. +1. Pick all rules wey fit give us goal value (i.e. goal dey RHS ("right-hand-side")) - conflict set +1. If no rule for dis attribute, or one rule talk sey make we ask user for value - ask am, else: +1. Use conflict resolution to pick one rule wey we go take as *hypothesis* - we go try prove am +1. Recursively repeat process for all attributes for LHS of rule, try prove dem as goals +1. If any time dis process fail - try another rule for step 3. -> ✅ For which situations forward inference dey better? How about backward inference? +> ✅ For which situations forward inference better? How about backward inference? ### Implementing Expert Systems -We fit implement expert systems using different tools: +Expert systems fit implement with different tools: -* Program dem directly for some high level programming language. Dis no be di best idea, because di main advantage of knowledge-based system na say knowledge dey separate from inference, and di expert for di problem area suppose fit write rules without sabi di details of di inference process. -* Use **expert systems shell**, i.e. system wey dem design specially to dey filled with knowledge using some knowledge representation language. +* Programming dem direct with high-level programming language. But dis no be best idea because main advantage of knowledge-based system na separation of knowledge from inference, and person wey sabi problem domain fit write rules without understanding inference details +* Use **expert systems shell**, i.e. system specially designed to be filled with knowledge with some knowledge representation language. ## ✍️ Exercise: Animal Inference -Check [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb) for example of how to implement forward and backward inference expert system. +See [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb) for example wey show how to implement forward and backward inference expert system. -> **Note**: Dis example dey simple, e just dey show how expert system dey look like. Once you start dey create dis kind system, you go only notice some *intelligent* behaviour from am once you get plenty rules, like 200+. At one point, di rules go too complex to keep all for mind, and na dat time you fit dey wonder why di system dey make some decisions. But di important thing about knowledge-based systems na say you fit always *explain* how di system make any decision. +> **Note**: Dis example simple small, and e only show how expert system be like. When you start create system like dis, you go only notice some *intelligent* behavior once rules con reach around 200+. At some point, rules go too complex to remember all, and you fit start wonder why system dey make certain decisions. But important quality of knowledge-based systems na sey you fit *explain* clear how any decision dem make. ## Ontologies and the Semantic Web -For di end of 20th century, dem start one initiative to use knowledge representation to mark Internet resources, so e go dey possible to find resources wey match very specific queries. Dis movement dem dey call **Semantic Web**, and e dey base on some ideas: +By end of 20th century, dem start initiative to use knowledge representation to tag Internet resources, so e go possible to find resources wey match very specific queries. Dis movement na **Semantic Web**, and e get several concepts: -- Special knowledge representation wey dey based on **[description logics](https://en.wikipedia.org/wiki/Description_logic)** (DL). E dey similar to frame knowledge representation, because e dey build hierarchy of objects with properties, but e get formal logical semantics and inference. Plenty DLs dey wey dey balance expressiveness and algorithmic complexity of inference. -- Distributed knowledge representation, where all di ideas dey represented by global URI identifier, wey make am possible to create knowledge hierarchies wey dey spread across di internet. -- One group of XML-based languages wey dem dey use for knowledge description: RDF (Resource Description Framework), RDFS (RDF Schema), OWL (Ontology Web Language). +- Special knowledge representation based on **[description logics](https://en.wikipedia.org/wiki/Description_logic)** (DL). E resemble frame knowledge representation, because e build hierarchy of objects with properties, but e get formal logical meaning and inference. DL na whole family wey balance expressiveness and algorithmic complexity of inference. +- Distributed knowledge representation, wey make all concepts get global URI identifier, wey fit make knowledge hierarchies wey stretch all internet possible. +- A family of XML-based languages for knowledge description: RDF (Resource Description Framework), RDFS (RDF Schema), OWL (Ontology Web Language). -One main idea for Semantic Web na di idea of **Ontology**. E mean say you go fit describe one problem area well-well using formal knowledge representation. Di simplest ontology fit just be hierarchy of objects for one problem area, but di more complex ones go get rules wey dem fit use for inference. +A core concept for Semantic Web na di concept of **Ontology**. E mean say na clear explanation of one problem area wit some formal knowledge representation. Di simplest ontology fit be just hierarchy of objects for di problem area, but more complex ontologies go include rules wey fit use do inference. -For Semantic Web, all di representation na based on triplets. Each object and each relation get im own unique URI. For example, if we wan talk say na Dmitry Soshnikov develop dis AI Curriculum on Jan 1st, 2022 - na di triplets we fit use be dis: +For di semantic web, all di representations dey base on triplets. Every object plus relation get unique URI wey identify am. For example, if we wan talk say dis AI Curriculum na Dmitry Soshnikov develop am for Jan 1st, 2022 - na dis triplets we fit use: - + ``` -http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 13, 2007” +http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 1, 2022” http://github.com/microsoft/ai-for-beginners http://purl.org/dc/elements/1.1/creator http://soshnikov.com ``` -> ✅ Here `http://www.example.com/terms/creation-date` and `http://purl.org/dc/elements/1.1/creator` na some well-known and universally accepted URIs to talk about di concepts of *creator* and *creation date*. +> ✅ Here `http://www.example.com/terms/creation-date` and `http://purl.org/dc/elements/1.1/creator` na some well-known and universally accepted URIs wey dem dey use to express the concepts of *creator* and *creation date*. -If di case complex pass dis one, and we wan define list of creators, we fit use some data structures wey RDF define. +For one more complex case, if we wan define list of creators, we fit use some data structures wey RDF define. - + > Diagrams wey dey above na by [Dmitry Soshnikov](http://soshnikov.com) -Di progress to build Semantic Web slow small because search engines and natural language processing techniques don dey successful, and dem dey help extract structured data from text. But for some areas, people still dey try maintain ontologies and knowledge bases. Some projects wey worth to mention: +Di progress to build Semantic Web slow small because search engines and natural language processing techniques don succeed well, wey dem dey use to take structured data come from text. But for some areas, dem still dey put plenty effort to maintain ontologies and knowledge bases. Some projects wey worth to mention be: -* [WikiData](https://wikidata.org/) na collection of machine-readable knowledge bases wey dey linked with Wikipedia. Most of di data dem dey mine am from Wikipedia *InfoBoxes*, wey be structured content inside Wikipedia pages. You fit [query](https://query.wikidata.org/) wikidata with SPARQL, one special query language for Semantic Web. See one sample query wey dey show di most popular eye colors among humans: +* [WikiData](https://wikidata.org/) na collection of machine readable knowledge bases wey dem link to Wikipedia. Most of the data na dem take comot from Wikipedia *InfoBoxes*, pieces of structured content wey dey inside Wikipedia pages. You fit [query](https://query.wikidata.org/) wikidata with SPARQL, one special query language for Semantic Web. Here be one sample query wey show di most popular eye colours for humans: ```sparql #defaultView:BubbleChart @@ -206,51 +206,51 @@ WHERE GROUP BY ?eyeColorLabel ``` -* [DBpedia](https://www.dbpedia.org/) na another project wey be like WikiData. +* [DBpedia](https://www.dbpedia.org/) na another project wey resemble WikiData. -> ✅ If you wan try build your own ontologies, or open di ones wey don already dey, one better visual ontology editor dey wey dem dey call [Protégé](https://protege.stanford.edu/). You fit download am, or use am online. +> ✅ If you want try build your own ontologies, or open existing ones, get one beta visual ontology editor wey dem call [Protégé](https://protege.stanford.edu/). Download am, or use am online. - + -*Web Protégé editor dey open with di Romanov Family ontology. Screenshot by Dmitry Soshnikov* +*Web Protégé editor open with the Romanov Family ontology. Screenshot by Dmitry Soshnikov* ## ✍️ Exercise: A Family Ontology -Check [FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb) to see example of how Semantic Web techniques fit help reason about family relationships. We go use family tree wey dey common GEDCOM format and one ontology of family relationships to build graph of all di family relationships for di people wey dem give. +See [FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb) for example of how Semantic Web techniques fit dey use reason about family relationships. We go take family tree wey show for common GEDCOM format and one ontology of family relationships to build graph of all family relationships for given set of people. ## Microsoft Concept Graph -Most times, people dey carefully create ontologies by hand. But e still dey possible to **mine** ontologies from unstructured data, like natural language texts. +For most cases, ontologies na dem dey carefully create by hand. But e possible to **mine** ontologies from unstructured data, example, from natural language texts. -Microsoft Research try do one like dat, and e result to [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste). +One attempt like dis na from Microsoft Research, wey produce [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste). -E be big collection of entities wey dem group together using `is-a` inheritance relationship. E fit answer questions like "Wetin be Microsoft?" - di answer fit be something like "a company with probability 0.87, and a brand with probability 0.75". +Na large collection of entities grouped together using `is-a` inheritance relationship. E dey fit answer questions like "Wetyn be Microsoft?" - di answer fit be something like "na company with probability 0.87, and na brand with probability 0.75". -Di Graph dey available as REST API, or as big downloadable text file wey list all di entity pairs. +Di Graph dey available either as REST API, or as large text file wey you fit download wey list all entity pairs. ## ✍️ Exercise: A Concept Graph -Try di [MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) notebook to see how we fit use Microsoft Concept Graph to group news articles into different categories. +Try the [MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) notebook to see how we fit use Microsoft Concept Graph to group news articles inside several categories. ## Conclusion -Nowadays, people dey see AI as di same thing with *Machine Learning* or *Neural Networks*. But human beings dey show explicit reasoning, and neural networks never sabi handle dat one. For real-world projects, explicit reasoning still dey useful to do tasks wey need explanation, or wey need make we fit control di system behavior. +Nowadays, AI many people dey consider say e be synonym for *Machine Learning* or *Neural Networks*. But human being still dey do explicit reasoning, way neural networks never really handle yet. For real world projects, explicit reasoning still dey used to do tasks wey need explanation, or to fit change how system dey work for one controlled way. ## 🚀 Challenge -For di Family Ontology notebook wey follow dis lesson, you fit try experiment with other family relations. Try discover new connections between people for di family tree. +For the Family Ontology notebook wey relate to this lesson, you get chance to try other family relations. Try find new connections between people inside family tree. ## [Post-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/4) ## Review & Self Study -Do small research online to find areas where humans don try quantify and codify knowledge. Check Bloom's Taxonomy, and go back to history to learn how humans don dey try understand di world. Look di work of Linnaeus to create taxonomy of organisms, and see how Dmitri Mendeleev create way to describe and group chemical elements. Wetin other interesting examples you fit find? +Try find some research for internet about areas where humans try quantify and codify knowledge. Check Bloom's Taxonomy, and waka go back for history to learn how humans try make sense of dia world. Explore work of Linnaeus to create taxonomy of organisms, and observe how Dmitri Mendeleev take create way for chemical elements to be described and grouped. Wetin be other interesting examples you fit find? **Assignment**: [Build an Ontology](assignment.md) --- -**Disclaimer**: -Dis dokyument don use AI transleshion service [Co-op Translator](https://github.com/Azure/co-op-translator) do di transleshion. Even though we dey try make am accurate, abeg make you sabi say automatik transleshion fit get mistake or no dey correct well. Di original dokyument for im native language na di main source wey you go fit trust. For important informashon, e good make you use professional human transleshion. We no go fit take blame for any misunderstanding or wrong meaning wey fit happen because you use dis transleshion. +**Warning**: +Dis document na im wey AI translation service [Co-op Translator](https://github.com/Azure/co-op-translator) translate. Even though we try make am correct well well, abeg sabi say automatic translation fit get some errors or mistakes. The original document wey dem write for im own language na im get final correct info. If na serious matter, better make human professional translate am. We no go take blame if pesin no understand well or if dem use dis translation do mistake. \ No newline at end of file diff --git a/translations/pcm/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/pcm/lessons/3-NeuralNetworks/03-Perceptron/README.md index f2a8679d..6951fb6b 100644 --- a/translations/pcm/lessons/3-NeuralNetworks/03-Perceptron/README.md +++ b/translations/pcm/lessons/3-NeuralNetworks/03-Perceptron/README.md @@ -15,7 +15,7 @@ One of di first try wey dem do to create somtin wey resemble modern neural netwo | | | |--------------|-----------| -|Frank Rosenblatt | The Mark 1 Perceptron| +|Frank Rosenblatt | The Mark 1 Perceptron| > Images [from Wikipedia](https://en.wikipedia.org/wiki/Perceptron) @@ -34,7 +34,7 @@ y(x) = f(wTx) where f na step activation function - + ## Training the Perceptron diff --git a/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb b/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb index f46441df..9496bfcb 100644 --- a/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb +++ b/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb @@ -373,7 +373,7 @@ "\n", "We don generate one dataset wey go help us do binary classification problem. But make we just assume say na multi-class classification from the beginning, so e go dey easy for us to change our code go multi-class classification later. For dis case, our one-layer perceptron go get dis kind architecture:\n", "\n", - "\n", + "\n", "\n", "The two outputs wey dey come from the network na for the two classes, and the class wey get the highest value among the two outputs na the correct answer.\n", "\n", @@ -620,7 +620,7 @@ "\n", "## Computational Graph\n", "\n", - "\n", + "\n", "\n", "Till dis point, we don define different classes for different layers of di network. Di way wey we fit join all those layers together na wetin we dey call **computational graph**. Now, we fit calculate di loss for one given training dataset (or part of am) like dis:\n" ] @@ -687,7 +687,7 @@ "source": [ "## Backward Propagation\n", "\n", - "\n", + "\n", "\n", "$$\\def\\L{\\mathcal{L}}\\def\\zz#1#2{\\frac{\\partial#1}{\\partial#2}}\n", "\\begin{align}\n", @@ -1267,7 +1267,7 @@ "* Low training loss - di model fit match training data well, because e get enough expressive power.\n", "* Validation loss fit dey higher pass training loss and fit start to increase during training - dis na because di model dey \"memorize\" training points, and e dey lose di \"overall picture.\"\n", "\n", - "![Overfitting](../../../../../translated_images/overfit.a0bd57f717c15769.pcm.png)\n", + "![Overfitting](../../../../../translated_images/pcm/overfit.a0bd57f717c15769.webp)\n", "\n", "> For dis picture, `x` na training data, `o` na validation data. Left - linear model (one-layer), e dey match di nature of di data well. Right - overfitted model, di model dey match training data perfectly, but e no make sense for any other data (validation error dey very high).\n" ] diff --git a/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/README.md index ca0da425..4cdce479 100644 --- a/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/README.md +++ b/translations/pcm/lessons/3-NeuralNetworks/04-OwnFramework/README.md @@ -65,7 +65,7 @@ Di gradient descent algorithm go still dey di same, but e go hard to calculate g Notice say di left-most part of all di expressions dey di same, so we fit calculate derivatives well starting from di loss function and go "backwards" through di computational graph. So di method of training multi-layered perceptron na **backpropagation**, or 'backprop'. -compute graph +compute graph > TODO: image citation diff --git a/translations/pcm/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/pcm/lessons/3-NeuralNetworks/05-Frameworks/README.md index fc13ceb5..bba9c430 100644 --- a/translations/pcm/lessons/3-NeuralNetworks/05-Frameworks/README.md +++ b/translations/pcm/lessons/3-NeuralNetworks/05-Frameworks/README.md @@ -58,7 +58,7 @@ Overfitting na very important concept for machine learning, and e dey very impor Look this problem of trying to fit 5 dots (we dey represent with `x` for the graphs below): -![linear](../../../../../translated_images/overfit1.f24b71c6f652e59e.pcm.jpg) | ![overfit](../../../../../translated_images/overfit2.131f5800ae10ca5e.pcm.jpg) +![linear](../../../../../translated_images/pcm/overfit1.f24b71c6f652e59e.webp) | ![overfit](../../../../../translated_images/pcm/overfit2.131f5800ae10ca5e.webp) -------------------------|-------------------------- **Linear model, 2 parameters** | **Non-linear model, 7 parameters** Training error = 5.3 | Training error = 0 @@ -79,7 +79,7 @@ E dey very important to balance the model strength (number of parameters) and th As you see for the graph above, overfitting fit show when training error dey very low, but validation error dey high. Normally, during training, both training and validation errors go dey reduce, but at one point validation error fit stop to reduce and start to increase. This na sign of overfitting, and e mean say we suppose stop training for that point (or at least save the model snapshot). -![overfitting](../../../../../translated_images/Overfitting.408ad91cd90b4371.pcm.png) +![overfitting](../../../../../translated_images/pcm/Overfitting.408ad91cd90b4371.webp) ## How to prevent overfitting diff --git a/translations/pcm/lessons/3-NeuralNetworks/README.md b/translations/pcm/lessons/3-NeuralNetworks/README.md index 0a6b4420..2928c21a 100644 --- a/translations/pcm/lessons/3-NeuralNetworks/README.md +++ b/translations/pcm/lessons/3-NeuralNetworks/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Introduction to Neural Networks -![Summary of Intro Neural Networks content in a doodle](../../../../translated_images/ai-neuralnetworks.1c687ae40bc86e83.pcm.png) +![Summary of Intro Neural Networks content in a doodle](../../../../translated_images/pcm/ai-neuralnetworks.1c687ae40bc86e83.webp) As we don talk for di introduction, one way wey we fit take achieve intelligence na to train one **computer model** or one **artificial brain**. Since di middle of 20th century, researchers don dey try different mathematical models, until recent years wey dis direction don show say e dey very successful. Dis kind mathematical models of di brain dem dey call am **neural networks**. @@ -36,13 +36,13 @@ For dis curriculum, we go only focus on neural network models. For biology, we sabi say our brain dey made up of neural cells (neurons), and each of dem get plenty "inputs" (dendrites) and one "output" (axon). Both dendrites and axons fit carry electrical signals, and di connections between dem — wey dem dey call synapses — fit get different levels of conductivity, wey neurotransmitters dey control. -![Model of a Neuron](../../../../translated_images/synapse-wikipedia.ed20a9e4726ea1c6.pcm.jpg) | ![Model of a Neuron](../../../../translated_images/artneuron.1a5daa88d20ebe6f.pcm.png) +![Model of a Neuron](../../../../translated_images/pcm/synapse-wikipedia.ed20a9e4726ea1c6.webp) | ![Model of a Neuron](../../../../translated_images/pcm/artneuron.1a5daa88d20ebe6f.webp) ----|---- Real Neuron *([Image](https://en.wikipedia.org/wiki/Synapse#/media/File:SynapseSchematic_lines.svg) from Wikipedia)* | Artificial Neuron *(Image by Author)* So, di simplest mathematical model of a neuron get plenty inputs X1, ..., XN and one output Y, plus weights W1, ..., WN. Di output na: -Y = f\left(\sum_{i=1}^N X_iW_i\right) +Y = f\left(\sum_{i=1}^N X_iW_i\right) where f na one non-linear **activation function**. diff --git a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/README.md index 061c2bbf..ddbebc98 100644 --- a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/README.md +++ b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/README.md @@ -73,14 +73,14 @@ For our [OpenCV Notebook](OpenCV.ipynb), we show some examples of how computer v * **Pre-processing photograph of Braille book**. We dey focus on how we fit use thresholding, feature detection, perspective transformation and NumPy manipulations to separate Braille symbols for classification by neural network. -![Braille Image](../../../../../translated_images/braille.341962ff76b1bd70.pcm.jpeg) | ![Braille Image Pre-processed](../../../../../translated_images/braille-result.46530fea020b03c7.pcm.png) | ![Braille Symbols](../../../../../translated_images/braille-symbols.0159185ab69d5339.pcm.png) +![Braille Image](../../../../../translated_images/pcm/braille.341962ff76b1bd70.webp) | ![Braille Image Pre-processed](../../../../../translated_images/pcm/braille-result.46530fea020b03c7.webp) | ![Braille Symbols](../../../../../translated_images/pcm/braille-symbols.0159185ab69d5339.webp) ----|-----|----- > Image from [OpenCV.ipynb](OpenCV.ipynb) * **Detecting motion for video using frame difference**. If camera no dey move, di frames from di camera feed suppose dey similar. Since frames dey as arrays, if you subtract di arrays for two frames wey follow each other, you go get di pixel difference, wey suppose dey small for static frames, and go big if motion dey for di image. -![Image of video frames and frame differences](../../../../../translated_images/frame-difference.706f805491a0883c.pcm.png) +![Image of video frames and frame differences](../../../../../translated_images/pcm/frame-difference.706f805491a0883c.webp) > Image from [OpenCV.ipynb](OpenCV.ipynb) @@ -89,7 +89,7 @@ For our [OpenCV Notebook](OpenCV.ipynb), we show some examples of how computer v - **Dense Optical Flow** dey calculate vector field wey show where each pixel dey move go. - **Sparse Optical Flow** dey use some special features for di image (like edges), and e dey build their movement from frame to frame. -![Image of Optical Flow](../../../../../translated_images/optical.1f4a94464579a83a.pcm.png) +![Image of Optical Flow](../../../../../translated_images/pcm/optical.1f4a94464579a83a.webp) > Image from [OpenCV.ipynb](OpenCV.ipynb) @@ -115,7 +115,7 @@ Read more about optical flow [for dis better tutorial](https://learnopencv.com/o For dis lab, you go take video wey get simple gestures, and your work na to find up/down/left/right movements using optical flow. -Palm Movement Frame +Palm Movement Frame --- diff --git a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/MovementDetection.ipynb b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/MovementDetection.ipynb index d6d5cc60..8bdda12b 100644 --- a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/MovementDetection.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/MovementDetection.ipynb @@ -10,7 +10,7 @@ "\n", "Check [dis video](../../../../../../lessons/4-ComputerVision/06-IntroCV/lab/palm-movement.mp4), wey person palm dey move go left/right/up/down for stable background.\n", "\n", - "\"Palm\n", + "\"Palm\n", "\n", "**Your goal** na to use Optical Flow to sabi which part of di video get up/down/left/right movements.\n", "\n", diff --git a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/README.md index a4036c5c..381aef05 100644 --- a/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/README.md +++ b/translations/pcm/lessons/4-ComputerVision/06-IntroCV/lab/README.md @@ -15,7 +15,7 @@ Lab Assignment from [AI for Beginners Curriculum](https://aka.ms/ai-beginners). Check [dis video](../../../../../../lessons/4-ComputerVision/06-IntroCV/lab/palm-movement.mp4), wey person palm dey move go left/right/up/down for stable background. -Palm Movement Frame +Palm Movement Frame **Your goal** na to use Optical Flow take know which part of di video get up/down/left/right movements. diff --git a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md index 501cde04..72a01e85 100644 --- a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md +++ b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md @@ -13,11 +13,11 @@ CO_OP_TRANSLATOR_METADATA: VGG-16 na network wey get 92.7% accuracy for ImageNet top-5 classification for 2014. E get dis kain layer structure: -![ImageNet Layers](../../../../../translated_images/vgg-16-arch1.d901a5583b3a51ba.pcm.jpg) +![ImageNet Layers](../../../../../translated_images/pcm/vgg-16-arch1.d901a5583b3a51ba.webp) As you fit see, VGG dey follow traditional pyramid architecture, wey be sequence of convolution-pooling layers. -![ImageNet Pyramid](../../../../../translated_images/vgg-16-arch.64ff2137f50dd49f.pcm.jpg) +![ImageNet Pyramid](../../../../../translated_images/pcm/vgg-16-arch.64ff2137f50dd49f.webp) > Image from [Researchgate](https://www.researchgate.net/figure/Vgg16-model-structure-To-get-the-VGG-NIN-model-we-replace-the-2-nd-4-th-6-th-7-th_fig2_335194493) @@ -25,7 +25,7 @@ As you fit see, VGG dey follow traditional pyramid architecture, wey be sequence ResNet na family of models wey Microsoft Research propose for 2015. Di main idea for ResNet na to use **residual blocks**: - + > Image from [this paper](https://arxiv.org/pdf/1512.03385.pdf) @@ -37,7 +37,7 @@ You fit also think say dis network fit adjust di complexity to di dataset. For d Google Inception architecture carry dis idea go one step further, and build each network layer as combination of different paths: - + > Image from [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) diff --git a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb index 8d28c91f..b9026f7d 100644 --- a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb @@ -262,7 +262,7 @@ "\n", "So, for normal CNN, e go get plenty convolutional layers, and pooling layers go dey between dem to reduce di image size. We go also increase di number of filters, because as di patterns dey more complex, we go need find more possible combinations wey dey important.\n", "\n", - "![An image showing several convolutional layers with pooling layers.](../../../../../translated_images/cnn-pyramid.85915455759ef0ce.pcm.png)\n", + "![An image showing several convolutional layers with pooling layers.](../../../../../translated_images/pcm/cnn-pyramid.85915455759ef0ce.webp)\n", "\n", "Because di spatial dimensions dey reduce and di feature/filters dimensions dey increase, dis architecture dey also call **pyramid architecture**.\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb index c28f52b7..81fae8d7 100644 --- a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb @@ -114,7 +114,7 @@ "\n", "For classical computer vision, dem dey use plenty filters for image to generate features, wey machine learning algorithm go use take build classifier. Dis filters dey similar to di neural structures wey dey di vision system of some animals.\n", "\n", - "\n", + "\n", "\n", "But for deep learning, we dey build networks wey go **learn** di best convolutional filters to solve classification problem. To do dis one, we dey introduce **convolutional layers**.\n" ] @@ -360,7 +360,7 @@ "\n", "So, for normal CNN, e go get plenty convolutional layers, wit pooling layers in between to reduce di size of di image. We go also increase di number of filters, because as di patterns dey more complex, e go get more possible combinations wey we need to dey look for.\n", "\n", - "![An image showing several convolutional layers with pooling layers.](../../../../../translated_images/cnn-pyramid.85915455759ef0ce.pcm.png)\n", + "![An image showing several convolutional layers with pooling layers.](../../../../../translated_images/pcm/cnn-pyramid.85915455759ef0ce.webp)\n", "\n", "Because di spatial dimensions dey reduce and di feature/filters dimensions dey increase, dis architecture dey also call **pyramid architecture**.\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/README.md index d73351be..625a1f45 100644 --- a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/README.md +++ b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/README.md @@ -17,14 +17,14 @@ For real life, we go wan sabi recognize objects for picture no matter where dem To fit extract patterns, we go use di idea of **convolutional filters**. As you sabi, image na 2D-matrix, or 3D-tensor wey get color depth. To apply filter mean say we go carry small **filter kernel** matrix, and for each pixel for di original image, we go calculate di weighted average with di points wey dey near am. We fit see am like small window wey dey slide for di whole image, dey average all di pixels based on di weights for di filter kernel matrix. -![Vertical Edge Filter](../../../../../translated_images/filter-vert.b7148390ca0bc356.pcm.png) | ![Horizontal Edge Filter](../../../../../translated_images/filter-horiz.59b80ed4feb946ef.pcm.png) +![Vertical Edge Filter](../../../../../translated_images/pcm/filter-vert.b7148390ca0bc356.webp) | ![Horizontal Edge Filter](../../../../../translated_images/pcm/filter-horiz.59b80ed4feb946ef.webp) ----|---- > Image by Dmitry Soshnikov Example, if we apply 3x3 vertical edge and horizontal edge filters to MNIST digits, we fit highlight (like high values) where vertical and horizontal edges dey for di original image. So, di two filters fit dey use to "find" edges. Di same way, we fit design different filters to find other low-level patterns: - + > Image of [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html) @@ -38,7 +38,7 @@ Di way CNNs dey work na based on di following important ideas: * We fit design di network make e train di filters by itself * We fit use di same method to find patterns for high-level features, no be only for di original image. So CNN feature extraction dey work for hierarchy of features, from low-level pixel combinations, reach higher level combination of picture parts. -![Hierarchical Feature Extraction](../../../../../translated_images/FeatureExtractionCNN.d9b456cbdae7cb64.pcm.png) +![Hierarchical Feature Extraction](../../../../../translated_images/pcm/FeatureExtractionCNN.d9b456cbdae7cb64.webp) > Image from [a paper by Hislop-Lynch](https://www.semanticscholar.org/paper/Computer-vision-based-pedestrian-trajectory-Hislop-Lynch/26e6f74853fc9bbb7487b06dc2cf095d36c9021d), based on [their research](https://dl.acm.org/doi/abs/10.1145/1553374.1553453) @@ -55,9 +55,9 @@ Most CNNs wey dem dey use for image processing dey follow wetin dem dey call pyr Example, make we look di architecture of VGG-16, one network wey achieve 92.7% accuracy for ImageNet's top-5 classification for 2014: -![ImageNet Layers](../../../../../translated_images/vgg-16-arch1.d901a5583b3a51ba.pcm.jpg) +![ImageNet Layers](../../../../../translated_images/pcm/vgg-16-arch1.d901a5583b3a51ba.webp) -![ImageNet Pyramid](../../../../../translated_images/vgg-16-arch.64ff2137f50dd49f.pcm.jpg) +![ImageNet Pyramid](../../../../../translated_images/pcm/vgg-16-arch.64ff2137f50dd49f.webp) > Image from [Researchgate](https://www.researchgate.net/figure/Vgg16-model-structure-To-get-the-VGG-NIN-model-we-replace-the-2-nd-4-th-6-th-7-th_fig2_335194493) diff --git a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/lab/README.md index 27ee863f..301411bc 100644 --- a/translations/pcm/lessons/4-ComputerVision/07-ConvNets/lab/README.md +++ b/translations/pcm/lessons/4-ComputerVision/07-ConvNets/lab/README.md @@ -21,7 +21,7 @@ You go need train one convolutional neural network to classify di different bree We go use di [Oxford-IIIT Pet Dataset](https://www.robots.ox.ac.uk/~vgg/data/pets/), wey get pictures of 37 different breeds of dogs and cats. -![Dataset we go use](../../../../../../translated_images/data.50b2a9d5484bdbf0.pcm.png) +![Dataset we go use](../../../../../../translated_images/pcm/data.50b2a9d5484bdbf0.webp) To download di dataset, use dis code snippet: diff --git a/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/AdversarialCat_TF.ipynb b/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/AdversarialCat_TF.ipynb index e8e845cd..016f5e79 100644 --- a/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/AdversarialCat_TF.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/AdversarialCat_TF.ipynb @@ -50,7 +50,7 @@ "\n", "To show wetin ideal cat go look like, we go start wit random noise image, and we go try use gradient descent optimization technique to adjust di image so di network go sabi say na cat.\n", "\n", - "![Optimization Loop](../../../../../translated_images/ideal-cat-loop.999fbb8ff306e044.pcm.png)\n", + "![Optimization Loop](../../../../../translated_images/pcm/ideal-cat-loop.999fbb8ff306e044.webp)\n", "\n", "Dis na di image wey we dey start wit:\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/README.md index 110e3eeb..69d139fe 100644 --- a/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/README.md +++ b/translations/pcm/lessons/4-ComputerVision/08-TransferLearning/README.md @@ -29,7 +29,7 @@ Both Keras and PyTorch get functions wey make am easy to load pre-trained neural See example of features wey VGG-16 network extract from cat picture: -![Features extracted by VGG-16](../../../../../translated_images/features.6291f9c7ba3a0b95.pcm.png) +![Features extracted by VGG-16](../../../../../translated_images/pcm/features.6291f9c7ba3a0b95.webp) ## Cats vs. Dogs Dataset @@ -48,19 +48,19 @@ Pre-trained neural network get different patterns for inside e *brain*, includin One way we fit try na to start with random image, then use **gradient descent optimization** technique to adjust di image so di network go dey think say na cat. -![Image Optimization Loop](../../../../../translated_images/ideal-cat-loop.999fbb8ff306e044.pcm.png) +![Image Optimization Loop](../../../../../translated_images/pcm/ideal-cat-loop.999fbb8ff306e044.webp) But if we do am like dis, wetin we go get go dey like random noise. Dis na because *plenty ways dey to make network think say di input image na cat*, including some wey no go make sense for eye. Even though di images get plenty patterns wey dey typical for cat, nothing dey hold dem to look clear. To make di result better, we fit add another term for di loss function, wey dem dey call **variation loss**. Na metric wey dey show how similar di neighboring pixels of di image be. If we minimize variation loss, e go make di image smooth, and remove noise - so we go fit see di patterns well. See example of dis kain "ideal" images wey dem classify as cat and zebra with high probability: -![Ideal Cat](../../../../../translated_images/ideal-cat.203dd4597643d6b0.pcm.png) | ![Ideal Zebra](../../../../../translated_images/ideal-zebra.7f70e8b54ee15a7a.pcm.png) +![Ideal Cat](../../../../../translated_images/pcm/ideal-cat.203dd4597643d6b0.webp) | ![Ideal Zebra](../../../../../translated_images/pcm/ideal-zebra.7f70e8b54ee15a7a.webp) -----|----- *Ideal Cat* | *Ideal Zebra* We fit use similar method to do wetin dem dey call **adversarial attacks** for neural network. Imagine say we wan confuse di neural network make e think say dog be cat. If we carry dog image wey di network recognize as dog, we fit adjust am small small with gradient descent optimization, until di network go dey classify am as cat: -![Picture of a Dog](../../../../../translated_images/original-dog.8f68a67d2fe0911f.pcm.png) | ![Picture of a dog classified as a cat](../../../../../translated_images/adversarial-dog.d9fc7773b0142b89.pcm.png) +![Picture of a Dog](../../../../../translated_images/pcm/original-dog.8f68a67d2fe0911f.webp) | ![Picture of a dog classified as a cat](../../../../../translated_images/pcm/adversarial-dog.d9fc7773b0142b89.webp) -----|----- *Original picture of a dog* | *Picture of a dog classified as a cat* diff --git a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb index dd4c88a3..be5b1e51 100644 --- a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb @@ -21,7 +21,7 @@ "\n", "Because we dey train autoencoder to capture as much information from the original image as e fit for better reconstruction, the network go dey try find the best **embedding** of input images to capture the meaning.\n", "\n", - "![AutoEncoder Diagram](../../../../../translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg)\n", + "![AutoEncoder Diagram](../../../../../translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp)\n", "\n", "> Image from [Keras blog](https://blog.keras.io/building-autoencoders-in-keras.html)\n", "\n", @@ -941,7 +941,7 @@ " * We go sample one vector `sample(z_val in code)` from di distribution $N(\\mathrm{z\\_mean},e^{\\mathrm{z\\_log\\_sigma}})$\n", " * Di decoder go try decode di original image using `sample` as di input vector\n", "\n", - " \n", + " \n", "\n", " > Image from [this blog post](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) by Isaak Dykeman\n" ] @@ -1264,7 +1264,7 @@ "\n", "For dis method, we get **three loss functions**: generator loss, discriminator loss from GAN's, and reconstruction loss from VAE.\n", "\n", - " \n", + " \n", "\n", " > Image from [dis blog post](https://blog.paperspace.com/adversarial-autoencoders-with-pytorch/) by Felipe Ducau\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb index 2d0d581e..6482592f 100644 --- a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb @@ -21,7 +21,7 @@ "\n", "Because we dey train autoencoder to capture as much information from the original image as e fit for better reconstruction, the network go try find the best **embedding** of input images to capture the meaning.\n", "\n", - "![AutoEncoder Diagram](../../../../../translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg)\n", + "![AutoEncoder Diagram](../../../../../translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp)\n", "\n", "*Image from [Keras blog](https://blog.keras.io/building-autoencoders-in-keras.html)*\n", "\n", @@ -888,7 +888,7 @@ " * We go sample one vector `sample` from di distribution $N(\\mathrm{z\\_mean},e^{\\mathrm{z\\_log\\_sigma}})$\n", " * Di Decoder go try decode di original image using `sample` as di input vector\n", "\n", - " \n" + " \n" ] }, { diff --git a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/README.md index 1f9793c1..9c035413 100644 --- a/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/README.md +++ b/translations/pcm/lessons/4-ComputerVision/09-Autoencoders/README.md @@ -19,7 +19,7 @@ But, we fit wan use raw (unlabeled) data to train CNN feature extractors, wey de Since we dey train autoencoder to capture as much information from the original image as e fit for accurate reconstruction, the network go try find the best **embedding** of input images to capture the meaning. -![AutoEncoder Diagram](../../../../../translated_images/autoencoder_schema.5e6fc9ad98a5eb61.pcm.jpg) +![AutoEncoder Diagram](../../../../../translated_images/pcm/autoencoder_schema.5e6fc9ad98a5eb61.webp) > Image from [Keras blog](https://blog.keras.io/building-autoencoders-in-keras.html) @@ -46,7 +46,7 @@ To summarize: * We go sample one vector `sample` from the distribution N(zmean,exp(zlog\_sigma)) * The decoder go try decode the original image using `sample` as input vector - + > Image from [this blog post](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) by Isaak Dykeman @@ -57,13 +57,13 @@ Variational auto-encoders dey use one complex loss function wey get two parts: One big advantage of VAEs be say e dey allow us generate new images easily, because we sabi the distribution wey we go sample latent vectors from. For example, if we train VAE with 2D latent vector on MNIST, we fit vary components of the latent vector to get different digits: -vaemnist +vaemnist > Image by [Dmitry Soshnikov](http://soshnikov.com) See as images dey blend into each other, as we dey get latent vectors from different parts of the latent parameter space. We fit also visualize this space for 2D: -vaemnist cluster +vaemnist cluster > Image by [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/pcm/lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb b/translations/pcm/lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb index f93e1405..370efc10 100644 --- a/translations/pcm/lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb @@ -15,7 +15,7 @@ " * **Generator** go take random vector, and e suppose create image from am\n", " * **Discriminator** na network wey suppose sabi di difference between original image (from training dataset) and di one wey generator create.\n", "\n", - "\n" + "\n" ] }, { @@ -670,7 +670,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "\n", + "\n", "\n", "> Foto dey from [dis tutorial](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html)\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/10-GANs/GANTF.ipynb b/translations/pcm/lessons/4-ComputerVision/10-GANs/GANTF.ipynb index 1995e38a..6221721c 100644 --- a/translations/pcm/lessons/4-ComputerVision/10-GANs/GANTF.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/10-GANs/GANTF.ipynb @@ -15,7 +15,7 @@ " * **Generator** go take random vector, and e suppose generate image from am\n", " * **Discriminator** na network wey suppose sabi di difference between original image (from training dataset) and di one wey generator create.\n", "\n", - "\n" + "\n" ] }, { diff --git a/translations/pcm/lessons/4-ComputerVision/10-GANs/README.md b/translations/pcm/lessons/4-ComputerVision/10-GANs/README.md index 359ab1d0..99e08120 100644 --- a/translations/pcm/lessons/4-ComputerVision/10-GANs/README.md +++ b/translations/pcm/lessons/4-ComputerVision/10-GANs/README.md @@ -17,7 +17,7 @@ But, if we wan generate something wey really make sense, like painting wey get b Di main idea for GAN na to get two neural networks wey go dey train against each other: - + > Image by [Dmitry Soshnikov](http://soshnikov.com) @@ -41,7 +41,7 @@ Generator small tricky pass. You fit see am as reversed discriminator. E dey sta > ✅ Because convolution layer dey work like linear filter wey dey waka through di image, deconvolution dey similar to convolution, and we fit implement am using di same layer logic. - + > Image by [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/pcm/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/pcm/lessons/4-ComputerVision/11-ObjectDetection/README.md index 7ababb50..6b9c9a1f 100644 --- a/translations/pcm/lessons/4-ComputerVision/11-ObjectDetection/README.md +++ b/translations/pcm/lessons/4-ComputerVision/11-ObjectDetection/README.md @@ -13,7 +13,7 @@ Di image classification models we don deal wit before na to take one image and p ## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/21) -![Object Detection](../../../../../translated_images/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.pcm.png) +![Object Detection](../../../../../translated_images/pcm/Screen_Shot_2016-11-17_at_11.14.54_AM.b4bb3769353287be.webp) > Image from [YOLO v2 web site](https://pjreddie.com/darknet/yolov2/) @@ -25,7 +25,7 @@ If we wan find cat for one picture, one simple way to do object detection go be 2. Run image classification for each tile. 3. Any tile wey get high activation fit mean say di object dey inside. -![Naive Object Detection](../../../../../translated_images/naive-detection.e7f1ba220ccd08c6.pcm.png) +![Naive Object Detection](../../../../../translated_images/pcm/naive-detection.e7f1ba220ccd08c6.webp) > *Image from [Exercise Notebook](ObjectDetection-TF.ipynb)* @@ -42,7 +42,7 @@ You fit see dis datasets for dis kind task: * [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/) - 20 classes * [COCO](http://cocodataset.org/#home) - Common Objects in Context. 80 classes, bounding boxes and segmentation masks -![COCO](../../../../../translated_images/coco-examples.71bc60380fa6cceb.pcm.jpg) +![COCO](../../../../../translated_images/pcm/coco-examples.71bc60380fa6cceb.webp) ## Object Detection Metrics @@ -50,7 +50,7 @@ You fit see dis datasets for dis kind task: For image classification, e dey easy to measure how di algorithm dey perform. But for object detection, we need to measure di class correctness and di bounding box location precision. For di bounding box, we dey use **Intersection over Union** (IoU), wey dey measure how two boxes (or areas) dey overlap. -![IoU](../../../../../translated_images/iou_equation.9a4751d40fff4e11.pcm.png) +![IoU](../../../../../translated_images/pcm/iou_equation.9a4751d40fff4e11.webp) > *Figure 2 from [dis blog post on IoU](https://pyimagesearch.com/2016/11/07/intersection-over-union-iou-for-object-detection/)* @@ -97,11 +97,11 @@ We get two main types of object detection algorithms: [R-CNN](http://islab.ulsan.ac.kr/files/announcement/513/rcnn_pami.pdf) dey use [Selective Search](http://www.huppelen.nl/publications/selectiveSearchDraft.pdf) to generate ROI regions, wey CNN go process to extract features. SVM-classifiers go determine di object class, and linear regression go predict di *bounding box* coordinates. [Official Paper](https://arxiv.org/pdf/1506.01497v1.pdf) -![RCNN](../../../../../translated_images/rcnn1.cae407020dfb1d1f.pcm.png) +![RCNN](../../../../../translated_images/pcm/rcnn1.cae407020dfb1d1f.webp) > *Image from van de Sande et al. ICCV’11* -![RCNN-1](../../../../../translated_images/rcnn2.2d9530bb83516484.pcm.png) +![RCNN-1](../../../../../translated_images/pcm/rcnn2.2d9530bb83516484.webp) > *Images from [dis blog](https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e) @@ -109,7 +109,7 @@ We get two main types of object detection algorithms: Dis method dey similar to R-CNN, but e dey define regions after convolution layers don run. -![FRCNN](../../../../../translated_images/f-rcnn.3cda6d9bb4188875.pcm.png) +![FRCNN](../../../../../translated_images/pcm/f-rcnn.3cda6d9bb4188875.webp) > Image from [di Official Paper](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Girshick_Fast_R-CNN_ICCV_2015_paper.pdf), [arXiv](https://arxiv.org/pdf/1504.08083.pdf), 2015 @@ -117,7 +117,7 @@ Dis method dey similar to R-CNN, but e dey define regions after convolution laye Dis method dey use neural network to predict ROIs - di *Region Proposal Network*. [Paper](https://arxiv.org/pdf/1506.01497.pdf), 2016 -![FasterRCNN](../../../../../translated_images/faster-rcnn.8d46c099b87ef30a.pcm.png) +![FasterRCNN](../../../../../translated_images/pcm/faster-rcnn.8d46c099b87ef30a.webp) > Image from [di official paper](https://arxiv.org/pdf/1506.01497.pdf) @@ -129,7 +129,7 @@ Dis algorithm dey faster pass Faster R-CNN. Di main idea be: 2. Process di features wit **Position-Sensitive Score Map**. Each object from $C$ classes dey divide into $k\times k$ regions, and we dey train to predict di object parts. 3. For each part, di network go vote for di object class, and di class wit di highest vote go dey selected. -![r-fcn image](../../../../../translated_images/r-fcn.13eb88158b99a3da.pcm.png) +![r-fcn image](../../../../../translated_images/pcm/r-fcn.13eb88158b99a3da.webp) > Image from [official paper](https://arxiv.org/abs/1605.06409) @@ -140,7 +140,7 @@ YOLO na realtime one-pass algorithm. Di main idea be: * Divide di image into $S\times S$ regions. * For each region, **CNN** go predict $n$ possible objects, *bounding box* coordinates, and *confidence*=*probability* * IoU. - ![YOLO](../../../../../translated_images/yolo.a2648ec82ee8bb4e.pcm.png) + ![YOLO](../../../../../translated_images/pcm/yolo.a2648ec82ee8bb4e.webp) > Image from [official paper](https://arxiv.org/abs/1506.02640) diff --git a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/README.md index 6e44201c..d98129f7 100644 --- a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/README.md +++ b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/README.md @@ -20,7 +20,7 @@ Segmentation fit be like **pixel classification**, wey mean say for **each** pix For instance segmentation, di sheep dem na different objects, but for semantic segmentation, all di sheep go dey under one class. - + > Image from [this blog post](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) @@ -29,7 +29,7 @@ Different neural architectures dey for segmentation, but all of dem get di same * **Encoder** dey extract features from di input image. * **Decoder** dey change di features into di **mask image**, wey get di same size and number of channels wey match di number of classes. - + > Image from [this publication](https://arxiv.org/pdf/2001.05566.pdf) @@ -43,7 +43,7 @@ For dis lesson, we go see segmentation in action by training di network to recog > ✅ Dis technique dey very good for dis type of medical imaging, but which other real-world applications you fit think of? -navi +navi > Image from di PH2 Database diff --git a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb index f1dff8ab..997e97a7 100644 --- a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb @@ -17,7 +17,7 @@ "\n", "For instance segmentation, 10 sheep go be different objects, but for semantic segmentation, all di sheep go dey under one class.\n", "\n", - "\n", + "\n", "\n", "> Image from [dis blog post](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)\n", "\n", @@ -26,7 +26,7 @@ "* **Encoder** dey extract features from di input image.\n", "* **Decoder** dey change di features into di **mask image**, wey get di same size and number of channels wey match di number of classes.\n", "\n", - "\n", + "\n", "\n", "> Image from [dis publication](https://arxiv.org/pdf/2001.05566.pdf)\n" ] @@ -252,7 +252,7 @@ "\n", "Di simplest encoder-decoder architecture na **SegNet**. E dey use standard CNN wey get convolutions and poolings for di encoder, and deconvolution CNN wey get convolutions and upsamplings for di decoder. E still dey depend on batch normalization to fit train multi-layered network well.\n", "\n", - "\n", + "\n", "\n", "> Image from dis paper: Badrinarayanan, V., Kendall, A., & Cipolla, R. (2015). [SegNet: A deep convolutional\n", "encoder-decoder architecture for image segmentation](https://arxiv.org/pdf/1511.00561.pdf)\n" @@ -548,7 +548,7 @@ "\n", "We go use one simple CNN architecture here, but U-Net fit also use more complex encoder for feature extraction, like ResNet-50.\n", "\n", - "\n", + "\n", "\n", "> Image from paper: Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. [U-Net: Convolutional networks for biomedical image segmentation.](https://arxiv.org/pdf/1505.04597.pdf)\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb index e424ff96..e6a5b897 100644 --- a/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb +++ b/translations/pcm/lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb @@ -12,13 +12,13 @@ "\n", "For instance segmentation, ten cars na **different** objects, but for semantic segmentation, **all** cars na one class.\n", "\n", - "\n", + "\n", "\n", "> Image from [this blog post](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)\n", "\n", "Almost all di architectures get di same structure. Di first part na **encoder** wey dey collect features from di input image, di second part na **decoder** wey dey change di features into image wey get di same height and width, plus some number of channels, wey fit equal to di classes count.\n", "\n", - "\n", + "\n", "\n", "> Image from [this publication](https://arxiv.org/pdf/2001.05566.pdf)\n" ] @@ -210,7 +210,7 @@ "\n", "Simple encoder-decoder wey get convolution, pooling for encoder side and convolution, upsampling for decoder side.\n", "\n", - "\n", + "\n", "\n", "* Badrinarayanan, V., Kendall, A., & Cipolla, R. (2015). [SegNet: A deep convolutional\n", "encoder-decoder architecture for image segmentation](https://arxiv.org/pdf/1511.00561.pdf)\n" @@ -602,7 +602,7 @@ "\n", "U-Net dey usually get default encoder for feature extraction, like resnet50.\n", "\n", - "\n", + "\n", "\n", "* Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. [U-Net: Convolutional networks for biomedical image segmentation.](https://arxiv.org/pdf/1505.04597.pdf)\n" ] diff --git a/translations/pcm/lessons/4-ComputerVision/README.md b/translations/pcm/lessons/4-ComputerVision/README.md index cb6e1df4..2653866b 100644 --- a/translations/pcm/lessons/4-ComputerVision/README.md +++ b/translations/pcm/lessons/4-ComputerVision/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Computer Vision -![Summary of Computer Vision content in a doodle](../../../../translated_images/ai-computervision.6506ebebac3fbf76.pcm.png) +![Summary of Computer Vision content in a doodle](../../../../translated_images/pcm/ai-computervision.6506ebebac3fbf76.webp) For dis section, we go learn about: diff --git a/translations/pcm/lessons/5-NLP/13-TextRep/README.md b/translations/pcm/lessons/5-NLP/13-TextRep/README.md index ebe853db..c604ae63 100644 --- a/translations/pcm/lessons/5-NLP/13-TextRep/README.md +++ b/translations/pcm/lessons/5-NLP/13-TextRep/README.md @@ -25,7 +25,7 @@ Our goal na to classify di news item into one of di categories based on di text. If we wan solve Natural Language Processing (NLP) tasks wit neural networks, we need way to represent text as tensors. Computers dey already represent text characters as numbers wey dey map to fonts for your screen using encodings like ASCII or UTF-8. -Image wey show diagram wey dey map one character to ASCII and binary representation +Image wey show diagram wey dey map one character to ASCII and binary representation > [Image source](https://www.seobility.net/en/wiki/ASCII) @@ -48,7 +48,7 @@ Sometimes, we fit use tri-grams -- combinations of three words -- too. Dis appro If we dey solve tasks like text classification, we need way to represent text as one fixed-size vector, wey we go use as input to di final dense classifier. One simple way na to combine all di individual word representations, like adding dem. If we add one-hot encodings of each word, we go get one vector of frequencies, wey go show how many times each word appear for di text. Dis representation of text na **bag of words** (BoW). - + > Image by di author diff --git a/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb b/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb index a1b21aa3..f202858d 100644 --- a/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb +++ b/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb @@ -199,7 +199,7 @@ "\n", "**Bag of Words** (BoW) vector representation na di most common traditional vector representation wey people dey use. Each word dey connect to one vector index, and di vector element dey show how many times one word appear for one document.\n", "\n", - "![Image wey dey show how bag of words vector representation dey show for memory.](../../../../../translated_images/bag-of-words-example.606fc1738f1d7ba9.pcm.png) \n", + "![Image wey dey show how bag of words vector representation dey show for memory.](../../../../../translated_images/pcm/bag-of-words-example.606fc1738f1d7ba9.webp) \n", "\n", "> **Note**: You fit also think of BoW like sum of all one-hot-encoded vectors for di individual words wey dey inside di text.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb b/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb index 896704e5..fb58d8f9 100644 --- a/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb +++ b/translations/pcm/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb @@ -188,7 +188,7 @@ "\n", "**Bag-of-words** (BoW) vector representation na the simplest way to understand traditional vector representation. Each word dey connect to one vector index, and one vector element dey show how many times each word appear for one document.\n", "\n", - "![Image showing how a bag of words vector representation is represented in memory.](../../../../../translated_images/bag-of-words-example.606fc1738f1d7ba9.pcm.png) \n", + "![Image showing how a bag of words vector representation is represented in memory.](../../../../../translated_images/pcm/bag-of-words-example.606fc1738f1d7ba9.webp) \n", "\n", "> **Note**: You fit also think of BoW as sum of all one-hot-encoded vectors for each word wey dey the text.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb b/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb index 11bf2bdf..f2b39adb 100644 --- a/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb +++ b/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb @@ -62,7 +62,7 @@ "\n", "If we use embedding layer as di first layer for our network, we fit change from bag-of-words to **embedding bag** model. For dis model, we go first change each word for our text to di embedding wey match am, then we go calculate one aggregate function for all di embeddings, like `sum`, `average` or `max`.\n", "\n", - "![Image showing an embedding classifier for five sequence words.](../../../../../translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png)\n", + "![Image showing an embedding classifier for five sequence words.](../../../../../translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp)\n", "\n", "Our classifier neural network go start wit embedding layer, then aggregation layer, and linear classifier on top:\n" ] @@ -176,7 +176,7 @@ "\n", "For di architecture wey we bin dey use before, we need to pad all di sequences make dem get di same length so dem go fit enter minibatch. Dis no be di most efficient way to represent sequences wey get different length - another way na to use **offset** vector, wey go hold di offsets of all di sequences wey dey inside one big vector.\n", "\n", - "![Image wey dey show offset sequence representation](../../../../../translated_images/offset-sequence-representation.eb73fcefb29b46ee.pcm.png)\n", + "![Image wey dey show offset sequence representation](../../../../../translated_images/pcm/offset-sequence-representation.eb73fcefb29b46ee.webp)\n", "\n", "> **Note**: For di picture wey dey up, we dey show sequence of characters, but for our example we dey work with sequences of words. But di general principle of how to represent sequences with offset vector still remain di same.\n", "\n", @@ -311,7 +311,7 @@ "\n", "CBoW fast pass, but skip-gram slow small, e dey do better work for words wey no dey common.\n", "\n", - "![Image wey show both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png)\n", + "![Image wey show both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp)\n", "\n", "To try word2vec embedding wey dem don pre-train for Google News dataset, we fit use **gensim** library. For di example below, we go find di words wey dey most similar to 'neural'\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb b/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb index d6da0985..32872d7d 100644 --- a/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb +++ b/translations/pcm/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb @@ -37,7 +37,7 @@ "\n", "If we use embedding layer as di first layer for our network, we fit change from bag-of-words to **embedding bag** model. For dis one, we go first change each word for our text to di embedding wey match am, then we go do one kind calculation for all di embeddings, like `sum`, `average` or `max`.\n", "\n", - "![Image wey dey show embedding classifier for five sequence words.](../../../../../translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png)\n", + "![Image wey dey show embedding classifier for five sequence words.](../../../../../translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp)\n", "\n", "Our classifier neural network get di following layers:\n", "\n", @@ -283,7 +283,7 @@ "\n", "CBoW fast well, but skip-gram slow small, e dey represent words wey no dey common better.\n", "\n", - "![Image wey dey show both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png)\n", + "![Image wey dey show both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp)\n", "\n", "To test di Word2Vec embedding wey dem don pretrain for Google News dataset, we fit use di **gensim** library. For di example below, we go find di words wey dey most similar to 'neural'.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/14-Embeddings/README.md b/translations/pcm/lessons/5-NLP/14-Embeddings/README.md index bec891cb..8c24311e 100644 --- a/translations/pcm/lessons/5-NLP/14-Embeddings/README.md +++ b/translations/pcm/lessons/5-NLP/14-Embeddings/README.md @@ -19,7 +19,7 @@ So, di embedding layer go take one word as input, and e go produce output vector If we use embedding layer as di first layer for our classifier network, we fit change from bag-of-words to **embedding bag** model. For here, we go first convert each word for our text into di embedding wey match am, then we go calculate one aggregate function like `sum`, `average` or `max` for all di embeddings. -![Image showing an embedding classifier for five sequence words.](../../../../../translated_images/embedding-classifier-example.b77f021a7ee67eee.pcm.png) +![Image showing an embedding classifier for five sequence words.](../../../../../translated_images/pcm/embedding-classifier-example.b77f021a7ee67eee.webp) > Image by di author @@ -40,7 +40,7 @@ To do dis, we need to pre-train our embedding model on big text collection in on CBoW dey faster, but skip-gram dey slow small, though e dey represent words wey no dey common better. -![Image showing both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png) +![Image showing both CBoW and Skip-Gram algorithms to convert words to vectors.](../../../../../translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp) > Image from [this paper](https://arxiv.org/pdf/1301.3781.pdf) diff --git a/translations/pcm/lessons/5-NLP/15-LanguageModeling/README.md b/translations/pcm/lessons/5-NLP/15-LanguageModeling/README.md index a7eaa658..c66f9916 100644 --- a/translations/pcm/lessons/5-NLP/15-LanguageModeling/README.md +++ b/translations/pcm/lessons/5-NLP/15-LanguageModeling/README.md @@ -23,7 +23,7 @@ For di examples wey we don do before, we use pre-trained semantic embeddings, bu * **Continuous Bag-of-Words** (CBoW), wey mean say we go predict di middle token $W_0$ for one token sequence $W_{-N}$, ..., $W_N$. * **Skip-gram**, wey mean say we go predict set of neighboring tokens {$W_{-N},\dots, W_{-1}, W_1,\dots, W_N$} from di middle token $W_0$. -![image from paper on converting words to vectors](../../../../../translated_images/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.pcm.png) +![image from paper on converting words to vectors](../../../../../translated_images/pcm/example-algorithms-for-converting-words-to-vectors.fbe9207a726922f6.webp) > Image from [this paper](https://arxiv.org/pdf/1301.3781.pdf) diff --git a/translations/pcm/lessons/5-NLP/16-RNN/README.md b/translations/pcm/lessons/5-NLP/16-RNN/README.md index 53d9eb49..539471bf 100644 --- a/translations/pcm/lessons/5-NLP/16-RNN/README.md +++ b/translations/pcm/lessons/5-NLP/16-RNN/README.md @@ -15,7 +15,7 @@ For di sections wey don pass, we don dey use beta semantic representation of tex To fit capture di meaning of text sequence, we go need another neural network architecture, wey dem dey call **recurrent neural network**, or RNN. For RNN, we go pass our sentence through di network one symbol at a time, and di network go produce one **state**, wey we go pass back to di network again with di next symbol. -![RNN](../../../../../translated_images/rnn.27f5c29c53d727b5.pcm.png) +![RNN](../../../../../translated_images/pcm/rnn.27f5c29c53d727b5.webp) > Image by di author @@ -31,7 +31,7 @@ Make we see how simple RNN cell dey organized. E dey accept di previous state S< Simple RNN cell get two weight matrices inside: one dey transform input symbol (make we call am W), and another one dey transform input state (H). For dis case, di output of di network dey calculate as σ(W×Xi+H×Si-1+b), where σ na di activation function and b na additional bias. -RNN Cell Anatomy +RNN Cell Anatomy > Image by di author @@ -61,7 +61,7 @@ We don talk about recurrent networks wey dey work for one direction, from di beg Recurrent network, whether na one-directional or bidirectional, dey capture some patterns inside sequence, and e fit store dem inside state vector or pass am into output. Just like convolutional networks, we fit build another recurrent layer on top di first one to capture higher level patterns and build from di low-level patterns wey di first layer extract. Dis one dey lead us to di idea of **multi-layer RNN** wey get two or more recurrent networks, where di output of di previous layer dey pass to di next layer as input. -![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg) +![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp) *Picture from [this wonderful post](https://towardsdatascience.com/from-a-lstm-cell-to-a-multilayer-lstm-network-with-pytorch-2899eb5696f3) by Fernando López* diff --git a/translations/pcm/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb b/translations/pcm/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb index 30aae6a2..45927a1c 100644 --- a/translations/pcm/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb +++ b/translations/pcm/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb @@ -10,7 +10,7 @@ "\n", "To fit capture di meaning of text sequence, we go need use another neural network architecture wey dem dey call **recurrent neural network**, or RNN. For RNN, we go dey pass our sentence through di network one symbol at a time, and di network go produce one **state**, wey we go then pass back to di network with di next symbol.\n", "\n", - "\"RNN\"\n", + "\"RNN\"\n", "\n", "If we get input sequence of tokens $X_0,\\dots,X_n$, RNN go create one sequence of neural network blocks, and e go train dis sequence end-to-end using back propagation. Each network block dey take one pair $(X_i,S_i)$ as input, and e go produce $S_{i+1}$ as result. Final state $S_n$ or output $X_n$ go enter one linear classifier to produce di result. All di network blocks dey share di same weights, and dem dey train end-to-end using one back propagation pass.\n", "\n", @@ -428,7 +428,7 @@ "\n", "Recurrent network, whether e dey go one direction or e dey bidirectional, dey capture some patterns inside sequence, and e fit store dem for state vector or pass dem go output. Just like convolutional networks, we fit build another recurrent layer on top di first one to capture higher level patterns, wey di low-level patterns wey di first layer extract go help build. Dis one na wetin dem dey call **multi-layer RNN**, wey get two or more recurrent networks, and di output of di previous layer go dey pass go di next layer as input.\n", "\n", - "![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg)\n", + "![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp)\n", "\n", "*Di picture dey from [dis fine post](https://towardsdatascience.com/from-a-lstm-cell-to-a-multilayer-lstm-network-with-pytorch-2899eb5696f3) by Fernando López*\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/16-RNN/RNNTF.ipynb b/translations/pcm/lessons/5-NLP/16-RNN/RNNTF.ipynb index aa797dbf..fae18f5d 100644 --- a/translations/pcm/lessons/5-NLP/16-RNN/RNNTF.ipynb +++ b/translations/pcm/lessons/5-NLP/16-RNN/RNNTF.ipynb @@ -10,7 +10,7 @@ "\n", "To fit capture di meaning of text sequence, we go use one neural network architecture wey dem dey call **recurrent neural network**, or RNN. When we dey use RNN, we go pass our sentence through di network one token at a time, and di network go produce some **state**, wey we go pass to di network again with di next token.\n", "\n", - "![Image wey dey show example of recurrent neural network generation.](../../../../../translated_images/rnn.27f5c29c53d727b5.pcm.png)\n", + "![Image wey dey show example of recurrent neural network generation.](../../../../../translated_images/pcm/rnn.27f5c29c53d727b5.webp)\n", "\n", "If we get di input sequence of tokens $X_0,\\dots,X_n$, di RNN go create one sequence of neural network blocks, and e go train dis sequence end-to-end using backpropagation. Each network block dey take one pair $(X_i,S_i)$ as input, and e dey produce $S_{i+1}$ as result. Di final state $S_n$ or output $Y_n$ go enter linear classifier to produce di result. All di network blocks dey share di same weights, and dem dey train am end-to-end using one back propagation pass.\n", "\n", @@ -371,7 +371,7 @@ "\n", "Recurrent networks, whether na unidirectional or bidirectional, dey capture patterns inside sequence, and dem dey store am for state vectors or return am as output. Just like convolutional networks, we fit build another recurrent layer after di first one to capture higher level patterns, wey dem build from di lower level patterns wey di first layer extract. Dis one na wetin dem dey call **multi-layer RNN**, wey get two or more recurrent networks, where di output of di previous layer dey pass go di next layer as input.\n", "\n", - "![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/multi-layer-lstm.dd975e29bb2a59fe.pcm.jpg)\n", + "![Image showing a Multilayer long-short-term-memory- RNN](../../../../../translated_images/pcm/multi-layer-lstm.dd975e29bb2a59fe.webp)\n", "\n", "*Picture from [dis wonderful post](https://towardsdatascience.com/from-a-lstm-cell-to-a-multilayer-lstm-network-with-pytorch-2899eb5696f3) by Fernando López.*\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb index be75c41c..e75f77e4 100644 --- a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb +++ b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb @@ -119,7 +119,7 @@ "\n", "Di way we go take train RNN to dey generate text na like dis. For each step, we go carry one sequence of characters wey get length `nchars`, and we go tell di network make e generate di next character wey go follow each input character:\n", "\n", - "![Image wey dey show example of RNN wey dey generate di word 'HELLO'.](../../../../../translated_images/rnn-generate.56c54afb52f9781d.pcm.png)\n", + "![Image wey dey show example of RNN wey dey generate di word 'HELLO'.](../../../../../translated_images/pcm/rnn-generate.56c54afb52f9781d.webp)\n", "\n", "Depending on di situation wey we dey, we fit wan add some special characters, like *end-of-sequence* ``. But for our own case, we just wan train di network to dey generate text without end, so we go fix di size of each sequence make e equal to `nchars` tokens. So, each training example go get `nchars` inputs and `nchars` outputs (di input sequence go shift one symbol go left). Minibatch go get plenty of dis kind sequences.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb index a7dc4f13..51c4d788 100644 --- a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb +++ b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb @@ -113,7 +113,7 @@ "\n", "Di way we go take train RNN to dey generate news titles na like dis. For each step, we go carry one title, wey we go put inside RNN, and for each character wey we put as input, we go tell di network make e generate di next character:\n", "\n", - "![Image wey dey show example of RNN wey dey generate di word 'HELLO'.](../../../../../translated_images/rnn-generate.56c54afb52f9781d.pcm.png)\n", + "![Image wey dey show example of RNN wey dey generate di word 'HELLO'.](../../../../../translated_images/pcm/rnn-generate.56c54afb52f9781d.webp)\n", "\n", "For di last character for our sequence, we go tell di network make e generate `` token.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/README.md index eb25ed9b..ac34e19e 100644 --- a/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/README.md +++ b/translations/pcm/lessons/5-NLP/17-GenerativeNetworks/README.md @@ -19,7 +19,7 @@ For di RNN architecture wey we discuss for di last unit, each RNN unit dey produ Dis one dey allow different neural architectures wey dem show for di picture below: -![Image showing common recurrent neural network patterns.](../../../../../translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.pcm.jpg) +![Image showing common recurrent neural network patterns.](../../../../../translated_images/pcm/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp) > Image from blog post [Unreasonable Effectiveness of Recurrent Neural Networks](http://karpathy.github.io/2015/05/21/rnn-effectiveness/) by [Andrej Karpaty](http://karpathy.github.io/) @@ -32,11 +32,11 @@ For dis unit, we go focus on simple generative models wey go help us generate te We go train dis RNN to generate text step by step. For each step, we go take sequence of characters wey get length `nchars`, then ask di network to generate di next output character for each input character: -![Image showing an example RNN generation of the word 'HELLO'.](../../../../../translated_images/rnn-generate.56c54afb52f9781d.pcm.png) +![Image showing an example RNN generation of the word 'HELLO'.](../../../../../translated_images/pcm/rnn-generate.56c54afb52f9781d.webp) When we dey generate text (during inference), we go start with one **prompt**, wey we go pass through RNN cells to generate di intermediate state, then from di state, di generation go start. We go generate one character at a time, then pass di state and di generated character to another RNN cell to generate di next one, until we generate enough characters. - + > Image by di author diff --git a/translations/pcm/lessons/5-NLP/18-Transformers/README.md b/translations/pcm/lessons/5-NLP/18-Transformers/README.md index 3eca065a..8f13bffa 100644 --- a/translations/pcm/lessons/5-NLP/18-Transformers/README.md +++ b/translations/pcm/lessons/5-NLP/18-Transformers/README.md @@ -20,13 +20,13 @@ With RNNs, sequence-to-sequence dey work with two recurrent networks. One networ **Attention Mechanisms** dey help to give weight to how each input vector go affect each output prediction of the RNN. E dey work by creating shortcuts between intermediate states of the input RNN and the output RNN. So, when we dey generate output symbol yt, we go consider all input hidden states hi, with different weight coefficients αt,i. -![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png) +![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp) > The encoder-decoder model with additive attention mechanism in [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf), cited from [this blog post](https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html) The attention matrix {αi,j} go show how much certain input words dey contribute to the generation of one word for the output sequence. Example of dis matrix dey below: -![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png) +![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp) > Figure from [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf) (Fig.3) @@ -56,7 +56,7 @@ The idea of positional encoding be like dis: * Trainable embedding, like token embedding. Na dis approach we go use here. We go apply embedding layers for both tokens and their positions, wey go give embedding vectors of the same dimensions, then we go add dem together. * Fixed position encoding function, as dem propose for the original paper. - + > Image by the author @@ -66,7 +66,7 @@ The result wey we go get with positional embedding go combine the original token Next, we need to capture some patterns inside our sequence. To do dis, transformers dey use **self-attention** mechanism, wey be attention wey dem apply to the same sequence as input and output. Self-attention dey help us consider **context** inside sentence, and see how words dey relate. For example, e dey help us see how words dey refer to coreferences like *it*, and also consider the context: -![](../../../../../translated_images/CoreferenceResolution.861924d6d384a7d6.pcm.png) +![](../../../../../translated_images/pcm/CoreferenceResolution.861924d6d384a7d6.webp) > Image from the [Google Blog](https://research.googleblog.com/2017/08/transformer-novel-neural-network.html) @@ -91,7 +91,7 @@ Because each input position dey map independently to each output position, trans **BERT** (Bidirectional Encoder Representations from Transformers) na very big multi-layer transformer network with 12 layers for *BERT-base*, and 24 for *BERT-large*. The model dey first pre-train on large corpus of text data (WikiPedia + books) using unsupervised training (predicting masked words for sentence). During pre-training, the model dey learn plenty language understanding wey fit help am perform well with other datasets when we fine-tune am. Dis process na **transfer learning**. -![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png) +![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp) > Image [source](http://jalammar.github.io/illustrated-bert/) diff --git a/translations/pcm/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb b/translations/pcm/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb index 49c4b783..01cdc36a 100644 --- a/translations/pcm/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb +++ b/translations/pcm/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb @@ -14,12 +14,12 @@ "\n", "Di image below dey show encoder-decoder model wit additive attention layer:\n", "\n", - "![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png)\n", + "![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp)\n", "*Di encoder-decoder model wit additive attention mechanism for [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf), wey dem take from [dis blog post](https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html)*\n", "\n", "Di Attention matrix $\\{\\alpha_{i,j}\\}$ go show how much certain input words dey contribute to di generation of one word for di output sequence. Below na example of di matrix:\n", "\n", - "![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png)\n", + "![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp)\n", "\n", "*Di figure dey from [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf) (Fig.3)*\n", "\n", @@ -37,7 +37,7 @@ "\n", "**BERT** (Bidirectional Encoder Representations from Transformers) na very big multi-layer transformer network wit 12 layers for *BERT-base*, and 24 for *BERT-large*. Di model dey first pre-train wit big corpus of text data (WikiPedia + books) using unsupervised training (predicting masked words for sentence). During di pre-training, di model dey learn plenty language understanding wey fit dey used wit other datasets through fine tuning. Dis process na wetin dem dey call **transfer learning**. \n", "\n", - "![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png)\n", + "![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp)\n", "\n", "Plenty variations of Transformer architectures dey, like BERT, DistilBERT, BigBird, OpenGPT3 and more wey fit dey fine-tuned. Di [HuggingFace package](https://github.com/huggingface/) dey provide repository for training plenty of dis architectures wit PyTorch. \n", "\n", diff --git a/translations/pcm/lessons/5-NLP/18-Transformers/TransformersTF.ipynb b/translations/pcm/lessons/5-NLP/18-Transformers/TransformersTF.ipynb index d0537bd6..20e6cba9 100644 --- a/translations/pcm/lessons/5-NLP/18-Transformers/TransformersTF.ipynb +++ b/translations/pcm/lessons/5-NLP/18-Transformers/TransformersTF.ipynb @@ -12,12 +12,12 @@ "\n", "**Attention Mechanisms** dey help to give weight to di contextual impact of each input vector for each output prediction of di RNN. Di way dem dey do am na by creating shortcuts between di intermediate states of di input RNN, and di output RNN. So, when we dey generate output symbol $y_t$, we go consider all di input hidden states $h_i$, wit different weight coefficients $\\alpha_{t,i}$. \n", "\n", - "![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/encoder-decoder-attention.7a726296894fb567.pcm.png)\n", + "![Image showing an encoder/decoder model with an additive attention layer](../../../../../translated_images/pcm/encoder-decoder-attention.7a726296894fb567.webp)\n", "*Di encoder-decoder model wit additive attention mechanism for [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf), wey dem show for [dis blog post](https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html)*\n", "\n", "Attention matrix $\\{\\alpha_{i,j}\\}$ go show how much certain input words dey contribute to di generation of one word for di output sequence. Below na example of di matrix:\n", "\n", - "![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/bahdanau-fig3.09ba2d37f202a6af.pcm.png)\n", + "![Image showing a sample alignment found by RNNsearch-50, taken from Bahdanau - arviz.org](../../../../../translated_images/pcm/bahdanau-fig3.09ba2d37f202a6af.webp)\n", "\n", "*Figure wey dem take from [Bahdanau et al., 2015](https://arxiv.org/pdf/1409.0473.pdf) (Fig.3)*\n", "\n", @@ -92,7 +92,7 @@ "source": [ "Dis layer get two `Embedding` layers: one for embedding tokens (like we don talk before) and another one for token positions. Token positions na sequence of natural numbers from 0 go reach `maxlen` wey dem use `tf.range` create, and dem go pass am through embedding layer. The two embedding vectors wey dem get go join together, and e go produce positionally-embedded representation of input wey get shape `maxlen`$\\times$`embed_dim`.\n", "\n", - "\n", + "\n", "\n", "Now, make we implement the transformer block. E go use the output wey the embedding layer we don define before produce:\n" ] @@ -134,7 +134,7 @@ "\n", "Di output of dis layer go then pass through `Dense` network (for our case - two-layer perceptron), and di result go join di final output (wey go still undergo normalization again).\n", "\n", - "\n", + "\n", "\n", "Now, we don ready to define di complete transformer model:\n" ] @@ -235,7 +235,7 @@ "\n", "**BERT** (Bidirectional Encoder Representations from Transformers) na one big transformer network wey get 12 layers for *BERT-base*, and 24 for *BERT-large*. Dem first train di model with plenty text data (WikiPedia + books) wey no get supervision (dem dey predict di words wey dem hide for sentence). As dem dey train di model, e dey learn plenty tins about language wey fit help am when dem wan use am with other datasets by fine-tuning. Dis process na wetin dem dey call **transfer learning**.\n", "\n", - "![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.pcm.png)\n", + "![picture from http://jalammar.github.io/illustrated-bert/](../../../../../translated_images/pcm/jalammarBERT-language-modeling-masked-lm.34f113ea5fec4362.webp)\n", "\n", "Plenty Transformer architectures dey like BERT, DistilBERT, BigBird, OpenGPT3 and others wey person fit fine-tune.\n", "\n", diff --git a/translations/pcm/lessons/5-NLP/19-NER/README.md b/translations/pcm/lessons/5-NLP/19-NER/README.md index dd809280..79e17e67 100644 --- a/translations/pcm/lessons/5-NLP/19-NER/README.md +++ b/translations/pcm/lessons/5-NLP/19-NER/README.md @@ -17,7 +17,7 @@ So far, we don dey focus mostly on one NLP task - classification. But e get othe Make we say you wan build natural language chat bot, like Amazon Alexa or Google Assistant. Di way wey smart chat bots dey work na to *understand* wetin di user wan by doing text classification for di sentence wey dem type. Di result of dis classification na wetin dem dey call **intent**, wey go show wetin di chat bot suppose do. -Bot NER +Bot NER > Image na di author create am @@ -58,7 +58,7 @@ infant | O Because we need to match tokens and classes one by one, we fit train di **many-to-many** neural network model wey dey show for dis picture: -![Image showing common recurrent neural network patterns.](../../../../../translated_images/unreasonable-effectiveness-of-rnn.541ead816778f42d.pcm.jpg) +![Image showing common recurrent neural network patterns.](../../../../../translated_images/pcm/unreasonable-effectiveness-of-rnn.541ead816778f42d.webp) > *Image na from [dis blog post](http://karpathy.github.io/2015/05/21/rnn-effectiveness/) by [Andrej Karpathy](http://karpathy.github.io/). NER token classification models na di right-most network architecture for dis picture.* diff --git a/translations/pcm/lessons/5-NLP/README.md b/translations/pcm/lessons/5-NLP/README.md index 141087df..94d9e386 100644 --- a/translations/pcm/lessons/5-NLP/README.md +++ b/translations/pcm/lessons/5-NLP/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Natural Language Processing -![Summary of NLP tasks in a doodle](../../../../translated_images/ai-nlp.b22dcb8ca4707cea.pcm.png) +![Summary of NLP tasks in a doodle](../../../../translated_images/pcm/ai-nlp.b22dcb8ca4707cea.webp) For dis section, we go focus on how Neural Networks fit handle tasks wey relate to **Natural Language Processing (NLP)**. Plenty NLP problems dey wey we wan make computer sabi solve: diff --git a/translations/pcm/lessons/6-Other/22-DeepRL/README.md b/translations/pcm/lessons/6-Other/22-DeepRL/README.md index 407afc64..9d7b0925 100644 --- a/translations/pcm/lessons/6-Other/22-DeepRL/README.md +++ b/translations/pcm/lessons/6-Other/22-DeepRL/README.md @@ -34,7 +34,7 @@ You don see modern balancing devices like *Segway* or *Gyroscooters* before? Dem Simplified version of balancing na **CartPole** problem. For CartPole world, we get horizontal slider wey fit move left or right, and di goal na to balance vertical pole on top di slider as e dey move. -a cartpole +a cartpole To create and use dis environment, we need small Python code: diff --git a/translations/pcm/lessons/6-Other/22-DeepRL/lab/README.md b/translations/pcm/lessons/6-Other/22-DeepRL/lab/README.md index 1eb8a384..721baecf 100644 --- a/translations/pcm/lessons/6-Other/22-DeepRL/lab/README.md +++ b/translations/pcm/lessons/6-Other/22-DeepRL/lab/README.md @@ -15,7 +15,7 @@ Lab Work wey come from [AI for Beginners Curriculum](https://github.com/microsof Your work na to train RL agent wey go control [Mountain Car](https://www.gymlibrary.ml/environments/classic_control/mountain_car/) for OpenAI Environment. -Mountain Car +Mountain Car ## Di Environment diff --git a/translations/pcm/lessons/6-Other/23-MultiagentSystems/README.md b/translations/pcm/lessons/6-Other/23-MultiagentSystems/README.md index 1bd0fbd9..78d20f76 100644 --- a/translations/pcm/lessons/6-Other/23-MultiagentSystems/README.md +++ b/translations/pcm/lessons/6-Other/23-MultiagentSystems/README.md @@ -60,7 +60,7 @@ You fit [download](https://ccl.northwestern.edu/netlogo/download.shtml) and inst One good thing about NetLogo na say e get one library of working models wey you fit try. Go **File → Models Library**, and you go see plenty categories of models to choose from. -NetLogo Models Library +NetLogo Models Library > Screenshot of di models library by Dmitry Soshnikov @@ -70,7 +70,7 @@ You fit open one of di models, like **Biology → Flocking**. After you open di model, you go see di main NetLogo screen. Here na sample model wey dey describe di population of wolves and sheep, wey dey depend on finite resources (grass). -![NetLogo Main Screen](../../../../../translated_images/NetLogo-Main.32653711ec1a01b3.pcm.png) +![NetLogo Main Screen](../../../../../translated_images/pcm/NetLogo-Main.32653711ec1a01b3.webp) > Screenshot by Dmitry Soshnikov diff --git a/translations/pcm/lessons/README.md b/translations/pcm/lessons/README.md index a3f3a0da..f79930c9 100644 --- a/translations/pcm/lessons/README.md +++ b/translations/pcm/lessons/README.md @@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA: --> # Overview -![Overview wey dem draw like doodle](../../../translated_images/ai-overview.0857791951d19500.pcm.png) +![Overview wey dem draw like doodle](../../../translated_images/pcm/ai-overview.0857791951d19500.webp) > Sketchnote by [Tomomi Imura](https://twitter.com/girlie_mac) diff --git a/translations/pcm/lessons/X-Extras/X1-MultiModal/README.md b/translations/pcm/lessons/X-Extras/X1-MultiModal/README.md index b06c074b..f6cacfdb 100644 --- a/translations/pcm/lessons/X-Extras/X1-MultiModal/README.md +++ b/translations/pcm/lessons/X-Extras/X1-MultiModal/README.md @@ -15,7 +15,7 @@ Afta transformer models don show say dem fit solve NLP tasks well, people don de Di main idea for CLIP na to fit compare text prompts wit image and check how di image match di prompt. -![CLIP Architecture](../../../../../translated_images/clip-arch.b3dbf20b4e8ed8be.pcm.png) +![CLIP Architecture](../../../../../translated_images/pcm/clip-arch.b3dbf20b4e8ed8be.webp) > *Picture from [this blog post](https://openai.com/blog/clip/)* @@ -29,7 +29,7 @@ Once dem don pre-train di model, we fit give am batch of images and batch of tex Suppose we wan classify images between, say, cats, dogs and humans. For dis case, we fit give di model one image, and series of text prompts: "*a picture of a cat*", "*a picture of a dog*", "*a picture of a human*". For di vector wey get 3 probabilities we go just pick di index wey get di highest value. -![CLIP for Image Classification](../../../../../translated_images/clip-class.3af42ef0b2b19369.pcm.png) +![CLIP for Image Classification](../../../../../translated_images/pcm/clip-class.3af42ef0b2b19369.webp) > *Picture from [this blog post](https://openai.com/blog/clip/)* @@ -53,13 +53,13 @@ Learn more about VQGAN for di [Taming Transformers](https://compvis.github.io/ta One big difference between VQGAN and traditional GAN na say di traditional GAN fit produce better image from any input vector, but VQGAN fit produce image wey no go make sense. So, we need to guide di image creation process well, and CLIP fit help us do dis. -![VQGAN+CLIP Architecture](../../../../../translated_images/vqgan.5027fe05051dfa31.pcm.png) +![VQGAN+CLIP Architecture](../../../../../translated_images/pcm/vqgan.5027fe05051dfa31.webp) To generate image wey match text prompt, we go start wit random encoding vector wey go pass through VQGAN to produce image. Then CLIP go dey use to produce loss function wey go show how di image match di text prompt. Di goal na to reduce dis loss, using back propagation to adjust di input vector parameters. One better library wey dey implement VQGAN+CLIP na [Pixray](http://github.com/pixray/pixray) -![Picture produced by Pixray](../../../../../translated_images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.pcm.png) | ![Picture produced by pixray](../../../../../translated_images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.pcm.png) | ![Picture produced by Pixray](../../../../../translated_images/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.pcm.png) +![Picture produced by Pixray](../../../../../translated_images/pcm/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.2384968e9db8a0d0.webp) | ![Picture produced by pixray](../../../../../translated_images/pcm/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.e0b6495f210a4390.webp) | ![Picture produced by Pixray](../../../../../translated_images/pcm/a_closeup_oil_portrait_of_old_male_teacher_of_math.5362e67aa7fc2683.webp) ----|----|---- Picture wey dem generate from prompt *a closeup watercolor portrait of young male teacher of literature with a book* | Picture wey dem generate from prompt *a closeup oil portrait of young female teacher of computer science with a computer* | Picture wey dem generate from prompt *a closeup oil portrait of old male teacher of mathematics in front of blackboard* diff --git a/translations/te/README.md b/translations/te/README.md index f91ba855..c0537f75 100644 --- a/translations/te/README.md +++ b/translations/te/README.md @@ -1,8 +1,8 @@ [Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](./README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md) -> **స్థానికంగా క్లోన్ చేయదలచుకున్నారా?** +> **స్థానికంగా క్లోన్ చేయాలని ఇష్టం ఉందా?** -> ఈ రిపోజిటరీ 50+ భాషా అనువాదాలను కలిగి ఉంది, ఇది డౌన్‌లోడ్ పరిమాణాన్ని గణనీయంగా పెంచుతుంది. అనువాదాలు లేకుండా క్లోన్ చేయడానికి, స్పార్స్ చెకౌట్ను ఉపయోగించండి: +> ఈ రిపోజిటరీలో 50+ భాషా అనువాదాలు ఉన్నాయి, అవి డౌన్లోడ్ పరిమాణాన్ని గణనీయంగా పెంచుతాయి. అనువాదాలు లేకుండా క్లోన్ చేయడానికి, sparse checkout ఉపయోగించండి: > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git > cd AI-For-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > ``` -> ఇది కోర్సు పూర్తి చేయడానికి అవసరమైన అన్ని వాటినీ Much వేగవంతమైన డౌన్‌లోడ్‌తో మీకు ఇస్తుంది. +> ఇది కోర్సు పూర్తి చేయడానికి మీరు అవసరమైన అన్ని వాటినీ చాలా వేగంగా డౌన్లోడ్ చేసుకునేందుకు సహాయపడుతుంది. -**మీకు అదనపు అనువాద భాషలు కావాలంటే అవి ఇక్కడ [listed](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) ఉన్నాయి** +**మీకు అదనపు అనువాద భాషలు కావాలనుకుంటే అవి ఇక్కడ [list](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) ఉన్నాయి** -## కమ్యూనిటీకి చేరండి +## కమ్యూనిటీలో చేరండి [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -## మీరు నేర్చుకునే విషయాలు +## మీరు ఏమి నేర్చుకోబడతారు -**[కోర్సు మైండ్ మ్యాప్](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** +**[కోర్సు మైండ్‌మ్యాప్](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** -ఈ పాఠ్యాంశంలో, మీరు నేర్చుకుంటారు: +ఈ పాఠ్యక్రమంలో, మీరు నేర్చుకుంటారు: -* "గుడ్ ఓల్డ్" సింబాలిక్ పద్ధతితో పాటు వివిధ ఆర్టిఫిషియల్ ఇంటెలిజెన్స్ దృష్టికోణాలు, అందులో **నాలెడ్జ్ రిప్రజెంటేషన్** మరియు నిర్ణయాత్మకత ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* ఆధునిక AI యొక్క మూలమైన **న్యూరల్ నెట్‌వర్క్స్** మరియు **డీప్ లెర్నింగ్**. ఈ ముఖ్యమైన అంశాల వెనుక కాన్సెప్ట్స్‌ను మేము రెండు అత్యంత ప్రాచుర్యం పొందిన ఫ్రేమ్‌వర్క్స్ - [TensorFlow](http://Tensorflow.org) మరియు [PyTorch](http://pytorch.org)లో కోడ్ ఉపయోగించి వివరిస్తాము. -* చిత్రాలు మరియు పాఠ్యంతో పనిచేసే **న్యూరల్ ఆర్కిటెక్చర్‌లు**. మేము తాజా నమూనాలను కవర్ చేస్తాము కానీ స్టేట్-ఆఫ్-ది-ఆర్ట్ కొద్దిగా తగ్గి ఉండొచ్చు. -* తక్కువ ప్రాచుర్యం పొందిన AI దృష్టికోణాలు, ఉదా: **జెనటిక అల్గోరిథమ్స్** మరియు **మల్టీ-ఏజెంట్ సిస్టమ్స్**. +* కృత్రిమ మేధస్సు పట్ల వివిధ దృష్టికోణాలు, వాటిలో “పాత నాణ్యమైన” చిహ్నాత్మక దృష్టికోణం మరియు **జ్ఞాన ప్రతినిధిత్వం** మరియు తర్కశక్తి ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* ఆధునిక AIలో ప్రస్థానమైన **న్యూరల్ నెట్‌వర్క్స్** మరియు **డీప్ లెర్నింగ్**. మేము ఈ ముఖ్యమైన అంశాల వెనుక ఉన్న భావాలను రెండు ప్రముఖ ఫ్రేమ్‌వర్క్లు - [TensorFlow](http://Tensorflow.org) మరియు [PyTorch](http://pytorch.org) లో కోడ్‌తో వివరించబోతున్నాము. +* చిత్రాలు మరియు వచనంతో పని చేసే **న్యూరల్ గঠনరచనలు**. మేము తాజా నమూనాలను కవర్ చేస్తాము కానీ అత్యాధునిక స్థాయిలో కొంత తొందర పోవచ్చు. +* తక్కువ ప్రాచుర్యం ఉన్న AI పద్ధతులు, ఉదాహరణకు **జెనెటిక్ అల్గోరిథమ్స్** మరియు **మల్టీ-ఏజెంట్ సిస్టమ్స్**. -ఈ పాఠ్యాంశంలో మేము కవర్ చేయని విషయాలు: +ఈ పాఠ్యక్రమంలో మేము కవర్ చేయనిదే: -> [ఈ కోర్సు యొక్క అదనపు వనరులను మా Microsoft Learn సేకరణలో చూడండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) +> [ఈ కోర్సుకు సంబంధించిన అన్ని అదనపు వనరులను మా Microsoft Learn సేకరణలో చూడండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* **వ్యాపారంలో AI ఉపయోగించే వ్యాపార సందర్భాలు**. Microsoft Learnలోని [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) అనే లెర్నింగ్ పాత్ తీసుకోండి లేదా [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), ఇది [INSEAD](https://www.insead.edu/)తో సమన్వయంతో అభివృద్ధి చేయబడింది. -* **క్లాసిక్ మెషీన్ లెర్నింగ్**, ఇది మా [Machine Learning for Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners)లో బాగా వివరించబడింది. -* **[కగ్నిటివ్ సర్వీసెస్](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** ఉపయోగించి నిర్మించిన ప్రాక్టికల్ AI అనువర్తనాలు. దీని కోసం, మేము Microsoft Learnలో [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Azure OpenAI Serviceతో జనరేటివ్ AI](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** మరియు ఇతర మాడ్యూల్ల నుంచి మొదలుపెట్టాలని సూచిస్తాము. -* నిర్దిష్ట ML **క్లౌడ్ ఫ్రేమ్‌వర్క్స్**, ఉదా: [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), లేదా [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). మీరు [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) మరియు [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పాత్‌లను ఉపయోగించవచ్చు. -* **కంటెస్టేషనల్ AI** మరియు **చాట్ బాట్స్**. దీనికి ప్రత్యేక [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పాత్ ఉంది, అలాగే మరిన్ని వివరాలకు [ఈ బ్లాగ్ పోస్టును](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) చూడండి. -* డీప్ లెర్నింగ్ వెనుక **గాఢమైన గణితం**. దీని కోసం, మేము [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) అనే ఇయాన్ గూడ్‌ఫెలో, యోషువా బెంగియో మరియు ఆహరాన్ కౌర్విల్ రచించిన పుస్తకాన్ని సిఫార్సు చేస్తున్నాము, ఇది ఆన్‌లైన్లో కూడా అందుబాటులో ఉంది: [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) . +* **AIని వ్యాపారంలో ఉపయోగించే** వ్యాపార కేసులు. దయచేసి [వ్యాపార వినియోగదారుల కోసం AI పరిచయం](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) Microsoft Learnలో లేదా [AI బిజినెస్ స్కూల్](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum) తీసుకొనండి, ఇది [INSEAD](https://www.insead.edu/)తో సహకారంతో అభివృద్ధి చేయబడింది. +* మన [మషీన్ లెర్నింగ్ ఫర్ బిగ్నర్స్ పాఠ్యక్రమంలో](http://github.com/Microsoft/ML-for-Beginners) సుపరిచితమైన **క్లాసిక్ మెషీన్ లెర్నింగ్**. +* **[కాగ్నిటివ్ సర్వీసెస్](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** ఉపయోగించి గణనీయ AI అనువర్తనాలు. దీనికి, Microsoft Learnలోని [విషన్](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [ప్రాకృత భాషా ప్రాసెసింగ్](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Azure OpenAI సేవతో జనరేటివ్ AI](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** మరియు ఇతర మాడ్యూల్స్‌ను ప్రారంభించడం సిఫార్సు చేస్తాము. +* [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), లేదా [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum) వంటి ప్రత్యేక ML **క్లౌడ్ ఫ్రేమ్‌వర్క్స్**. [Azure Machine Learningతో మిషీన్ లెర్నింగ్ పరిష్కారాలను నిర్మించడం మరియు నిర్వహించడం](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) మరియు [Azure Databricksతో మిషీన్ లెర్నింగ్ పరిష్కారాలను నిర్మించడం, నిర్వహించడం](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పథాలను ఉపయోగించడం పరిగణించండి. +* **సంభాషణాత్మక AI** మరియు **చాట్ బాట్లు**. ఒక వేర్వేరు [సంభాషణాత్మక AI పరిష్కారాలను సృష్టించడం](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పథం ఉంది, అలాగే మరిన్ని వివరాలకు [ఈ బ్లాగ్ పోస్ట్](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) చూడవచ్చు. +* డీప్ లెర్నింగ్ వెనుక **గణితశాస్త్రం**. దీనికి, ఇయాన్ గూడ్‌ఫెల్లో, యోషువా బెంగియో మరియు ఆరాన్ కుర్విల్ రచించిన [డీప్ లెర్నింగ్](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) పుస్తకాన్ని సిఫార్సు చేస్తాము, ఇది ఆన్‌లైన్‌లో కూడా అందుబాటులో ఉంది [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -క్లౌడ్‌లో AIకి సరళమైన పరిచయం కోసం మీరు [Azureలో కళात्मक మేధస్సుతో ప్రారంభించండి](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పాత్ తీసుకోవచ్చు. +_కృత్రిమ మేధస్సు క్లౌడ్‌లో_ మొదటి పరిచయానికి, మీరు [Azureలో కృత్రిమ మేధస్సుతో మొదలుపెట్టడం](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) లెర్నింగ్ పథం తీసుకోవచ్చు. -# విషయాలు +# విషయ సూచిక -| | పాఠం లింక్ | PyTorch/Keras/TensorFlow | ప్రయోగశాల | +| | పాఠం లింక్ | PyTorch/Keras/TensorFlow | ప్రయోగశాల | | :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | | 0 | [కోర్సు సెటప్](./lessons/0-course-setup/setup.md) | [మీ అభివృద్ధి వాతావరణాన్ని సెటప్ చేయండి](./lessons/0-course-setup/how-to-run.md) | | -| I | [**AIకి పరిచయం**](./lessons/1-Intro/README.md) | | | +| I | [**AI పరిచయం**](./lessons/1-Intro/README.md) | | | | 01 | [AI పరిచయం మరియు చరిత్ర](./lessons/1-Intro/README.md) | - | - | -| II | **సింబాలిక్ AI** | -| 02 | [నాలెడ్జ్ రిప్రజెంటేషన్ మరియు ఎక్స్‌పర్ట్ సిస్టమ్స్](./lessons/2-Symbolic/README.md) | [ఎక్స్‌పర్ట్ సిస్టమ్స్](./lessons/2-Symbolic/Animals.ipynb) / [ఆంటాలజీ](./lessons/2-Symbolic/FamilyOntology.ipynb) /[కాన్సెప్టు గ్రాఫ్](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | -| III | [**న్యూరల్ నెట్‌వర్క్స్‌కు పరిచయం**](./lessons/3-NeuralNetworks/README.md) ||| -| 03 | [పర్సెప్ట్రాన్](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [నోట్బుక్](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [ప్రయోగశాల](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | -| 04 | [బహుస్థాయి పర్సెప్ట్రాన్ మరియు మన సొంత ఫ్రేమ్‌వర్క్ సృష్టించడం](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [నోట్బుక్](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [ప్రయోగశాల](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | -| 05 | [ఫ్రేమ్‌వర్క్‌లకు పరిచయం (PyTorch/TensorFlow) మరియు అధిగమింపు](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [ప్రయోగశాల](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | -| IV | [**కంప్యూటర్ విజన్**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [మైక్రోసాఫ్ట్ Azureపై కంప్యూటర్ విజన్ అన్వేషించండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | -| 06 | [కంప్యూటర్ విజన్‌కి పరిచయం. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [నోట్బుక్](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [ప్రయోగశాల](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | -| 07 | [కన్వల్యూషనల్ న్యూరల్ నెట్‌వర్క్‌లు](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN ఆర్కిటెక్చర్స్](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [ప్రయోగశాల](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) | -| 08 | [ముందుగా శిక్షణ పొందిన నెట్‌వర్క్‌లు మరియు ట్రాన్స్ఫర్ లెర్నింగ్](./lessons/4-ComputerVision/08-TransferLearning/README.md) మరియు [శిక్షణ చిట్కాలు](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [ప్రయోగశాల](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | -| 09 | [ఆటోఎంకోడర్లు మరియు VAEలు](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | | -| 10 | [జనరేటివ్ అడ్వర్శరియల్ నెట్‌వర్క్‌లు & కళాత్మక శైలి బదిలీ](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | -| 11 | [వస్తు గుర్తింపు](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [ప్రయోగశాల](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | -| 12 | [సెమాంటిక్ సెగ్మెంటేషన్. U-నెట్](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | | -| V | [**ప్రাকృత భాషా ప్రక్రియ**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [మైక్రోసాఫ్ట్ Azureపై ప్రకృత భాషా ప్రక్రియను అన్వేషించండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| -| 13 | [పాఠ్య ప్రతినిధ్యత. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | | +| II | **చిహ్నాత్మక AI** | +| 02 | [జ్ఞాన ప్రతినిధిత్వం మరియు నిపుణుల వ్యవస్థలు](./lessons/2-Symbolic/README.md) | [నిపుణుల వ్యవస్థలు](./lessons/2-Symbolic/Animals.ipynb) / [ఆంటాలజీ](./lessons/2-Symbolic/FamilyOntology.ipynb) /[కాన్సెప్ట్ గ్రాఫ్](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | +| III | [**న్యూరల్ నెట్‌వర్క్స్ పరిచయం**](./lessons/3-NeuralNetworks/README.md) ||| +| 03 | [పర్సెప్ట్రాన్](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [నోట్‌బుక్](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [ల్యాబ్](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | +| 04 | [మల్టీ-లేయర్డ్ పర్సెప్ట్రాన్ మరియు మనం సొంత ఫ్రేమ్‌వర్క్ సృష్టించడం](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [నోట్‌బుక్](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [ల్యాబ్](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | +| 05 | [ఫ్రేమ్‌వర్క్లు పరిచయం (PyTorch/TensorFlow) మరియు ఓవర్‌ఫిట్టింగ్](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [ల్యాబ్](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | +| IV | [**కంప్యూటర్ విజన్**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Microsoft Azure మీద కంప్యూటర్ విజన్ అన్వేషించండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | +| 06 | [కంప్యూటర్ విజన్ ప్రవేశం. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [నోట్‌బుక్](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [ల్యాబ్](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | +| 07 | [కన్వల్యూషనల్ న్యూరల్ నెట్‌వర్క్స్](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN నిర్మాణాలు](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [ల్యాబ్](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) | +| 08 | [ముందుగా శిక్షణ పొందిన నెట్‌వర్క్లు మరియు ట్రాన్స్ఫర్ లెర్నింగ్](./lessons/4-ComputerVision/08-TransferLearning/README.md) మరియు [శిక్షణ ట్రిక్స్](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [ల్యాబ్](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | +| 09 | [ఆటోఎంకోడర్స్ మరియు VAEs](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | | +| 10 | [జనరేటివ్ అద్వర్సరియల్ నెట్‌వర్క్స్ & ఆర్టిస్టిక్ స్టైల్ ట్రాన్స్ఫర్](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | +| 11 | [వస్తువు గుర్తింపు](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [ల్యాబ్](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | +| 12 | [సెమాంటిక్ స_SEGMENTATION. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | | +| V | [**స్వభావిక భాషా ప్రాసెసింగ్**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Microsoft Azureపై స్వభావిక భాషా ప్రాసెసింగ్ అన్వేషించండి](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| +| 13 | [పాఠ్య ప్రాతినిధ్యం. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | | | 14 | [సెమాంటిక్ పదం ఎంబెడ్డింగ్స్. Word2Vec మరియు GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | | -| 15 | [భాషా మోడలింగ్. మీ సొంత ఎంబెడ్డింగ్స్ శిక్షణ](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [ప్రయోగశాల](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | -| 16 | [రెకర런్ట్ న్యూరల్ నెట్‌వర్క్‌లు](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | | -| 17 | [జనరేటివ్ రికర్రెంట్ నెట్‌వర్క్‌లు](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [ప్రయోగశాల](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) | -| 18 | [ట్రాన్స్‌ఫార్మర్‌లు. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | | -| 19 | [పేరు గుర్తింపు](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [ప్రయోగశాల](./lessons/5-NLP/19-NER/lab/README.md) | -| 20 | [పెద్ద భాషా మోడల్‌లు, ప్రాంప్ట్ ప్రోగ్రామింగ్ మరియు కొద్దిగా-శిక్షణ టాస్క్‌లు](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | +| 15 | [భాషా మోడలింగ్. మీ సొంత ఎంబెడ్డింగ్స్ శిక్షణ](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [ల్యాబ్](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | +| 16 | [రికరెంట్ న్యూరల్ నెట్‌వర్క్స్](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | | +| 17 | [జనరేటివ్ రికరెంట్ నెట్‌వర్క్స్](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [ల్యాబ్](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) | +| 18 | [ట్రాన్స్‌ఫార్మర్స్. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | | +| 19 | [నేమ్డ్ ఎంటిటీ రికగ్నిషన్](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [ల్యాబ్](./lessons/5-NLP/19-NER/lab/README.md) | +| 20 | [పెద్ద భాషా మోడల్స్, ప్రాంప్ట్ ప్రోగ్రామింగ్ మరియు ఫ్యూషాట్ టास్కులు](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | | VI | **ఇతర AI సాంకేతికతలు** || | -| 21 | [జెనెటిక్ అల్గోరిథమ్స్](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [నోట్బుక్](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | -| 22 | [డీప్ రీన్ఫోర్స్మెంట్ లెర్నింగ్](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [ప్రయోగశాల](./lessons/6-Other/22-DeepRL/lab/README.md) | -| 23 | [బహు-ఏజెంట్ వ్యవస్థలు](./lessons/6-Other/23-MultiagentSystems/README.md) | | | +| 21 | [జెనెటికల్ ఆల్గోరిధమ్స్](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [నోట్‌బుక్](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | +| 22 | [డీప్ రీఇన్ఫోర్స్‌మెంట్ లెర్నింగ్](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [ల్యాబ్](./lessons/6-Other/22-DeepRL/lab/README.md) | +| 23 | [మల్టీ-ఏజెంట్ వ్యవస్థలు](./lessons/6-Other/23-MultiagentSystems/README.md) | | | | VII | **AI నైతికతలు** | | | -| 24 | [AI నైతికతలు మరియు బాధ్యతాయుక్త AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: బాధ్యతాయుక్త AI సിദ്ധాంతాలు](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | -| IX | **అదనపు విషయాలు** | | | -| 25 | [బహుముఖ నెట్‌వర్క్‌లు, CLIP మరియు VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [నోట్బుక్](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | +| 24 | [AI నైతికతలు మరియు బాధ్యతాయుతమైన AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: బాధ్యతాయుతమైన AI ప్రిన్సిపుల్స్](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | +| IX | **అమరికలు** | | | +| 25 | [మల్టీ-మోడల్ నెట్‌వర్క్స్, CLIP మరియు VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [నోట్‌బుక్](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | -## ప్రతి పాఠంలో ఉండే అంశాలు +## ప్రతి పాఠం లో ఉన్నాయి -* ముందస్తు చదవలసిన సామగ్రి -* అమలు చేయగల జూపిటర్ నోట్బువుక్స్, ఇవి తరచుగా ఫ్రేమ్‌వర్క్ క్రింద ప్రత్యేకంగా ఉంటాయి (**PyTorch** లేదా **TensorFlow**). అమలు చేయగల నోట్బుక్‌లో చాలా స 이త్యపు విషయం కూడా ఉంటుంది, కాబట్టి విషయాన్ని అర్థం చేసుకోవడానికి కనీసం ఒక సంస్కరణ (PyTorch లేదా TensorFlow లో) చూడాలి. -* కొన్ని అంశాలకు అందుబాటులో ఉండే **ప్రయోగశాలలు** ఉన్నాయి, ఇవి మీరు నేర్చుకున్న విషయాన్ని ఒక ప్రత్యేక సమస్యకు అన్వయించడానికి అవకాశాన్ని ఇస్తాయి. -* కొంత భాగాల్లో సంబంధిత అంశాలను కవర్ చేసే [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) మాడ్యూల్స్‌కు లింకులు ఉంటాయి. +* ముందస్తు పఠనం పదార్థం +* అమలు చేయదగిన జుపైటర్ నోట్‌బుక్స్, అవి తరచుగా ఫ్రేమ్‌వర్క్ ( **PyTorch** లేదా **TensorFlow** ) కు ప్రత్యేకంగా ఉంటాయి. అమలు నోట్‌బుక్ లో థియరీ పదార్థం కూడా చాలా ఉంటుంది, కాబట్టి విషయం అర్థం చేసుకోవడానికి కనీసం ఒక వెర్షన్ (PyTorch లేదా TensorFlow) ను చూడాలి. +* కొంత విషయాలకు **ల్యాబ్స్** అందుబాటులో ఉంటాయి, అవి మీరు నేర్చుకున్న పదార్థం ను ఒక నిర్దిష్ట సమస్యపై ప్రయోగించేందుకు అవకాశం ఇస్తాయి. +* కొన్ని విభాగాలు సంబంధిత అంశాలను కవర్ చేసే [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) మాడ్యూల్స్ కు లింకులు కలిగి ఉంటాయి. -## ప్రారంభించడానికి +## ప్రారంభం -### 🎯 AI కొత్తదా? ఇక్కడ ప్రారంభించండి! +### 🎯 AIలో కొత్తవారా? ఇక్కడ నుండి ప్రారంభించండి! -మీరు పూర్తిగా AI కొత్తవారు అయితే మరియు తక్షణం, చేతితో చేయగలిగే ఉదాహరణలు కావాలంటే, మా [**ప్రారంభికుల అనుకూల ఉదాహరణలు**](./examples/README.md) చూడండి! ఇవి ఉన్నాయి: +మీరు పూర్తిగా AI కొత్తవారిగా ఉంటే మరియు వేగంగా, ప్రయోగాత్మక ఉదాహరణలు చూచాలనుకుంటే, మా [**ప్రారంభకులకు అనుకూల ఉదాహరణలు**](./examples/README.md) ను చూడండి! ఇవి కలిగి ఉంటాయి: -- 🌟 **హలో AI వరల్డ్** - మీ మొదటి AI ప్రోగ్రాం (ప్యాటర్న్ గుర్తింపు) -- 🧠 **సాదా న్యూరల్ నెట్‌వర్క్** - మొదలు నుండి న్యూరల్ నెట్‌వర్క్ నిర్మించండి -- 🖼️ **చిత్ర శ్రేణీకరణ** - వివరమైన వ్యాఖ్యలతో చిత్రాలను వర్గీకరించండి -- 💬 **పాఠ్య భావం** - పాజిటివ్/నెగటివ్ టెక్స్ట్ విశ్లేషణ +- 🌟 **హలో AI వరల్డ్** - మీ మొదటి AI ప్రోగ్రామ్ (నమూనా గుర్తింపు) +- 🧠 **సాధారణ న్యూరల్ నెట్‌వర్క్** - మొదటి నుండీ న్యూరల్ నెట్‌వర్క్ నిర్మించండి +- 🖼️ **చిత్ర వర్గీకర్త** - విపుల వ్యాఖ్యలతో చిత్రాలను వర్గీకరించండి +- 💬 **పాఠ్య నిర్వహణ భావన** - సానుకూల / ప్రతిస్కూల పాఠ్యాన్ని విశ్లేషించండి -ఈ ఉదాహరణలు మీరు పూర్తి పాఠ్యాంశాన్ని ప్రారంభించడానికి ముందు AI సంకల్పనలను అర్థం చేసుకోవడానికి రూపొందించబడ్డాయి. +ఈ ఉదాహరణలు మీరు పూర్తి కోర్సును ప్రారంభించడానికి ముందుగా AI מושגים ను అర్థం చేసుకోవడంలో సహాయపడేందుకు రూపొందించబడినవి. -### 📚 పూర్తి పాఠ్యాంశం సెటప్ +### 📚 పూర్తి పాఠ్యక్రమం అమరిక -- మేము మీ అభివృద్ధి పరిసరాన్ని సెటప్ చేయడంలో సహాయపడటానికి [సెటప్ పాఠం](./lessons/0-course-setup/setup.md) రూపొందించాము. - ఉపాధ్యాయుల కోసం, మేము మీకోసం కూడా ఒక [పాఠ్యాంశం సెటప్ పాఠం](./lessons/0-course-setup/for-teachers.md) రూపొందించాము! -- VSCode లేదా Codepace లో [కోడ్ ఎలా నడుపాలి](./lessons/0-course-setup/how-to-run.md) +- మేము మీ అభివృద్ధి వాతావరణం అమరిక కోసం [సెట్టప్ పాఠం](./lessons/0-course-setup/setup.md) సృష్టించాము. - విద్యాసంస్థలకు, మేము మీ కోసం ఒక [పాఠ్యక్రమ అమరిక పాఠం](./lessons/0-course-setup/for-teachers.md) కూడా రూపొందించాము! +- [VSCode లేదా Codespace లో కోడ్ ఎలా నడిపించాలి](./lessons/0-course-setup/how-to-run.md) -ఈ దశలను అనుసరించండి: +ఈ దశలనుఇ అనుసరించండి: -రిపాజిటరీని ఫోర్క్ చేయండి: ఈ పేజీ పై-కుడివైపు ఉన్న "Fork" బటన్ పై క్లిక్ చేయండి. +Repository ని Fork చేయండి: ఈ పేజీపై ఎడమ-పైన ఉన్న "Fork" బటన్ పై క్లిక్ చేయండి. -రిపాజిటరీని క్లోన్ చేయండి: `git clone https://github.com/microsoft/AI-For-Beginners.git` +Repository Clone చేయండి: `git clone https://github.com/microsoft/AI-For-Beginners.git` -తరువాత దీన్ని సులభంగా కనుగొనడానికి ఈ రిపోకు స్టార్ (🌟) ఇవ్వండి. +తరువాత ఈ రిపోను సులభంగా కనుగొనడానికి స్టార్ (🌟) చేయడం మర్చిపోకండి. -## ఇతర విద్యార్థులతో కలుసుకోండి +## ఇతర అభ్యసకులతో కలవండి -ఈ కోర్సు తీసుకుంటున్న ఇతర విద్యార్థులతో కలుసుకోవడం మరియు నెట్‌వర్క్ చేయడానికి మా [ అధికారిక AI Discord సర్వర్](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) లో చేరండి మరియు మద్దతు పొందండి. +ఈ కోర్సు నేర్చుకుంటున్న ఇతర అభ్యసకులతో కలవడానికి మరియు నెట్‌వర్క్ చేయడానికి మా [అధికారిక AI Discord సర్వర్](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) లో చేరండి మరియు మద్దతు పొందండి. -మీరు ఉత్పత్తి ప్రతిపాదనలు లేదా ప్రశ్నలు ఉన్నట్లయితే, మా [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) కు వెళ్ళండి. +మీకు ఉత్పత్తి అభిప్రాయం లేదా ప్రశ్నలుంటే మా [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) ను సందర్శించండి ## క్విజ్‌లు -> **క్విజ్‌ల గురించీ ఒక గమనిక**: అన్ని క్విజ్‌లు etc\quiz-app ఫోల్డర్‌లో Quiz-app లో ఉన్నాయి, లేదా [ఆన్లైన్ ఇక్కడ](https://ff-quizzes.netlify.app/) వీటిని పాఠాల్లోనుండి లింక్ చేస్తారు. క్విజ్ యాప్ లోకల్ గా నడపవచ్చు లేదా Azure లో డిప్లాయ్ చేయవచ్చు; `quiz-app` ఫోల్డర్ లో సూచనలను అనుసరించండి. ఇవి తరచుగా ప్రాంతీయీకరించబడుతున్నాయి. +> **క్విజ్‌ల గురించి ఒక గమనిక**: అన్ని క్విజ్‌లు Quiz-app ఫోల్డర్ లో etc\quiz-app లో ఉంటాయి లేదా [ఆన్‌లైన్ ఇక్కడ](https://ff-quizzes.netlify.app/) లభ్యం. అవి పాఠ్యాల్లోనుంచి లింక్ గా ఉంటాయి. Quiz appని స్థానికంగా నడపవచ్చు లేదా Azureపై అమలు చేయవచ్చు; `quiz-app` ఫోల్డర్ లో ఇచ్చిన సూచనలు అనుసరించండి. అవి దశల వారీగా స్థానికీకరించబడుతున్నాయి. -## సహాయం అవసరం +## సహాయం కావాలి -మీ దగ్గర సూచనలు లేదా వ్రాతపుడులు లేదా కోడ్ పాఠ్య తప్పిదాలు కనుగొన్నట్లయితే? ఒక ఇష్యూ ఎత్తండి లేదా పుల్ రిక్వెస్ట్ సృష్టించండి. +మీకు సూచనలు ఉన్నాయా లేదా చదువు పొరపాట్లు లేదా కోడ్ లో లోపాలు కనుగొన్నారా? ఒక ఇష్యూ ఎత్తి లేదా పుల్ రిక్వెస్ట్ సృష్టించండి. ## ప్రత్యేక ధన్యవాదాలు -* **✍️ ప్రాథమిక రచయిత:** [Dmitry Soshnikov](http://soshnikov.com), PhD -* **🔥 ఎడిటర్:** [Jen Looper](https://twitter.com/jenlooper), PhD -* **🎨 స్కెచ్‍నోట్ చిత్రకారిణి:** [Tomomi Imura](https://twitter.com/girlie_mac) -* **✅ క్విజ్ సృష్టికర్త:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) -* **🙏 ప్రాథమిక సహకారులు:** [Evgenii Pishchik](https://github.com/Pe4enIks) +* **✍️ ప్రధాన రచయిత:** [Dmitry Soshnikov](http://soshnikov.com), PhD +* **🔥 ఎడిటర్:** [Jen Looper](https://twitter.com/jenlooper), PhD +* **🎨 స్కెచ్‌నోట్ చిత్రకారుడు:** [Tomomi Imura](https://twitter.com/girlie_mac) +* **✅ క్విజ్ సృష్టికర్త:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) +* **🙏 ప్రధాన సహకారులు:** [Evgenii Pishchik](https://github.com/Pe4enIks) -## ఇతర పాఠ్యాంశాలు +## ఇతర పాఠ్యక్రమాలు -మా టీమ్ ఇతర పాఠ్యాంశాలు కూడా తయారు చేస్తుంది! చూడండి: +మన బృందం ఇతర పాఠ్యక్రమాలు కూడా తయారుచేస్తోంది! చూడండి: ### LangChain @@ -190,7 +189,7 @@ CO_OP_TRANSLATOR_METADATA: --- -### Generative AI సిరీస్ +### Generative AI Series [![Generative AI for Beginners](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) @@ -198,36 +197,36 @@ CO_OP_TRANSLATOR_METADATA: --- -### కోర్ లెర్నింగ్ +### Core Learning [![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![డేటా సైన్స్ ఫర్ బిగినర్స్](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) [![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![సైబర్‌సెక్యూరిటీ ఫర్ బిగినర్స్](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![వెబ్ డెవలప్మెంట్ ఫర్ బిగినర్స్](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) [![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) [![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- -### కోపైలట్ సిరీస్ -[![AI జతగా ప్రోగ్రామింగ్ కోసం కోపైలట్](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![C#/.NET కోసం కోపైలట్](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![కోపైలట్ అడ్వెంచర్](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +### Copilot Series +[![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## సహాయం పొందడం +## సాయం పొందండి -మీరుద్వంద్వ దశలో చిక్కుకున్నట్లయితే లేదా AI యాప్‌లు నిర్మించడంపై ఏదైనా ప్రశ్నలు ఉంటే Fellow learners మరియు అనుభవజ్ఞులైన డెవలపర్లు MCP గురించి చర్చలలో చేరండి. ఇది ప్రశ్నలకు స్వాగతం తెలిపే, జ్ఞానాన్ని స్వేచ్ఛగా పంచుకునే మద్దతు వంతమైన క‌మ్యూనిటీ. +మీరు আটకిపోతే లేదా AI అప్లికేషన్లు నిర్మించే విషయంలో ఏవైనా ప్రశ్నలు ఉంటే MCP గురించి fellow learners మరియు అనుభవజ్ఞుల అభివృద్ధిదారులతో చర్చలలో చేరండి. ఇది ప్రశ్నలు విచారించడానికి మరియు విజ్ఞానాన్ని స్వేచ్ఛగా పంచుకునేందుకు సహాయక సమాజం. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -నిర్మాణ సమయంలో ఉత్పత్తి సూచనలు లేదా తప్పిదాలు ఉంటే సందర్శించండి: +మీకు ఉత్పత్తి అభిప్రాయం లేదా నిర్మాణంలో పിശుకులు ఉంటే సందర్శించండి: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**అస్పష్టం**: -ఈ డాక్యుమెంట్ AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మనం ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో తప్పులు లేదా అసమర్థతలు ఉండవచ్చు. స్థానిక భాషలో ఉన్న అసలు డాక్యుమెంట్‌ను అధికారిక మూలంగా చూడాలి. కీలక సమాచారం కోసం నిపుణుల చేతి అనువాదం చేయించుకోవడం మంచిది. ఈ అనువాదం వాడకం వల్ల ఉద్భవించే ఏవైనా అపార్థాలు లేదా తప్పు అర్థాల కోసం మేము బాధ్యత వహించము. +**వీడ్కోలు**: +ఈ డాక్యుమెంట్‌ను AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించడం జరిగింది. ఖచ్చితత్వాన్ని పాటించడానికి ప్రయత్నించినప్పటికీ, స్వయంచాలక అనువాదాల్లో తప్పులు లేదా అపరిశుద్ధతలు ఉండవచ్చు. అసలు డాక్యుమెంట్ తన స్థానిక భాషలోనే అధికారిక మూలం అని పరిగణించాలి. ముఖ్యమైన సమాచారానికి, నిపుణుల చేతినివసలైన అనువాదం సిఫారసు చేయబడుతుంది. ఈ అనువాదం వాడకం వల్ల ఉత్పన్నమయ్యే ఏవైనా అపార్థాలు లేదా తప్పు అర్థాలు పట్ల మేము బాధ్యత వహించము. \ No newline at end of file diff --git a/translations/te/lessons/0-course-setup/how-to-run.md b/translations/te/lessons/0-course-setup/how-to-run.md index c4d4f5b8..443bacb5 100644 --- a/translations/te/lessons/0-course-setup/how-to-run.md +++ b/translations/te/lessons/0-course-setup/how-to-run.md @@ -1,81 +1,80 @@ - -# కోడ్‌ను ఎలా నడపాలి - -ఈ పాఠ్యాంశంలో మీరు నడపాలనుకునే అనేక అమలు చేయగల ఉదాహరణలు మరియు ప్రయోగశాలలు ఉన్నాయి. దీన్ని చేయడానికి, ఈ పాఠ్యాంశంలో భాగంగా అందించిన Jupyter నోట్బుక్స్‌లో Python కోడ్‌ను అమలు చేసే సామర్థ్యం అవసరం. కోడ్ నడపడానికి మీకు కొన్ని ఎంపికలు ఉన్నాయి: - -## మీ కంప్యూటర్‌లో స్థానికంగా నడపడం - -మీ కంప్యూటర్‌లో కోడ్‌ను స్థానికంగా నడపడానికి, మీరు Python యొక్క ఏదైనా వెర్షన్ ఇన్‌స్టాల్ చేసుకోవాలి. నేను వ్యక్తిగతంగా **[miniconda](https://conda.io/en/latest/miniconda.html)** ఇన్‌స్టాల్ చేయాలని సిఫార్సు చేస్తాను - ఇది తేలికపాటి ఇన్‌స్టాలేషన్, వివిధ Python **వర్చువల్ ఎన్విరాన్మెంట్స్** కోసం `conda` ప్యాకేజ్ మేనేజర్‌ను మద్దతు ఇస్తుంది. - -miniconda ఇన్‌స్టాల్ చేసిన తర్వాత, మీరు రిపోజిటరీని క్లోన్ చేసి ఈ కోర్సు కోసం ఉపయోగించే వర్చువల్ ఎన్విరాన్మెంట్‌ను సృష్టించాలి: - -```bash -git clone http://github.com/microsoft/ai-for-beginners -cd ai-for-beginners -conda env create --name ai4beg --file .devcontainer/environment.yml -conda activate ai4beg -``` - -### Python ఎక్స్‌టెన్షన్‌తో Visual Studio Code ఉపయోగించడం - -ఈ పాఠ్యాంశాన్ని ఉపయోగించడానికి ఉత్తమ మార్గం [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste)లో [Python ఎక్స్‌టెన్షన్](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste)తో తెరవడం. - -> **Note**: మీరు రిపోజిటరీని క్లోన్ చేసి VS Codeలో డైరెక్టరీని ఓపెన్ చేసిన వెంటనే, Python ఎక్స్‌టెన్షన్లను ఇన్‌స్టాల్ చేయమని సూచన వస్తుంది. మీరు పైగా వివరించినట్లుగా miniconda కూడా ఇన్‌స్టాల్ చేయాలి. - -> **Note**: VS Code మీరు రిపోజిటరీని కంటైనర్‌లో మళ్లీ ఓపెన్ చేయమని సూచిస్తే, స్థానిక Python ఇన్‌స్టాలేషన్ ఉపయోగించాలంటే దాన్ని తిరస్కరించాలి. - -### బ్రౌజర్‌లో Jupyter ఉపయోగించడం - -మీ స్వంత కంప్యూటర్‌లో బ్రౌజర్ ద్వారా కూడా Jupyter వాతావరణాన్ని ఉపయోగించవచ్చు. వాస్తవానికి, క్లాసికల్ Jupyter మరియు Jupyter Hub రెండూ ఆటో-కంప్లీషన్, కోడ్ హైలైటింగ్ వంటి సౌకర్యాలతో సౌకర్యవంతమైన అభివృద్ధి వాతావరణాన్ని అందిస్తాయి. - -స్థానికంగా Jupyter ప్రారంభించడానికి, కోర్సు డైరెక్టరీకి వెళ్లి ఈ క్రింది ఆదేశాన్ని అమలు చేయండి: - -```bash -jupyter notebook -``` - లేదా -```bash -jupyterhub -``` - -తర్వాత మీరు `.ipynb` ఫైళ్లలో ఏదైనా ఎంచుకుని, వాటిని తెరవడం ద్వారా పని ప్రారంభించవచ్చు. - -### కంటైనర్‌లో నడపడం - -Python ఇన్‌స్టాలేషన్‌కు ప్రత్యామ్నాయం గా కోడ్‌ను కంటైనర్‌లో నడపవచ్చు. మా రిపోజిటరీలో ప్రత్యేకమైన `.devcontainer` ఫోల్డర్ ఉంది, ఇది ఈ రిపో కోసం కంటైనర్‌ను ఎలా నిర్మించాలో సూచిస్తుంది, అందువల్ల VS Code మీకు కోడ్‌ను కంటైనర్‌లో మళ్లీ ఓపెన్ చేయమని సూచిస్తుంది. దీని కోసం Docker ఇన్‌స్టాలేషన్ అవసరం, మరియు ఇది కొంత క్లిష్టమైనది, కాబట్టి ఇది అనుభవజ్ఞులైన వినియోగదారులకు సిఫార్సు చేయబడుతుంది. - -## క్లౌడ్‌లో నడపడం - -మీరు Python స్థానికంగా ఇన్‌స్టాల్ చేయాలనుకోకపోతే, మరియు మీకు కొన్ని క్లౌడ్ వనరులు అందుబాటులో ఉంటే - కోడ్‌ను క్లౌడ్‌లో నడపడం మంచి ప్రత్యామ్నాయం. మీరు దీన్ని చేయడానికి కొన్ని మార్గాలు ఉన్నాయి: - -* **[GitHub Codespaces](https://github.com/features/codespaces)** ఉపయోగించడం, ఇది GitHubపై మీ కోసం సృష్టించబడిన వర్చువల్ ఎన్విరాన్మెంట్, VS Code బ్రౌజర్ ఇంటర్‌ఫేస్ ద్వారా యాక్సెస్ చేయవచ్చు. మీరు Codespaces యాక్సెస్ ఉంటే, రిపోలో **Code** బటన్‌పై క్లిక్ చేసి, కోడ్స్‌పేస్ ప్రారంభించి, వెంటనే నడపవచ్చు. -* **[Binder](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)** ఉపయోగించడం. [Binder](https://mybinder.org) GitHubలోని కొంత కోడ్‌ను పరీక్షించడానికి ఉచిత కంప్యూటింగ్ వనరులు అందిస్తుంది. ఫ్రంట్ పేజీలో రిపోజిటరీని Binderలో తెరవడానికి ఒక బటన్ ఉంటుంది - ఇది త్వరగా బైండర్ సైట్‌కు తీసుకెళ్తుంది, అక్కడ కంటైనర్ నిర్మించి Jupyter వెబ్ ఇంటర్‌ఫేస్‌ను సజావుగా ప్రారంభిస్తుంది. - -> **Note**: దుర్వినియోగం నివారించడానికి, Binder కొన్ని వెబ్ వనరులకు యాక్సెస్‌ను బ్లాక్ చేస్తుంది. ఇది కొంత కోడ్ పనిచేయకుండా ఉండవచ్చు, ముఖ్యంగా పబ్లిక్ ఇంటర్నెట్ నుండి మోడల్స్ లేదా డేటాసెట్‌లను పొందే కోడ్. మీరు కొన్ని పరిష్కారాలు కనుగొనవలసి ఉంటుంది. అలాగే, Binder అందించే కంప్యూట్ వనరులు చాలా ప్రాథమికమైనవి, కాబట్టి శిక్షణ నెమ్మదిగా జరుగుతుంది, ముఖ్యంగా తర్వాతి క్లిష్టమైన పాఠాల్లో. - -## GPUతో క్లౌడ్‌లో నడపడం - -ఈ పాఠ్యాంశంలోని కొన్ని తర్వాతి పాఠాలు GPU మద్దతుతో చాలా లాభపడతాయి, లేకపోతే శిక్షణ చాలా నెమ్మదిగా జరుగుతుంది. మీరు అనుసరించగల కొన్ని ఎంపికలు ఉన్నాయి, ముఖ్యంగా మీరు [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste) ద్వారా లేదా మీ సంస్థ ద్వారా క్లౌడ్ యాక్సెస్ ఉంటే: - -* [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) సృష్టించి, దానితో Jupyter ద్వారా కనెక్ట్ అవ్వండి. మీరు రిపోను నేరుగా ఆ మెషీన్‌పై క్లోన్ చేసి, నేర్చుకోవడం ప్రారంభించవచ్చు. NC-సిరీస్ VMలకు GPU మద్దతు ఉంటుంది. - -> **Note**: కొన్ని సబ్‌స్క్రిప్షన్లు, Azure for Students సహా, డిఫాల్ట్‌గా GPU మద్దతు ఇవ్వవు. మీరు అదనపు GPU కోర్ల కోసం సాంకేతిక మద్దతు అభ్యర్థన చేయవలసి ఉంటుంది. - -* [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) సృష్టించి, అక్కడ నోట్బుక్ ఫీచర్ ఉపయోగించండి. [ఈ వీడియో](https://azure-for-academics.github.io/quickstart/azureml-papers/)లో రిపోజిటరీని Azure ML నోట్బుక్‌లో ఎలా క్లోన్ చేసి ఉపయోగించాలో చూపిస్తుంది. - -మీరు Google Colab కూడా ఉపయోగించవచ్చు, ఇది కొంత ఉచిత GPU మద్దతుతో వస్తుంది, మరియు Jupyter నోట్బుక్స్‌ను అక్కడ అప్‌లోడ్ చేసి ఒక్కొక్కటిగా అమలు చేయవచ్చు. - ---- - - -**అస్పష్టత**: -ఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో పొరపాట్లు లేదా తప్పిదాలు ఉండవచ్చు. మూల పత్రం దాని స్వదేశీ భాషలోనే అధికారిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారానికి, ప్రొఫెషనల్ మానవ అనువాదం చేయించుకోవడం మంచిది. ఈ అనువాదం వలన కలిగే ఏవైనా అపార్థాలు లేదా తప్పుదారుల బాధ్యత మేము తీసుకోము. + +# కోడ్ ఎలా నడిపించాలి + +ఈ పాఠ్యక్రమం అనేక అమలుచేయగల ఉదాహరణలు మరియు ప్రయోగశాలలను కలిగి ఉంది, మీరు వాటిని నడపాలి అనుకుంటారు. దీని కోసం, ఈ పాఠ్యక్రమం భాగంగా అందించబడిన Jupyter నోట్బుక్స్ లో Python కోడ్ అమలు చేసే సామర్థ్యం అవసరం. కోడ్ నడపడానికి మీకు అనేక ఎంపికలు ఉన్నాయి: + +## మీ కంప్యూటర్లో స్థానికంగా నడపండి + +మీ కంప్యూటర్లో స్థానికంగా కోడ్ నడపడానికి, Python ఇన్‌స్టాలేషన్ అవసరం. ఒక సిఫార్సు **[miniconda](https://conda.io/en/latest/miniconda.html)** ను ఇన్‌స్టాల్ చేయడం - ఇది తేలికపాటి ఇన్‌స్టాలేషన్, మరియు వివిధ Python **వర్చువల్ ఎన్విరాన్‌మెంట్ల** కోసం `conda` ప్యాకేజ్ మేనేజర్ ని మద్దతు ఇస్తుంది. + +miniconda ఇన్‌స్టాల్ చేసిన తర్వాత, రిపాజిటరీని క్లోన్ చేసి ఈ కోर्स్ కోసం ఉపయోగించాల్సిన వర్చువల్ ఎన్విరాన్‌మెంట్ సృష్టించండి: + +```bash +git clone http://github.com/microsoft/ai-for-beginners +cd ai-for-beginners +conda env create --name ai4beg --file .devcontainer/environment.yml +conda activate ai4beg +``` + +### Python ఎక్స్‌టెన్షన్ తో Visual Studio Code ఉపయోగించడం + +ఈ పాఠ్యక్రమాన్ని అత్యుత్తమంగా ఉపయోగించుటకు [Visual Studio Code](http://code.visualstudio.com/?WT.mc_id=academic-77998-cacaste) లో [Python Extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python&WT.mc_id=academic-77998-cacaste) తో తెరవడం ఉత్తమం. + +> **గమనిక**: మీరు రిపాజిటరీని క్లోన్ చేసి VS Code లో డైరెక్టరీని ఓపెన్ చేసిన వెంటనే, ఇది ఆటోమాటిక్ గా Python ఎక్స్టెన్షన్స్ ను ఇన్‌స్టాల్ చేయాలని సూచిస్తుంది. పై విధంగా miniconda ని కూడా ఇన్‌స్టాల్ చేయాలి. + +> **గమనిక**: VS Code మీకు రిపాజిటరీని కంటైనర్‌లో మళ్లీ ఓపెన్ చేయమని సూచిస్తే, స్థానిక Python ఇన్‌స్టాలేషన్ ఉపయోగించాలంటే దాన్ని నిరాకరించాలి. + +### బ్రౌజర్‌లో Jupyter ఉపయోగించడం + +మీ స్వంత కంప్యూటర్లో బ్రౌజర్ నుండి కూడా Jupyter ఎన్విరాన్‌మెంట్ ఉపయోగించవచ్చు. సంప్రదాయ Jupyter, జూపిటర్‌హబ్ రెండూ ఆటో-కంప్లీషన్, కోడ్ హైలైటింగ్ మొదలైన సౌకర్యాలతో ఒక సౌకర్యవంతమైన అభివృద్ధి వాతావరణం అందిస్తాయి. + +స్థానికంగా Jupyter ప్రారంభించటానికి, కోర్సు డైరెక్టరీకి వెళ్ళి ఈ ఆదేశాలను అమలుచేయండి: + +```bash +jupyter notebook +``` +or +```bash +jupyterhub +``` +ఆ తర్వాత మీరు `.ipynb` ఫైల్స్ ఎక్కడైనా వెళ్లి తెరిచి పని ప్రారంభించవచ్చు. + +### కంటైనర్‌లో నడపడం + +Python ఇన్‌స్టాలేషన్ కి మరొక ప్రత్యామ్నాయం కోడ్‌ను కంటైనర్‌లో నడపటం. మా రిపాజిటరీ ప్రత్యేకమైన `.devcontainer` ఫోల్డర్ ని అందిస్తుంది, ఇది ఈ రిపో కాన్‌స్ట్రక్చర్ కోసం కంటైనర్ రూపొందించడానికి సూచనిస్తుందని, VS Code రిపోను కంటైనర్‌లో మళ్లీ ఓపెన్ చేయగల అవకాశం ఇస్తుంది. దీనికి Docker ఇన్‌స్టాలేషన్ అవసరం మరియు ఇది కొంచెం సంక్లిష్టం, కాబట్టి దీన్ని అనుభవజ్ఞులైన వాడుకరులకు ఆహ్వానిస్తున్నాం. + +## క్లౌడ్‌లో నడపడం + +మీరు స్థానికంగా Python ఇన్‌స్టాల్ చేయకూడదని అనుకుంటే, మరియు కొంత క్లౌడ్ వనరులకు ప్రాప్యత ఉంటే - కోడ్‌ను క్లౌడ్‌లో నడపడం ఒక మంచి ప్రత్యామ్నాయం. మీరు ఇది చేయడానికి అనేక మార్గాలు ఉన్నాయి: + +* **[GitHub Codespaces](https://github.com/features/codespaces)** ఉపయోగించడం, ఇది GitHub లో మీ కోసం సృష్టించిన వర్చువల్ ఎన్విరాన్‌మెంట్, VS Code బ్రౌజర్ ఇంటర్‌ఫేస్ ద్వారా యాక్సెసబుల్. మీరు Codespaces కి యాక్సెస్ ఉంటే, రిపోలోని **Code** బటన్ క్లిక్ చేసి, Codespace ప్రారంభించి తక్షణమే నడపవచ్చు. +* **[Binder](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD)** ఉపయోగించడం. [Binder](https://mybinder.org) GitHub లోని కొడ్‌ను పరీక్షించడానికి క్లౌడ్‌లో ఉచిత కంప్యూటింగ్ వనరులను అందిస్తుంది. ముందుభాగపు పేజీలో ఒక బటన్ ఉంటుంది, దానితో రిపాజిటరీని Binder లో ఓపెన్ చేయొచ్చు - ఇది వేగంగా బైండర్ సైటుకు తీసుకెళ్లి, మీకు బ్యాక్‌గ్రౌండ్‌లో కంటైనర్ నిర్మించి Jupyter వెబ్ ఇంటర్‌ఫేస్‌ను ప్రారంభిస్తుంది. + +> **గమనిక**: తప్పుగా ఉపయోగించడం నివారించడానికి, Binder కు కొన్ని వెబ్ వనరుల యాక్సెస్ బ్లాక్ చేయబడింది. ఇది కొంత కోడ్ పనిచేయడానికి నిరోధకమవచ్చు, ముఖ్యంగా ఇండిపబ్లిక్ ఇంటర్నెట్ నుండి మోడల్స్ మరియు/లేదా డేటాసెట్లు పొందే సందర్భంలో. మీరు కొంత పరిష్కారాలు కనుగొంటారు కావచ్చు. అదనంగా, Binder అందించే కంప్యూట్ వనరులు బేసిక్ స్థాయి మాత్రమే, కాబట్టి మందగమన శిక్షణ వేళ్లలో నిబంధన మీరిద్దరు తప్పకుండా నేర్చుకోవాలి. + +## GPU తో క్లౌడ్‌లో నడపడం + +ఈ పాఠ్యక్రమం యొక్క కొంతమంది తరువాతి పాఠాలు GPU మద్దతుతో గణనీయంగా ప్రయోజనం పొందుతాయి. మోడల్ శిక్షణ, ఉదాహరణకి, లేకపోతే బాగా మందగమనంగా ఉంటుంది. మీరు అనుసరించగల కొంత ఎంపికలు ఉన్నాయి, ముఖ్యంగా మీరు క్లౌడ్‌కు యాక్సెస్ ఉంటే [Azure for Students](https://azure.microsoft.com/free/students/?WT.mc_id=academic-77998-cacaste) లేదా మీ సంస్థ ద్వారా: + +* [Data Science Virtual Machine](https://docs.microsoft.com/learn/modules/intro-to-azure-data-science-virtual-machine/?WT.mc_id=academic-77998-cacaste) సృష్టించి Jupyter ద్వారా దానికి కనెక్ట్ అవ్వండి. మీరు ఆ మెషీన్ మీద రిపోను క్లోన్ చేసి, నేర్చుకోవడం ప్రారంభించవచ్చు. NC-సిరీస్ VM లకు GPU మద్దతు ఉంటుంది. + +> **గమనిక**: కొన్ని సబ్‌స్క్రిప్షన్లు, Azure for Students సహా, బాక్స్ బయట GPU మద్దతు ఇవ్వరు. మీరు సాంకేతిక సపోర్ట్ అభ్యర్థనతో అదనపు GPU కోర్ల కోసం అభ్యర్థించవచ్చు. + +* [Azure Machine Learning Workspace](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-cacaste) సృష్టించి అక్కడి నోట్‌బుక్ ఫీచర్ ఉపయోగించండి. [ఈ వీడియో](https://azure-for-academics.github.io/quickstart/azureml-papers/) Azure ML నోట్‌బుక్‌లో రిపాజిటరీని క్లోన్ చేసి ఎలా ఉపయోగించి ప్రారంభించాలో చూపుతుంది. + +మీరు Google Colab కూడా ఉపయోగించవచ్చు, ఇది కొంత ఉచిత GPU మద్దతుతో వస్తుంది, మరియు అక్కడ Jupyter నోట్బుక్స్‌ను ఒక్కొక్కటి అప్లోడ్ చేసి అమలు చేయవచ్చు. + +--- + + +**డిస్క్లెయిమర్**: +ఈ డాక్యుమెంట్‌ను AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ను ఉపయోగించి అనువదించబడింది. మేము సరిగ్గా అనువదించేందుకు గట్టిగా శ్రమిస్తునప్పటికీ, స్వయంచాలక అనువాదాలలో పొరపాట్లు లేదా తప్పులు ఉండవచ్చు అనే విషయాన్ని దయచేసి గమనించండి. అసలు డాక్యుమెంట్ native భాషలో ఉనికివున్న డాక్యుమెంట్‌ను ప్రామాణిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారం కోసం, వృత్తిపరమైన మానవ అనువాదాన్ని సూచిస్తాము. ఈ అనువాదం వలన ఏర్పడే ఏదైనా అవగాహనలు లేదా తప్పు అర్థపరిచయాలకు మేము బాధ్యత వహించము. \ No newline at end of file diff --git a/translations/te/lessons/2-Symbolic/Animals.ipynb b/translations/te/lessons/2-Symbolic/Animals.ipynb index 04733068..d1db78b2 100644 --- a/translations/te/lessons/2-Symbolic/Animals.ipynb +++ b/translations/te/lessons/2-Symbolic/Animals.ipynb @@ -6,25 +6,25 @@ "collapsed": true }, "source": [ - "# జంతు నిపుణుల వ్యవస్థను అమలు చేయడం\n", + "# జంతువుల నిపుణుల వ్యవస్థను అమలు చేయడం\n", "\n", "[AI for Beginners Curriculum](http://github.com/microsoft/ai-for-beginners) నుండి ఒక ఉదాహరణ.\n", "\n", - "ఈ నమూనాలో, కొన్ని శారీరక లక్షణాల ఆధారంగా జంతువును గుర్తించడానికి ఒక సులభమైన జ్ఞానాధారిత వ్యవస్థను అమలు చేస్తాము. ఈ వ్యవస్థను క్రింది AND-OR చెట్టు ద్వారా ప్రదర్శించవచ్చు (ఇది మొత్తం చెట్టు యొక్క ఒక భాగం, మేము సులభంగా మరిన్ని నియమాలను జోడించవచ్చు):\n", + "ఈ నమూనాలో, కొన్ని శారీరక లక్షణాల ఆధారంగా జంతువును నిర్ణయించే సులభమైన జ్ఞానాధారిత వ్యవస్థను అమలు చేస్తాము. ఈ వ్యవస్థను కింద ఉన్న AND-OR చెట్టు ద్వారా ప్రతిబింబించవచ్చు (ఇది మొత్తం చెట్టు భాగమే, మనం సులభంగా మరిన్ని నియమాలను జోడించవచ్చు):\n", "\n", - "![](../../../../translated_images/te/AND-OR-Tree.5592d2c70187f283.webp)\n" + "![](../../../../../../translated_images/te/AND-OR-Tree.5592d2c70187f283.webp)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## మన స్వంత నిపుణుల వ్యవస్థ షెల్ వెనుకబడిన నిర్ధారణతో\n", + "## మన స్వంత నిపుణుల వ్యవస్థ షెల్ బ్యాక్వర్డ్ ఇన్ఫెరెన్స్‌తో\n", "\n", - "ఉత్పత్తి నియమాల ఆధారంగా జ్ఞాన ప్రాతినిధ్యం కోసం ఒక సరళమైన భాషను నిర్వచించడానికి ప్రయత్నిద్దాం. నియమాలను నిర్వచించడానికి Python తరగతులను కీవర్డ్లుగా ఉపయోగిస్తాము. మూడే రకాల తరగతులు ఉంటాయి:\n", - "* `Ask` అనేది వినియోగదారుని అడగవలసిన ప్రశ్నను సూచిస్తుంది. ఇది సాధ్యమైన సమాధానాల సమాహారాన్ని కలిగి ఉంటుంది.\n", - "* `If` అనేది ఒక నియమాన్ని సూచిస్తుంది, ఇది నియమపు విషయాన్ని నిల్వ చేయడానికి ఒక సింటాక్టిక్ షుగర్ మాత్రమే.\n", - "* `AND`/`OR` అనేవి చెట్టు యొక్క AND/OR శాఖలను సూచించే తరగతులు. అవి కేవలం లోపల ఆర్గ్యుమెంట్ల జాబితాను నిల్వ చేస్తాయి. కోడ్ సులభతరం చేయడానికి, అన్ని ఫంక్షనాలిటీని తల్లిదండ్రి తరగతి `Content` లో నిర్వచించబడింది.\n" + "ఉత్పత్తి నియమాలపై ఆధారపడి జ్ఞాన ప్రాతినిధ్యం కోసం ఒక సరళ భాషను నిర్వచించడానికి ప్రయత్నిద్దాం. నియమాలను నిర్వచించడానికి కీవర్డ్లుగా Python తరగతులను ఉపయోగిస్తాము. ప్రధానంగా 3 రకాల తరగతులు ఉంటాయి:\n", + "* `Ask` ఉపయోగించబడేది వినియోగదారునికి అడగాల్సిన ప్రశ్నను సూచించడానికి. ఇందులో సాధ్యమైన సమాధానాల సమాహారం ఉంటుంది.\n", + "* `If` ఒక నియమాన్ని సూచిస్తుంది, ఇది ఆ నియమపు విషయాంశాన్ని నిల్వచేసే సింటాక్టిక్ షుగర్ మాత్రమే\n", + "* `AND`/`OR` చూడండి, ఇవి పామును AND/OR శాఖలను సూచించడానికి తరగతులు. ఇవి కేవలం లోపల ఆర్గ్యుమెంట్ల జాబితాను నిల్వచేస్తాయి. కోడ్ సులభతరం చేసేందుకు, అన్నీ ఫంక్షనాలిటీ మాతృ తరగతి `Content` లో నిర్వచించబడతాయి.\n" ] }, { @@ -66,7 +66,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "మన వ్యవస్థలో, వర్కింగ్ మెమరీలో **గుణం-విలువ జంటలుగా** **వాస్తవాలు** జాబితా ఉంటుంది. జ్ఞానాధారం అనేది ఒక పెద్ద నిఘంటువు లాగా నిర్వచించవచ్చు, ఇది చర్యలను (వర్కింగ్ మెమరీలో చేర్చవలసిన కొత్త వాస్తవాలు) AND-OR వ్యక్తీకరణలుగా వ్యక్తం చేసిన షరతులకు మ్యాప్ చేస్తుంది. అలాగే, కొన్ని వాస్తవాలను `Ask` చేయవచ్చు.\n" + "మన వ్యవస్థలో, పని జ్ఞాపకం **ఫ్యాక్ట్స్** జాబితాను **గుణము-విలువ జంటలుగా** కలిగి ఉంటుంది. జ్ఞానాధారం అనేది ఒక పెద్ద నిఘంటువు అని నిర్వచించవచ్చు, ఇది చర్యలు (పని జ్ఞాపకంలో చేర్చాల్సిన కొత్త ఫ్యాక్ట్స్) ను షరతులతో మ్యాప్ చేస్తుంది, అవి AND-OR వ్యక్తీకరణల రూపంలో ఉంటాయి. అలాగే, కొన్ని ఫ్యాక్ట్స్ ని `Ask` చేయవచ్చు.\n" ] }, { @@ -99,13 +99,13 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "వెనుకకు సూచన చేయడానికి, మనం `Knowledgebase` క్లాస్‌ను నిర్వచిస్తాము. ఇది కలిగి ఉంటుంది:\n", - "* పని చేసే `memory` - లక్షణాలను విలువలకు మ్యాప్ చేసే డిక్షనరీ\n", - "* పైగా నిర్వచించిన ఫార్మాట్‌లో ఉన్న Knowledgebase `rules`\n", + "వెనుకబడిన భావనను నిర్వహించడానికి, మనం `Knowledgebase` తరగతిని నిర్వచించబోతున్నాము. ఇది కలిగి ఉంటుంది:\n", + "* పని `memory` - లక్షణాలను విలువలకు మ్యాప్ చేసే డిక్షనరీ\n", + "* పై పేర్కొన్న ఫార్మాట్‌లో ఉన్న Knowledgebase `rules`\n", "\n", "రెండు ప్రధాన విధానాలు:\n", - "* `get` ఒక లక్షణం యొక్క విలువను పొందడానికి, అవసరమైతే సూచన చేస్తుంది. ఉదాహరణకు, `get('color')` రంగు స్లాట్ యొక్క విలువను పొందుతుంది (అవసరమైతే అడుగుతుంది, మరియు తరువాత ఉపయోగానికి పని చేసే మెమరీలో విలువను నిల్వ చేస్తుంది). మనం `get('color:blue')` అడిగితే, అది రంగును అడిగి, ఆ రంగు ఆధారంగా `y`/`n` విలువను ఇస్తుంది.\n", - "* `eval` వాస్తవ సూచనను నిర్వహిస్తుంది, అంటే AND/OR ట్రీని దాటుతూ, ఉప-లక్ష్యాలను మూల్యాంకనం చేస్తుంది, మొదలైనవి.\n" + "* విలువను పొందడానికి `get`, అవసరమైతే భావనను నడుపుతుంది. ఉదాహరణకు, `get('color')` రంగు స్థానం విలువను పొందుతుంది (అవసరమైతే అడుగుతుంది, మరియు తర్వాత ఉపయోగానికి పని మెమరీలో విలువను నిల్వ చేస్తుంది). మనం `get('color:blue')` అడిగితే, అది రంగును అడుగుతుంది, తరువాత రంగుపై ఆధారంగా `y`/`n` విలువను ఇస్తుంది.\n", + "* `eval` వాస్తవ భావనను నిర్వహిస్తుంది, అంటే AND/OR వృక్షాన్ని అన్వేషించి, ఉప-గోల్స్‌ను మూల్యాంకనం చేస్తుంది, మరియు ఇతర చర్యలు పొందుతుంది.\n" ] }, { @@ -172,7 +172,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "ఇప్పుడు మన జంతు జ్ఞానాధారాన్ని నిర్వచించి సంప్రదింపును నిర్వహిద్దాం. ఈ కాల్ మీకు ప్రశ్నలు అడుగుతుంది. అవును-కాదు ప్రశ్నలకు మీరు `y`/`n` టైప్ చేసి సమాధానం ఇవ్వవచ్చు, లేదా ఎక్కువ ఎంపికలున్న ప్రశ్నలకు 0..N సంఖ్యను పేర్కొనవచ్చు.\n" + "ఇప్పుడు మన జంతు జ్ఞానాధారాన్ని నిర్వచించి సంప్రదింపును జరపుదాం. ఈ కాల్ మీకు కొన్ని ప్రశ్నలు అడగనుంది. అవును-కాదు ప్రశ్నలకు మీరు `y`/`n` టైప్ చేసి సమాధానం ఇవ్వవచ్చు, లేదా విస్తృత ప్రమేయాలున్న ప్రశ్నల కోసం సంఖ్య (0..N) సూచించవచ్చు.\n" ] }, { @@ -229,11 +229,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## ఫార్వర్డ్ ఇన్ఫరెన్స్ కోసం PyKnow ఉపయోగించడం\n", + "## ఫార్వర్డ్ ఇన్ఫరెన్స్ కోసం Experta ఉపయోగించడం\n", "\n", - "తరువాతి ఉదాహరణలో, జ్ఞాన ప్రాతినిధ్యం కోసం ఉన్న లైబ్రరీలలో ఒకటి అయిన [PyKnow](https://github.com/buguroo/pyknow/) ఉపయోగించి ఫార్వర్డ్ ఇన్ఫరెన్స్‌ను అమలు చేయడానికి ప్రయత్నిస్తాము. **PyKnow** అనేది Pythonలో ఫార్వర్డ్ ఇన్ఫరెన్స్ సిస్టమ్స్ సృష్టించడానికి ఉపయోగించే లైబ్రరీ, ఇది పాత క్లాసికల్ సిస్టమ్ [CLIPS](http://www.clipsrules.net/index.html)కి సమానంగా రూపొందించబడింది.\n", + "తదుపరి ఉదాహరణలో, జ్ఞాన ప్రాతినిధ్యం కోసం లైబ్రరీలలో ఒకటైన [Experta](https://github.com/nilp0inter/experta) ఉపయోగించి ఫార్వర్డ్ ఇన్ఫరెన్స్‌ను అమలు చేయడానికి ప్రయత్నిస్తాము. **Experta** అనేది Python లో ఫార్వర్డ్ ఇన్ఫరెన్స్ సిస్టమ్లను సృష్టించడానికి ఉపయోగించే లైబ్రరీ, ఇది సాంప్రదాయాత్మక పాత సిస్టమ్ [CLIPS](http://www.clipsrules.net/index.html) కు చాలా సమానంగా ఉండేలా రూపొందించబడింది.\n", "\n", - "మనం ఫార్వర్డ్ చైనింగ్‌ను స్వయంగా కూడా అమలు చేయవచ్చు, కానీ సాధారణ అమలు పద్ధతులు ఎక్కువగా సమర్థవంతంగా ఉండవు. మరింత సమర్థవంతమైన రూల్ మ్యాచ్ చేయడానికి ప్రత్యేక అల్గోరిథం [Rete](https://en.wikipedia.org/wiki/Rete_algorithm) ఉపయోగిస్తారు.\n" + "మేము కూడా ఫార్వర్డ్ చైనింగ్‌ను స్వయంగా ఏమీ పెద్ద తంత్రములు లేకుండా అమలు చేయవచ్చు, కానీ స్థానిక అమలు సాధారాణంగా చాలా సమర్థవంతంగా ఉండవు. మరింత ప్రభావవంతమైన నియమాలు సరిపోయే కొరకు ప్రత్యేక అల్గోరిథమ్ [Rete](https://en.wikipedia.org/wiki/Rete_algorithm) ఉపయోగించబడుతుంది.\n" ] }, { @@ -247,32 +247,31 @@ "name": "stdout", "output_type": "stream", "text": [ - "Collecting git+https://github.com/buguroo/pyknow/\n", - " Cloning https://github.com/buguroo/pyknow/ to /tmp/pip-req-build-3cqeulyl\n", - " Running command git clone --filter=blob:none --quiet https://github.com/buguroo/pyknow/ /tmp/pip-req-build-3cqeulyl\n", - " Resolved https://github.com/buguroo/pyknow/ to commit 48818336f2e9a126f1964f2d8dc22d37ff800fe8\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting frozendict==1.2\n", - " Using cached frozendict-1.2.tar.gz (2.6 kB)\n", - " Preparing metadata (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25hCollecting schema==0.6.7\n", - " Using cached schema-0.6.7-py2.py3-none-any.whl (14 kB)\n", - "Building wheels for collected packages: pyknow, frozendict\n", - " Building wheel for pyknow (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for pyknow: filename=pyknow-1.7.0-py3-none-any.whl size=34228 sha256=b7de5b09292c4007667c72f69b98d5a1b5f7324ff15f9dd8e077c3d5f7aade42\n", - " Stored in directory: /tmp/pip-ephem-wheel-cache-k7jpave7/wheels/81/1a/d3/f6c15dbe1955598a37755215f2a10449e7418500d7bd4b9508\n", - " Building wheel for frozendict (setup.py) ... \u001b[?25ldone\n", - "\u001b[?25h Created wheel for frozendict: filename=frozendict-1.2-py3-none-any.whl size=3148 sha256=2863d55c240d2409cddf05ccfe600591f8478681549fc97555c47c90dc6bb160\n", - " Stored in directory: /home/rg/.cache/pip/wheels/49/ac/f8/cb8120244e710bdb479c86198b03c7b08c3c2d3d2bf448fd6e\n", - "Successfully built pyknow frozendict\n", - "Installing collected packages: schema, frozendict, pyknow\n", - "Successfully installed frozendict-1.2 pyknow-1.7.0 schema-0.6.7\n" + "Collecting git+https://github.com/nilp0inter/experta\n", + " Cloning https://github.com/nilp0inter/experta to /tmp/pip-req-build-7qurtwk3\n", + " Running command git clone --filter=blob:none --quiet https://github.com/nilp0inter/experta /tmp/pip-req-build-7qurtwk3\n", + " Resolved https://github.com/nilp0inter/experta to commit c6d5834b123861f5ae09e7d07027dc98bec58741\n", + " Installing build dependencies ... \u001b[?25ldone\n", + "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n", + "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25hRequirement already satisfied: frozendict~=2.4.6 in /opt/conda/envs/ai4beg/lib/python3.12/site-packages (from experta==1.9.5.dev1) (2.4.7)\n", + "Collecting schema~=0.6.7 (from experta==1.9.5.dev1)\n", + " Downloading schema-0.6.8-py2.py3-none-any.whl.metadata (14 kB)\n", + "Downloading schema-0.6.8-py2.py3-none-any.whl (14 kB)\n", + "Building wheels for collected packages: experta\n", + " Building wheel for experta (pyproject.toml) ... \u001b[?25ldone\n", + "\u001b[?25h Created wheel for experta: filename=experta-1.9.5.dev1-py3-none-any.whl size=34804 sha256=888c459512a5e713f4b674caa9a0f96cfdf07ec0d6eb56cc318ce0653d218014\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-1eeii9zy/wheels/3d/e8/bb/22d7956359603fa8dd679aa09f5b8efb3f29991c3986fdc787\n", + "Successfully built experta\n", + "Installing collected packages: schema, experta\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2/2\u001b[0m [experta]\n", + "\u001b[1A\u001b[2KSuccessfully installed experta-1.9.5.dev1 schema-0.6.8\n" ] } ], "source": [ "import sys\n", - "!{sys.executable} -m pip install git+https://github.com/buguroo/pyknow/" + "!{sys.executable} -m pip install git+https://github.com/nilp0inter/experta" ] }, { @@ -283,15 +282,15 @@ }, "outputs": [], "source": [ - "from pyknow import *\n", - "#import pyknow" + "from experta import *\n", + "#import experta" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "మేము మా సిస్టమ్‌ను `KnowledgeEngine` ను సబ్‌క్లాస్ చేసే క్లాస్‌గా నిర్వచిస్తాము. ప్రతి నియమం `@Rule` అనోటేషన్‌తో వేరే ఫంక్షన్ ద్వారా నిర్వచించబడుతుంది, ఇది నియమం ఎప్పుడు అమలవ్వాలో సూచిస్తుంది. నియమం లోపల, మేము `declare` ఫంక్షన్ ఉపయోగించి కొత్త వాస్తవాలను జోడించవచ్చు, మరియు ఆ వాస్తవాలను జోడించడం ఫార్వర్డ్ ఇన్ఫరెన్స్ ఇంజిన్ ద్వారా మరిన్ని నియమాలు పిలవబడటానికి కారణమవుతుంది.\n" + "మేము మా సిస్టమ్ను `KnowledgeEngine` ను subclass చేసే క్లాస్ గా నిర్వచిస్తాము. ప్రతి Rule ఒక విభిన్న ఫంక్షన్ ద్వారా నిర్వచించబడుతుంది, దీనికి `@Rule` అనోటేషన్ ఉంటుంది, ఇది ఆ Rule ఎప్పుడు అమలు చేయాలి అని సూచిస్తుంది. ఆ Rule లో, మేము `declare` ఫంక్షన్ ఉపయోగించి కొత్త వాస్తవాలను జత చేయవచ్చు, మరియు ఆ వాస్తవాలను జతచేయడం వల్ల ముందుకు inferencing ఇంజన్ మరికొన్ని Rules ను పిలుస్తుంది.\n" ] }, { @@ -378,7 +377,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "ఒకసారి మనం ఒక జ్ఞానాధారం నిర్వచించిన తర్వాత, మన పని జ్ఞాపకశక్తిని కొన్ని ప్రారంభ వాస్తవాలతో నింపుతాము, మరియు ఆపై `run()` పద్ధతిని పిలిచి తర్కాన్ని నిర్వహిస్తాము. మీరు ఫలితంగా చూడవచ్చు కొత్త తర్కించిన వాస్తవాలు పని జ్ఞాపకశక్తికి జోడించబడ్డాయి, అందులో ఆ జంతువు గురించి తుది వాస్తవం కూడా ఉంటుంది (మనం అన్ని ప్రారంభ వాస్తవాలను సరిగ్గా సెట్ చేసినట్లయితే).\n" + "ఒక్కసారి మనం ఒక జ్ఞానాధారాన్ని నిర్వచించిన తర్వాత, మనం మా పని జ్ఞాపకాన్ని కొన్ని ప్రారంభ వాస్తవాలతో నింపుతాము, మరియు ఆపై inferencing చేయడానికి `run()` మెటోడ్ను పిలుస్తాము. మీరు ఫలితంగా చూసుకోవచ్చు కొత్త infer చేయబడిన వాస్తవాలు పని జ్ఞాపకానికి జోడించబడ్డాయి, చివరి వాస్తవం ప్రాణి గురించి (మనం అన్ని ప్రారంభ వాస్తవాలను సరిగ్గా సెటప్ చేస్తే).\n" ] }, { @@ -440,7 +439,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "---\n\n\n**అస్పష్టత**: \nఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో పొరపాట్లు లేదా తప్పిదాలు ఉండవచ్చు. మూల పత్రం దాని స్వదేశీ భాషలోనే అధికారిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారానికి, ప్రొఫెషనల్ మానవ అనువాదం సిఫార్సు చేయబడుతుంది. ఈ అనువాదం వాడకంలో ఏర్పడిన ఏవైనా అపార్థాలు లేదా తప్పుదారుల కోసం మేము బాధ్యత వహించము.\n\n" + "---\n\n\n**అస్పష్టత సూచన**:\nఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించారు. మేము ఖచ్చితత్వానికి ప్రయత్నిస్తూనే ఉన్నప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో తప్పులు లేదా అసత్యతలు ఉండవచ్చని గమనించగలరు. అసలు పత్రం దాని స్వదేశ భాషలో ఉన్నదాన్ని అధికారిక మూలంగా పరిగణించాలి. కీలకమైన సమాచారానికి, వృత్తిపరమైన మానవ అనువాదాన్ని సిఫారసు చేస్తాము. ఈ అనువాదం ఉపయోగంతో ఏర్పడే ఏదైనా అపవాదాలు లేదా తప్పుదారులపై మేము బాధ్యత వహించము.\n\n" ] } ], @@ -467,8 +466,8 @@ "version": "3.11.2" }, "coopTranslator": { - "original_hash": "ab2bd97b0453415b89a469284609a8ce", - "translation_date": "2025-11-25T23:47:55+00:00", + "original_hash": "8ef43db4b9182239fd150a76bd494fdb", + "translation_date": "2026-01-16T07:21:37+00:00", "source_file": "lessons/2-Symbolic/Animals.ipynb", "language_code": "te" } diff --git a/translations/te/lessons/2-Symbolic/README.md b/translations/te/lessons/2-Symbolic/README.md index ed10e722..29ee587d 100644 --- a/translations/te/lessons/2-Symbolic/README.md +++ b/translations/te/lessons/2-Symbolic/README.md @@ -1,62 +1,62 @@ -# జ్ఞాన ప్రాతినిధ్యం మరియు నిపుణుల వ్యవస్థలు +# జ్ఞాన ప్రతినిధిత్వం మరియు నిపుణుల సిస్టమ్‌లు -![సాంబాలిక AI విషయాల సారాంశం](../../../../translated_images/te/ai-symbolic.715a30cb610411a6.webp) +![Summary of Symbolic AI content](../../../../../../translated_images/te/ai-symbolic.715a30cb610411a6.webp) -> స్కెచ్ నోట్ [Tomomi Imura](https://twitter.com/girlie_mac) ద్వారా +> స్కెచ్‌నోట్ దీన్ని [Tomomi Imura](https://twitter.com/girlie_mac) చేత రాయబడింది -కృత్రిమ మేధస్సు కోసం ప్రయత్నం అనేది మనుషులు ప్రపంచాన్ని అర్థం చేసుకునే విధంగా జ్ఞానాన్ని వెతకడమే. కానీ దీన్ని ఎలా చేయాలి? +కృత్రిమ మేధస్సు అన్వేషణ అనేది మానవులు ప్రపంచాన్ని అర్థం చేసుకునే విధంగా, ప్రపంచాన్ని అర్థం చేసుకోవడానికి జ్ఞానం కోసం ఒక శోధన ఆధారంగా ఉంటుంది. కానీ దీన్ని ఎలా చేయవచ్చు? -## [పూర్వ-లెక్చర్ క్విజ్](https://ff-quizzes.netlify.app/en/ai/quiz/3) +## [ప్రివ్య Lecture క్విజ్](https://ff-quizzes.netlify.app/en/ai/quiz/3) -AI ప్రారంభ దశల్లో, తెలివైన వ్యవస్థలను సృష్టించడానికి టాప్-డౌన్ విధానం (మునుపటి పాఠంలో చర్చించబడింది) ప్రాచుర్యం పొందింది. ఆలోచన ఏమిటంటే, మనుషుల నుండి జ్ఞానాన్ని యంత్రం చదవగల రూపంలోకి తీసుకుని, దానిని ఆటోమేటిక్‌గా సమస్యలను పరిష్కరించడానికి ఉపయోగించడం. ఈ విధానం రెండు పెద్ద ఆలోచనలపై ఆధారపడి ఉంది: +AI ప్రారంభ దశలలో, తెలివైన సిస్టమ్‌లను సృష్టించడానికి టాప్-డౌన్ విధానం (మునుపటి పాఠంలో చర్చించబడినది) ప్రజాదరణ పొందింది. ఆ ఆలోచన మీకు తెలుసు, మనుషుల నుండి జ్ఞానాన్ని తీసుకుని యంత్రం రీడబుల్ రూపంలోకి మార్చి, దానిని ఆటోమేటల్లీ సమస్యలను పరిష్కరించడానికి ఉపయోగించడం. ఈ విధానం రెండు పెద్ద ఆలోచనలపై ఆధారపడి ఉంది: -* జ్ఞాన ప్రాతినిధ్యం -* తర్కం +* జ్ఞాన ప్రతినిధిత్వం +* తార్కికం -## జ్ఞాన ప్రాతినిధ్యం +## జ్ఞాన ప్రతినిధిత్వం -సాంబాలిక AIలో ఒక ముఖ్యమైన భావన **జ్ఞానం**. జ్ఞానాన్ని *సమాచారం* లేదా *డేటా* నుండి వేరుచేసుకోవడం ముఖ్యం. ఉదాహరణకు, పుస్తకాలు జ్ఞానం కలిగి ఉంటాయని చెప్పవచ్చు, ఎందుకంటే పుస్తకాలను చదివి నిపుణులు అవ్వవచ్చు. కానీ పుస్తకాల్లో ఉన్నది వాస్తవానికి *డేటా* అని పిలవబడుతుంది, పుస్తకాలను చదివి ఆ డేటాను మన ప్రపంచ మోడల్‌లోకి సమీకరించడం ద్వారా ఆ డేటాను జ్ఞానంగా మార్చుకుంటాము. +సింబాలిక్ AIలో ఒక ముఖ్యమైన భావన **జ్ఞానం**. దాన్ని *సమాచారం* లేదా *డేటా* నుండి వేరుచేసుకోవడం ముఖ్యం. ఉదాహరణకు, పుస్తకాలు జ్ఞానం కలిగి ఉన్నట్లు చెప్పవచ్చు, ఎందుకంటే మనం పుస్తకాలు చదివి నిపుణులు అవ్వగలము. కానీ, విషయం ఏమిటంటే పుస్తకాలు వాస్తవానికి *డేటా*ని కలిగి ఉంటాయి, మనం పుస్తకాలను చదవటం మరియు ఈ డేటాను మన ప్రపంచ నమూనాకి అనుసంధానం చేయడం ద్వారా డేటాను జ్ఞానంగా మారుస్తాము. -> ✅ **జ్ఞానం** అనేది మన తలలో ఉండే, ప్రపంచాన్ని మనం అర్థం చేసుకునే విధానాన్ని ప్రతిబింబించే విషయం. ఇది ఒక క్రియాశీల **అధ్యయన** ప్రక్రియ ద్వారా పొందబడుతుంది, అందులో మనం పొందే సమాచారాన్ని మన ప్రపంచ మోడల్‌లోకి సమీకరిస్తాము. +> ✅ **జ్ఞానం** అనేది మన తలలో ఉండి, ప్రపంచాన్నో అర్థం చేసుకునే మన అవగాహనను సూచిస్తుంది. ఇది ఒక క్రియాశీల **అధ్యయనం** ప్రక్రియ ద్వారా పొందబడుతుంది, ఇది మనకు అందే సమాచార భాగాలను మన సక్రియ మోడల్‌లో చోటు చేస్తుంది. -చాలా సార్లు, మనం జ్ఞానాన్ని ఖచ్చితంగా నిర్వచించము, కానీ దాన్ని ఇతర సంబంధిత భావనలతో [DIKW పిరమిడ్](https://en.wikipedia.org/wiki/DIKW_pyramid) ద్వారా సరిపోల్చుకుంటాము. ఇందులో ఈ భావనలు ఉంటాయి: +చాలా సార్లు, మనం కఠినంగా జ్ఞానాన్ని నిర్వచించము, కానీ మనం దాన్ని ఇతర సంబందిత భావనలతో [DIKW Pyramid](https://en.wikipedia.org/wiki/DIKW_pyramid) ద్వారా సరిపోలుస్తాము. దీని లో ఈ భావనలు ఉంటాయి: -* **డేటా** అనేది భౌతిక మాధ్యమాలలో ప్రాతినిధ్యం వహిస్తుంది, ఉదాహరణకు వ్రాసిన పాఠ్యం లేదా మాట్లాడిన మాటలు. డేటా మనుషుల నుండి స్వతంత్రంగా ఉంటుంది మరియు వ్యక్తుల మధ్య పంచుకోవచ్చు. -* **సమాచారం** అనేది మన తలలో డేటాను ఎలా అర్థం చేసుకుంటామో. ఉదాహరణకు, *కంప్యూటర్* అనే పదం విని, దాని గురించి మనకు కొంత అవగాహన ఉంటుంది. -* **జ్ఞానం** అనేది సమాచారాన్ని మన ప్రపంచ మోడల్‌లోకి సమీకరించడం. ఉదాహరణకు, కంప్యూటర్ అంటే ఏమిటి తెలుసుకున్న తర్వాత, అది ఎలా పనిచేస్తుంది, ధర ఎంత, దానిని ఏం కోసం ఉపయోగించవచ్చు అనే ఆలోచనలు కలుగుతాయి. ఈ సంబంధిత భావనల నెట్‌వర్క్ మన జ్ఞానాన్ని ఏర్పరుస్తుంది. -* **ప్రజ్ఞ** అనేది మన ప్రపంచం గురించి మరొక స్థాయి అవగాహన, ఇది *మెటా-జ్ఞానం* ను సూచిస్తుంది, అంటే జ్ఞానాన్ని ఎప్పుడు మరియు ఎలా ఉపయోగించాలో తెలియజేస్తుంది. +* **డేటా** అనేది శారీరక మీడియా (ఉదా: వ్రాసిన వచనం లేదా మాట్లాడిన మాటలు)లో ప్రతినిధ్యం వహిస్తుంది. డేటా మానవులతో సంబంధం లేకుండా కూడా ఉంటుంది మరియు ప్రజల మధ్య పంచుకోగలదు. +* **సమాచారం** అనేది మన తలలో డేటాను ఎలా అర్థం చేసుకుంటామో. ఉదా: *కంప్యూటర్* అనే పదం వింటే మనకి దానికి సంబంధించిన అవగాహన ఉంటుంది. +* **జ్ఞానం** అనేది సమాచారాన్ని మన ప్రపంచ నమూనాలో అనుసంధానించడం. ఉదా: ఒకసారి కంప్యూటర్ అంటే ఏంటి తెలుసుకుంటే, అది ఎలా పనిచేస్తుంది, దీనికి ఎంత ధర ఉంటుంది, దానిని ఏం కోసం ఉపయోగిస్తారు అనే అంశాల్లో కొంత అవగాహన కలిగి మేము అవుతాము. +* **ప్రముఖత** అనేది మన ప్రపంచపు అవగాహనలో మరొక అంతస్తు, ఇది *మెటా-జ్ఞానం*, అంటే జ్ఞానాన్ని ఎప్పుడే మరియు ఎలా ఉపయోగించాలోనూ కొంత భావన. *చిత్రం [వికీపీడియా నుండి](https://commons.wikimedia.org/w/index.php?curid=37705247), Longlivetheux - స్వంత పని, CC BY-SA 4.0* -కాబట్టి, **జ్ఞాన ప్రాతినిధ్యం** సమస్య అనేది కంప్యూటర్‌లో జ్ఞానాన్ని డేటా రూపంలో సమర్థవంతంగా ప్రాతినిధ్యం చేయడం, దాన్ని ఆటోమేటిక్‌గా ఉపయోగించుకునేలా చేయడం. దీన్ని ఒక స్పెక్ట్రమ్‌గా చూడవచ్చు: +కాబట్టి, **జ్ఞాన ప్రతినిధిత్వం** సమస్య అనేది జ్ఞానాన్ని కంప్యూటర్ లో డేటా రూపంలో ప్రతినిధ్యం చేసుకునే సమర్థవంతమైన మార్గం కనుగొనడమే, తద్వారా దాన్ని ఆటోమేటిక్ గా ఉపయోగించుకోవచ్చు. దీనిని ఒక స్పెక్ట్రమ్ గా చూడవచ్చు: -![జ్ఞాన ప్రాతినిధ్యం స్పెక్ట్రమ్](../../../../translated_images/te/knowledge-spectrum.b60df631852c0217.webp) +![Knowledge representation spectrum](../../../../../../translated_images/te/knowledge-spectrum.b60df631852c0217.webp) -> చిత్రం [Dmitry Soshnikov](http://soshnikov.com) ద్వారా +> చిత్రాన్ని [Dmitry Soshnikov](http://soshnikov.com) నిర్మించారు -* ఎడమవైపు, కంప్యూటర్లు సమర్థవంతంగా ఉపయోగించగల చాలా సరళమైన జ్ఞాన ప్రాతినిధ్య రకాలు ఉంటాయి. అత్యంత సరళమైనది అల్గోరిథమిక్, అంటే జ్ఞానం కంప్యూటర్ ప్రోగ్రామ్ ద్వారా ప్రాతినిధ్యం చేయబడుతుంది. ఇది సరళమైనది కానీ సరైన మార్గం కాదు, ఎందుకంటే ఇది సడలింపు లేదు. మన తలలోని జ్ఞానం తరచుగా అల్గోరిథమిక్ కాదు. -* కుడివైపు, సహజ పాఠ్యం వంటి ప్రాతినిధ్యాలు ఉంటాయి. ఇవి అత్యంత శక్తివంతమైనవి, కానీ ఆటోమేటిక్ తర్కానికి ఉపయోగపడవు. +* ఎడమ వైపు, కంప్యూటర్‌ ల ద్వారా సమర్థవంతంగా ఉపయోగించదగిన చాలా సరళ జ్ఞాన ప్రతినిధిత్వ రకాలు ఉన్నాయి. అత్యంత సరళమైనది అల్గోరిథమిక్ విధానం, ఇది జ్ఞానాన్ని ఒక కంప్యూటర్ ప్రోగ్రామ్ ద్వారా ప్రతినిధ్యం చేస్తుంది. అయితే ఇది మంచిదైన మార్గం కాదు, ఎందుకంటే ఇది సర్దుబాటు కానిది. మన తలలో జ్ఞానం చాల సార్లు అల్గోరిథమిక్ కాదు. +* కుడి వైపు, సహజ వచనం వంటి ప్రతినిధిత్వాలు ఉన్నాయి. ఇవి అత్యంత శక్తివంతమైనవి కానీ ఆటోమేటిక్ తార్కికం కోసం ఉపయోగించలేవు. -> ✅ మీ తలలో జ్ఞానాన్ని ఎలా ప్రాతినిధ్యం చేస్తారు, దాన్ని నోట్స్‌గా మార్చేటప్పుడు ఏ విధమైన ఫార్మాట్ మీకు retentionకి సహాయపడుతుంది అని ఒక నిమిషం ఆలోచించండి. +> ✅ మీరు మీ తలలో జ్ఞానాన్ని ఎలా ప్రతినిధ్యం చేస్తారు మరియు దాన్ని నోట్స్‌గా మారుస్తారు అని ఒక నిమిషం ఆలోచించండి. మీకు జ్ఞాన నిల్వకి సహాయపడే ఎటువంటి నిర్దిష్ట రూపకం ఉన్నదా? -## కంప్యూటర్ జ్ఞాన ప్రాతినిధ్యాలను వర్గీకరించడం +## కంప్యూటర్ జ్ఞాన ప్రతినిధిత్వాలను వర్గీకరించడం -వివిధ కంప్యూటర్ జ్ఞాన ప్రాతినిధ్య పద్ధతులను ఈ కేటగిరీలుగా వర్గీకరించవచ్చు: +మేము వివిధ కంప్యూటర్ జ్ఞాన ప్రతినిధిత్వ పద్ధతులను ఈ క్రింది వర్గాల్లో వర్గీకరించవచ్చు: -* **నెట్‌వర్క్ ప్రాతినిధ్యాలు** మన తలలో ఉన్న సంబంధిత భావనల నెట్‌వర్క్ ఆధారంగా ఉంటాయి. మనం అదే నెట్‌వర్క్‌ను కంప్యూటర్‌లో గ్రాఫ్‌గా పునరుత్పత్తి చేయవచ్చు - దీనిని **సెమాంటిక్ నెట్‌వర్క్** అంటారు. +* **నెట్‌వర్క్ ప్రతినిధిత్వాలు** మన తలలో అనుసంధానిత భావనల నెట్‌వర్క్ ఉనికిని ఆధారపడి ఉంటాయి. మనం యే విధంగా ఈ నెట్‌వర్క్‌లను కంప్యూటర్ లో గ్రాఫ్ గా పునఃసృష్టించవచ్చు - దీన్ని **సెమాంటిక్ నెట్‌వర్క్** అంటారు. -1. **ఆబ్జెక్ట్-అట్రిబ్యూట్-వాల్యూ త్రిపుట్లు** లేదా **అట్రిబ్యూట్-వాల్యూ జంటలు**. గ్రాఫ్‌ను కంప్యూటర్‌లో నోడ్స్ మరియు ఎడ్జెస్ జాబితాగా ప్రాతినిధ్యం చేయవచ్చు, కాబట్టి సెమాంటిక్ నెట్‌వర్క్‌ను ఆబ్జెక్టులు, అట్రిబ్యూట్లు, విలువలతో కూడిన త్రిపుట్ల జాబితాగా ప్రాతినిధ్యం చేయవచ్చు. ఉదాహరణకు, ప్రోగ్రామింగ్ భాషల గురించి ఈ క్రింది త్రిపుట్లు ఉంటాయి: +1. **ఆబ్జెక్ట్-గుణం-మూల్యం త్రిపుటాలు** లేదా **గుణం-మూల్యం జంటలు**. ఒక గ్రాఫ్‌ను కంప్యూటర్‌లో నోడ్స్ మరియు ఎడ్జెస్ జాబితాగా ప్రతినిధ్యం చేయవచ్చు, అందువల్ల అనుసంధానిత నెట్‌వర్క్‌ను త్రిపుటాల జాబితాగా ప్రతినిధ్యం చేయవచ్చు, దానిలో ఆబ్జెక్టులు, గుణాలు మరియు విలువలు ఉంటాయి. ఉదా: ప్రోగ్రామింగ్ భాషలపై క్రింది త్రిపుటాలు నిర్మిస్తాము: Object | Attribute | Value -------|-----------|------ @@ -65,12 +65,12 @@ Python | invented-by | Guido van Rossum Python | block-syntax | indentation Untyped-Language | doesn't have | type definitions -> ✅ త్రిపుట్లు ఇతర రకాల జ్ఞానాన్ని ఎలా ప్రాతినిధ్యం చేయగలవో ఆలోచించండి. +> ✅ ఇతర రకాల జ్ఞానాన్ని త్రిపుటలతో ఎలా ప్రతినిధ్యం చేయవచ్చు అనేది ఆలోచించండి. -2. **హైరార్కికల్ ప్రాతినిధ్యాలు** మన తలలో తరచుగా వస్తువుల హైరార్కీని సృష్టిస్తామని సూచిస్తాయి. ఉదాహరణకు, కెనరీ పక్షి అని మనకు తెలుసు, అన్ని పక్షులకు రెక్కలు ఉంటాయి. కెనరీ సాధారణంగా ఏ రంగులో ఉంటుంది, దాని ఎగరడం వేగం ఎంత అనే ఆలోచనలు కూడా మనకు ఉంటాయి. +2. **హైరార్కికల్ ప్రతినిధిత్వాలు** మనం తరచూ మన తలలోని ఆబ్జెక్టుల హైరార్కీ సృష్టించే విషయం పై గమనిస్తాయి. ఉదాహరణకు, మనకు తెలియదు కేనరీ చిలుకపై భాగమైన పక్షి అని, అన్ని పక్షులకి రెక్కలు ఉంటాయి అని. కేనరీ సాధారణంగా ఏ రంగులో ఉంటుందో, వాటి ప్రయాణ వేగం ఎంత అనేది కూడా కొంత అవగాహన ఉంటుంది. - - **ఫ్రేమ్ ప్రాతినిధ్యం** ప్రతి వస్తువు లేదా వస్తువుల తరగతిని **ఫ్రేమ్**గా ప్రాతినిధ్యం చేస్తుంది, ఇందులో **స్లాట్లు** ఉంటాయి. స్లాట్లకు డిఫాల్ట్ విలువలు, విలువ పరిమితులు లేదా విలువ పొందడానికి కాల్ చేయగల ప్రొసీజర్లు ఉంటాయి. అన్ని ఫ్రేమ్‌లు ఒక హైరార్కీని ఏర్పరుస్తాయి, ఇది ఆబ్జెక్ట్-ఓరియెంటెడ్ ప్రోగ్రామింగ్ భాషలలోని ఆబ్జెక్ట్ హైరార్కీకి సమానంగా ఉంటుంది. - - **సినారియోలు** సమయానుకూలంగా విస్తరించగల సంక్లిష్ట పరిస్థితులను ప్రాతినిధ్యం చేసే ప్రత్యేక రకమైన ఫ్రేమ్‌లు. + - **ఫ్రేమ్ ప్రతినిధిత్వం** ప్రతీ ఆబ్జెక్ట్ లేదా ఆబ్జెక్టుల తరగతిని ఒక **ఫ్రేమ్** ద్వారా ప్రతినిధ్యం చేస్తుంది. ఈ ఫ్రేమ్‌ లో **స్లాట్లు** ఉంటాయి. స్లాట్లకు సాధారణ విలువలు, విలువ పరిమితులు లేదా విలువను పొందటానికి పిలవదగిన సంరక్షిత పద్ధతులు ఉండవచ్చు. అన్ని ఫ్రేములు ఒక హైరార్కీని సృష్టిస్తాయి, ఇది ఆబ్జెక్ట్-ఒరియెంటెడ్ ప్రోగ్రామింగ్ భాషలలో ఆబ్జెక్ట్ హైరార్కీకు సమానం. + - **స్కెనారియోలు** కాలపరిమితిలో విస్తరించగల సంక్లిష్ట పరిస్థితులను సూచించే ప్రత్యేక రకాల ఫ్రేములు. **Python** @@ -82,35 +82,35 @@ Variable Case | | CamelCase | | Program Length | | | 5-5000 lines | Block Syntax | Indent | | | -3. **ప్రొసీజరల్ ప్రాతినిధ్యాలు** ఒక నిర్దిష్ట పరిస్థితి సంభవించినప్పుడు అమలు చేయగల చర్యల జాబితాగా జ్ఞానాన్ని ప్రాతినిధ్యం చేస్తాయి. - - ప్రొడక్షన్ రూల్స్ అనేవి if-then స్టేట్మెంట్లు, ఇవి తర్కాన్ని సులభతరం చేస్తాయి. ఉదాహరణకు, ఒక డాక్టర్ వద్ద ఒక నియమం ఉండవచ్చు: **IF** రోగికి అధిక జ్వరం లేదా రక్త పరీక్షలో C-రియాక్టివ్ ప్రోటీన్ అధికంగా ఉంటే **THEN** అతనికి ఇన్ఫ్లమేషన్ ఉంది. ఒక పరిస్థితి కనుగొనగానే, ఇన్ఫ్లమేషన్ గురించి తర్కం చేయవచ్చు, తదుపరి తర్కంలో ఉపయోగించవచ్చు. - - అల్గోరిథమ్స్ కూడా మరో రకమైన ప్రొసీజరల్ ప్రాతినిధ్యం, కానీ అవి జ్ఞాన ఆధారిత వ్యవస్థల్లో నేరుగా ఉపయోగించబడవు. +3. **ప్రొసీజరల్ ప్రతినిధిత్వాలు** ఒక నిర్దిష్ట పరిస్థితి జరిగే సమయంలో నిర్వర్తించదగిన చర్యల జాబితాగా జ్ఞానాన్ని ప్రతినిధ్యం చేస్తాయి. + - ప్రొడక్షన్ రూల్స్ అనేవి if-then ప్రకటనలు, ఇవి మనకు తరచుగా నిష్కర్ష లెక్కించడానికి అనుమతిస్తాయి. ఉదా: ఒక డాక్టర్ కె షరతుని ఉన్నట్టు అనుకుంటే, ఒక రోగికి ఎక్కువ జ్వరం లేదా రక్త పరీక్షలో C-reactive ప్రోటీన్ ఎక్కువగా ఉన్నట్లయితే, అతనికి వాపు ఉందని రూల్ ఉంటే. ఈ పరిస్థితులు గమనించిన తర్వాత వాపుపై ఒక తరచుగా నిష్కర్ష లెక్కించవచ్చు, తదుపరి తార్కికంలో ఉపయోగించవచ్చు. + - అల్గోరిథమ్స్ ను మరో ప్రొసీజరల్ ప్రతినిధిత్వ రూపంగా పరిగణించవచ్చు, అయినప్పటికీ అవి చాలసార్లు నేరుగా జ్ఞాన ఆధారిత సిస్టమ్‌లలో ఉపయోగించబడవు. -4. **లాజిక్** మొదట ఆరిస్టాటిల్ ప్రతిపాదించినది, ఇది సార్వత్రిక మానవ జ్ఞానాన్ని ప్రాతినిధ్యం చేయడానికి. - - ప్రెడికేట్ లాజిక్ గణిత సిద్ధాంతంగా చాలా సమృద్ధిగా ఉంటుంది, అందువల్ల దాని ఉపసమితి సాధారణంగా ఉపయోగిస్తారు, ఉదాహరణకు ప్రోలాగ్‌లో హార్న్ క్లాజులు. - - డిస్క్రిప్టివ్ లాజిక్ అనేది వస్తువుల హైరార్కీలను ప్రాతినిధ్యం చేసి తర్కం చేయడానికి ఉపయోగించే లాజిక్ వ్యవస్థల కుటుంబం, ఉదాహరణకు *సెమాంటిక్ వెబ్*. +4. **లాజిక్** మొదలగిన వాటిని అరిస్టోటిల్ ప్రతిపాదించారు, ఇది విశ్వవ్యాప్త మానవ జ్ఞానాన్ని సూచించే మార్గం. + - ప్రతిపాదిత లాజిక్ గణిత సిద్దాంతానికి చాలా సంక్లిష్టంగా ఉండటంతో, సాధారణంగా కొన్ని ఉపసమూహాలు - ఉదా: ప్రొలాగ్‌లో ఉపయోగించే హోర్న్ క్లాజస్‌లను ఉపయోగిస్తారు. + - వివరణాత్మక లాజిక్ అనేది తర్కపూర్వక సిస్టమ్‌ల కుటుంబం, ఇది వస్తువుల హైరార్కీలు మరియు *సెమాంటిక్ వెబ్* వంటి పంపిణీ చేయబడిన జ్ఞాన ప్రతినిధిత్వాలను ప్రతినిధ్యం చేసి, దాని గురించి తార్కికం చేయడానికి ఉపయోగిస్తారు. -## నిపుణుల వ్యవస్థలు +## నిపుణుల సిస్టమ్‌లు -సాంబాలిక AI ప్రారంభ విజయాలలో ఒకటి **నిపుణుల వ్యవస్థలు** - కొన్ని పరిమిత సమస్యల పరిధిలో నిపుణులుగా వ్యవహరించే కంప్యూటర్ వ్యవస్థలు. ఇవి ఒక లేదా ఎక్కువ మానవ నిపుణుల నుండి తీసుకున్న **జ్ఞాన బేస్** ఆధారంగా ఉండి, దాని పై తర్కం చేసే **ఇన్ఫరెన్స్ ఇంజిన్** కలిగి ఉంటాయి. +సింబాలిక్ AI ప్రారంభ విజయాలలో ఒకటి **నిపుణుల సిస్టమ్‌లు** - ఇది కొన్ని పరిమిత సమస్యా పరిధిలో నిపుణుడి పాత్రను పోషించడానికి రూపొందించిన కంప్యూటర్ సిస్టమ్‌లు. ఇవి ఒక లేదా ఎక్కువ మానవ నిపుణుల నుండి తీసుకున్న **జ్ఞాన సమస్యా పాఠశాల** ఆధారంగా ఉంటాయి మరియు అందుపైని తార్కికం నిర్వహించే **అవధారణ యంత్రం** ను కలిగి ఉంటాయి. -![మానవ నిర్మాణం](../../../../translated_images/te/arch-human.5d4d35f1bba3ab1c.webp) | ![జ్ఞాన ఆధారిత వ్యవస్థ](../../../../translated_images/te/arch-kbs.3ec5c150b09fa8da.webp) +![Human Architecture](../../../../../../translated_images/te/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../../../translated_images/te/arch-kbs.3ec5c150b09fa8da.webp) ---------------------------------------------|------------------------------------------------ -మానవ న్యూరల్ సిస్టమ్ సరళీకృత నిర్మాణం | జ్ఞాన ఆధారిత వ్యవస్థ నిర్మాణం +మానవ నరమైన వ్యవస్థ సరళీకృత నిర్మాణం | జ్ఞాన-ఆధారిత వ్యవస్థ నిర్మాణం -నిపుణుల వ్యవస్థలు మానవ తర్క వ్యవస్థలా నిర్మించబడ్డాయి, ఇందులో **తాత్కాలిక జ్ఞాపకం** మరియు **దీర్ఘకాలిక జ్ఞాపకం** ఉంటాయి. అలాగే, జ్ఞాన ఆధారిత వ్యవస్థల్లో ఈ భాగాలు ఉంటాయి: +నిపుణుల సిస్టమ్‌లు మానవ తార్కిక వ్యవస్థ లాగా తయారు చేయబడ్డాయి, ఇందులో **సన్నాహిత స్మృతి** మరియు **దీర్ఘకాల స్మృతి** ఉంటాయి. ఇదే విధంగా, జ్ఞాన-ఆధారిత సిస్టమ్‌లలో ఈ భాగాలు వేరుచేయబడతాయి: -* **సమస్య జ్ఞాపకం**: ప్రస్తుతం పరిష్కరించబడుతున్న సమస్య గురించి జ్ఞానం, ఉదాహరణకు రోగి ఉష్ణోగ్రత లేదా రక్తపోటు, ఇన్ఫ్లమేషన్ ఉందా లేదా. దీనిని **స్థిర జ్ఞానం** అంటారు, ఎందుకంటే ఇది సమస్య గురించి మనకు ఉన్న ఒక స్నాప్‌షాట్ - *సమస్య స్థితి*. -* **జ్ఞాన బేస్**: సమస్య పరిధి గురించి దీర్ఘకాలిక జ్ఞానం. ఇది మానవ నిపుణుల నుండి మాన్యువల్‌గా తీసుకుంటారు, మరియు ప్రతి సలహా సమయంలో మారదు. ఇది ఒక సమస్య స్థితి నుండి మరొకదానికి మారడానికి సహాయపడుతుంది, అందువల్ల దీనిని **డైనమిక్ జ్ఞానం** కూడా అంటారు. -* **ఇన్ఫరెన్స్ ఇంజిన్**: సమస్య స్థితి స్థలంలో శోధన ప్రక్రియను సమన్వయపరుస్తుంది, అవసరమైతే వినియోగదారుని ప్రశ్నలు అడుగుతుంది. ప్రతి స్థితికి వర్తించే సరైన నియమాలను కనుగొనడం బాధ్యత. +* **సమస్య స్మృతి**: ప్రస్తుతం పరిష్కరించబడుతున్న సమస్య గురించి జ్ఞానం ఉంటుంది, ఉదా: రోగి ఉష్ణోగ్రత లేదా రక్తపోటు, వాపు ఉందా లేదా, మొదలైనవి. దీనిని **స్థిర జ్ఞానం** అని కూడా పిలుస్తారు, ఎందుకంటే ఇది మనకు ప్రస్తుత సమస్య స్థితి సంక్షిప్తాన్ని ఇస్తుంది. +* **జ్ఞానపీఠం**: సమస్య పరిధి గురించి దీర్ఘకాలం జ్ఞానం. ఇది మానవ నిపుణులచే మాన్యువల్ గా తీసుకురాబడుతుంది మరియు సలహా ప్రతిసారి మారదు. ఇది ఒక్క సమస్య స్థితి నుండి మరొక దానికి మారేందుకు అనుమతిస్తుందని, అందువల్ల దీనిని **డైనమిక్ జ్ఞానం** అని కూడా అంటారు. +* **అవధారణ యంత్రం**: సమస్య స్థితి స్థలం నుంచి శోధన మరియూ అవసరమైతే వినియోగదారుడి నుండి ప్రశ్నలు అడుగుతుందని మొత్తం ప్రక్రియను నిర్వర్తించేది. ప్రతి సమస్య స్థితికి సరైన నియమాలను అన్వయించే బాధ్యత కూడా దీనికే ఉంటుంది. -ఉదాహరణకు, ఒక జంతువును దాని శారీరక లక్షణాల ఆధారంగా గుర్తించే నిపుణుల వ్యవస్థను పరిశీలిద్దాం: +ఉదాహరణకు, ఒక జంతువును దాని శారీరక లక్షణాల ఆధారంగా గుర్తించడం కోసం క్రింది నిపుణుల సిస్టమ్‌ను పరిగణించాము: -![AND-OR చెట్టు](../../../../translated_images/te/AND-OR-Tree.5592d2c70187f283.webp) +![AND-OR Tree](../../../../../../translated_images/te/AND-OR-Tree.5592d2c70187f283.webp) -> చిత్రం [Dmitry Soshnikov](http://soshnikov.com) ద్వారా +> చిత్రాన్ని [Dmitry Soshnikov](http://soshnikov.com) చిత్రించేరు -ఈ డయాగ్రామ్‌ను **AND-OR చెట్టు** అంటారు, ఇది ప్రొడక్షన్ రూల్స్ సెట్ యొక్క గ్రాఫికల్ ప్రాతినిధ్యం. నిపుణుల నుండి జ్ఞానం తీసుకోవడంలో చెట్టు గీయడం ప్రారంభంలో ఉపయోగకరం. కంప్యూటర్‌లో జ్ఞానాన్ని ప్రాతినిధ్యం చేయడానికి నియమాలను ఉపయోగించడం సౌకర్యవంతం: +ఈ డయాగ్రామ్‌ను **AND-OR చెట్టు** అంటారు, ఇది ప్రొడక్షన్ రూల్స్ సమితి యొక్క గ్రాఫికల్ ప్రాతినిధ్యం. నిపుణుల నుండి జ్ఞానం సేకరించడం ప్రారంభంలో చెట్టును గీసుకోవడం ఉపయోగకరం. కంప్యూటర్‌లో జ్ఞానాన్ని ప్రతినిధ్యం చెయ్యడానికి, రూల్స్ ఉపయోగించడం మరింత సౌకర్యవంతం: ``` IF the animal eats meat @@ -121,71 +121,78 @@ OR (animal has sharp teeth THEN the animal is a carnivore ``` -ప్రతి నియమం ఎడమవైపు ఉన్న పరిస్థితి మరియు చర్య వాస్తవానికి ఆబ్జెక్ట్-అట్రిబ్యూట్-వాల్యూ (OAV) త్రిపుట్లు. **వర్కింగ్ మెమరీ** ప్రస్తుతం పరిష్కరించబడుతున్న సమస్యకు సంబంధించిన OAV త్రిపుట్లను కలిగి ఉంటుంది. **నియమాల ఇంజిన్** పరిస్థితి సంతృప్తి చెందే నియమాలను వెతుకుతుంది మరియు వాటిని వర్తింపజేస్తుంది, వర్కింగ్ మెమరీలో మరో త్రిపుట్ జోడిస్తుంది. +మీకు గమనించవచ్చు, నియమంల బ 左వైపున ఉన్న ప్రతి షరతు మరియు చర్య ఆబ్జెక్ట్-గుణం-మూల్యం (OAV) త్రిపుటలే. **పనిలో ఉన్న స్మృతి** ప్రస్తుత సమస్య పరిష్కారానికి సంబంధించిన OAV త్రిపుటలు కలిగి ఉంటుంది. **రూల్స్ ఇంజిన్** షరతు తార్కికం అయిన రూల్స్ కోసం వెతుకుతుంది, వాటిని వర్తింపజేస్తుంది మరియు పనిలో ఉన్న స్మృతిలో కొత్త త్రిపుటను జోడిస్తుంది. > ✅ మీకు ఇష్టమైన అంశంపై మీ స్వంత AND-OR చెట్టు వ్రాయండి! -### ముందుకు vs. వెనుకకు తర్కం +### ముందుకు లేదా వెనుకకు అవధారణ -పై ప్రక్రియను **ముందుకు తర్కం** అంటారు. ఇది వర్కింగ్ మెమరీలో ఉన్న ప్రారంభ డేటాతో మొదలవుతుంది, తరువాత ఈ తర్కం లూప్‌ను అమలు చేస్తుంది: +పై ప్రక్రియ **ముందుకు అవధారణ** అని పిలవబడుతుంది. ఇది పనిలో ఉన్న స్మృతిలో ఉన్న కొన్ని ప్రాథమిక డేటాతో మొదలుకుని ఈ తార్కిక చక్రాన్ని కొనసాగిస్తుంది: -1. లక్ష్య అట్రిబ్యూట్ వర్కింగ్ మెమరీలో ఉంటే - ఆపు మరియు ఫలితాన్ని ఇవ్వు -2. ప్రస్తుతం సంతృప్తి చెందుతున్న పరిస్థితి ఉన్న అన్ని నియమాలను వెతుకు - **సంఘర్షణ సెట్** పొందు -3. **సంఘర్షణ పరిష్కారం** చేయి - ఈ దశలో అమలు చేయవలసిన ఒక నియమాన్ని ఎంచుకో. వివిధ పరిష్కార విధానాలు ఉండవచ్చు: - - జ్ఞాన బేస్‌లో మొదటి వర్తించే నియమాన్ని ఎంచుకో - - యాదృచ్ఛిక నియమాన్ని ఎంచుకో - - *మరింత ప్రత్యేకమైన* నియమాన్ని ఎంచుకో, అంటే ఎల్ఎచ్ఎస్‌లో ఎక్కువ పరిస్థితులు తీరుస్తున్నది -4. ఎంచుకున్న నియమాన్ని వర్తింపజెయ్యి మరియు సమస్య స్థితిలో కొత్త జ్ఞానాన్ని చేర్చు -5. దశ 1 నుండి పునరావృతం చేయి +1. లక్ష్య గుణం పనిలో ఉన్న స్మృతిలో ఉందా అయితే నిలిపి ఫలితం ఇవ్వండి +2. ప్రస్తుతం షరతు తార్కికం అయ్యే అన్ని రూల్స్ కోసం వెతకండి - **సంఘర్షణ సెట్** పొందండి +3. **సంఘర్షణ పరిష్కారం** చేయండి - ఈ దశలో అమలు చేయదగిన ఒక రూల్‌ని ఎంచుకోండి. వివిధ పరిష్కార వ్యూహాలు ఉండవచ్చు: + - జ్ఞానపీఠంలో మొదటి వర్తించదగిన నియమాన్ని ఎంచుకోండి + - యాదృచ్ఛిక రూల్ ఎంచుకోండి + - *మరింత ప్రత్యేకమైన* రూల్ ఎంచుకోండి, అంటే ఎల్‌హెచ్ఎస్ (ఎడమవైపు)లో ఎక్కువ షరతులు కలిసే రూల్ +4. ఎంచుకున్న రూల్ వర్తించి సమస్య స్థితిలో కొత్త జ్ఞానాన్ని చేర్చండి +5. రెండవ దశ నుండి పునరావృతం చేయండి -కానీ, కొన్ని సందర్భాల్లో సమస్య గురించి ఖాళీ జ్ఞానంతో మొదలుపెట్టి, తర్కానికి సహాయపడే ప్రశ్నలు అడగాలనుకోవచ్చు. ఉదాహరణకు, వైద్య నిర్ధారణలో, రోగిని పరీక్షించే ముందు అన్ని వైద్య పరీక్షలు చేయరు. నిర్ణయం తీసుకోవాల్సినప్పుడు పరీక్షలు చేస్తారు. +కానీ మనం కొన్ని సందర్భాల్లో సమస్య గురించి ఖాళీ జ్ఞానంతో ప్రారంభించి, నిర్ణయానికి సహాయపడే ప్రశ్నలు అడగాలని కావచ్చు. ఉదాహరణకు, వైద్య నిర్ధారణలో, రోగిని నిర్ధారించడానికి ముందే అన్ని వైద్య పరీక్షలు చేయరు. అవసరమైనప్పుడు పరీక్షలు చేస్తారు. -ఈ ప్రక్రియను **వెనుకకు తర్కం** ద్వారా మోడల్ చేయవచ్చు. ఇది **లక్ష్యం** ఆధారంగా నడుస్తుంది - మనం కనుగొనదలచిన అట్రిబ్యూట్ విలువ: +ఈ ప్రక్రియ **వెనుకకు అవధారణ** ద్వారా గేయించవచ్చు. ఇది **లక్ష్యం** ఆధారంగా నడుస్తుంది - మనం కనుగొనదలిచిన గుణ విలువ: -1. లక్ష్య విలువను ఇవ్వగల అన్ని నియమాలను ఎంచుకో (అంటే ఆ లక్ష్యం ఆర్హత ఉన్న నియమాలు) - సంఘర్షణ సెట్ -2. ఆ అట్రిబ్యూట్‌కు నియమాలు లేకపోతే, లేదా వినియోగదారుని నుండి విలువ అడగాలని నియమం ఉంటే - అడుగు, లేకపోతే: -3. సంఘర్షణ పరిష్కార విధానంతో ఒక నియమాన్ని *హైపోథసిస్* గా ఎంచుకో - దాన్ని నిరూపించడానికి ప్రయత్నించు -4. ఆ నియమం ఎల్ఎచ్ఎస్‌లో ఉన్న అన్ని అట్రిబ్యూట్ల కోసం పునరావృతంగా ప్రక్రియను చేయి, వాటిని లక్ష్యాలుగా నిరూపించు -5. ఎక్కడైనా ప్రక్రియ విఫలమైతే - దశ 3లో మరో నియమాన్ని ఉపయోగించు +1. లక్ష్య విలువ ఇచ్చే అన్ని రూల్స్‌ను ఎంచుకోండి (రైట్హెండ్సైడ్ ఉన్న వాటితో) - సంఘర్షణ సెట్ +2. ఆ గుణానికి ఎలాంటి రూల్స్ లేకపోతే లేదా యూజర్ నుండి విలువ అడగమని రూల్ ఉంటే - అడగండి, లేకపోతే: +3. సంఘర్షణ పరిష్కార వ్యూహం ద్వారా అవగాహన కోసం ఒక రూల్ ఎంచుకోండి - మనం దాన్ని ప్రూవ్ చేయబోతున్నాం +4. ఆ రూల్ LHSలోని అన్ని గుణాల కోసం పునరావృత ప్రక్రియ చేసి వాటినీ లక్ష్యంగా పరిశీలించండి +5. ఏదైనా దశలో ఫెయిలయితే - మూడవ దశలో మరొక రూల్ ఉపయోగించండి -> ✅ ఏ సందర్భాల్లో ముందుకు తర్కం అనుకూలం? వెనుకకు తర్కం ఎప్పుడు మంచిది? +> ✅ ఏ పరిస్థితుల్లో ముందుకు అవధారణ ఎక్కువగా సరిపోతుంది? వెనుకకు అవధారణ గురించి ఎలా? -### నిపుణుల వ్యవస్థలను అమలు చేయడం +### నిపుణుల సిస్టమ్‌ల అమలుపరచడం -నిపుణుల వ్యవస్థలను వివిధ సాధనాలతో అమలు చేయవచ్చు: +నిపుణుల సిస్టమ్‌లను వివిధ పరికరాలతో అమలు చేయవచ్చు: -* ఎత్తైన స్థాయి ప్రోగ్రామింగ్ భాషలో నేరుగా ప్రోగ్రామ్ చేయడం. ఇది ఉత్తమ ఆలోచన కాదు, ఎందుకంటే జ్ఞాన ఆధారిత వ్యవస్థలో జ్ఞానం మరియు తర్కం వేరు ఉండాలి, మరియు సమస్య పరిధి నిపుణుడు తర్క ప్రక్రియ వివరాలు తెలియకుండానే నియమాలు రాయగలగాలి. -* **నిపుణుల వ్యవస్థ షెల్** ఉపయోగించడం, అంటే జ్ఞాన ప్రాతినిధ్యం భాష ఉపయోగించి జ్ఞానాన్ని నింపడానికి ప్రత్యేకంగా రూపొందించిన వ్యవస్థ. +* వారు ఏదైనా ఉన్నత స్థాయి ప్రోగ్రామింగ్ భాషలో నేరుగా ప్రోగ్రామింగ్ చేయవచ్చు. ఇది ఉత్తమ ఆలోచన కాదు, ఎందుకంటే జ్ఞాన-ఆధారిత సిస్టమ్ లో జ్ఞానం మరియు అవధారణ వేరు ఉండవలెను, మరియు పరిస్థితి నిపుణుడు నేరుగా అవధారణ ప్రక్రియ వివరాలు తెలుసుకోకుండా రూల్స్ రాయగలగాలి. +* **నిపుణుల సిస్టమ్ శెల్** ఉపయోగించడం, అంటే ప్రత్యేకంగా డిజైన్ చేసిన సిస్టమ్, దానిలో జ్ఞానం ప్రతినిధిత్వ భాష ద్వారా చేర్చవచ్చు. -## ✍️ వ్యాయామం: జంతు తర్కం +## ✍️ వ్యాయామం: జంతు అవధారణ -ముందుకు మరియు వెనుకకు తర్కం నిపుణుల వ్యవస్థను అమలు చేసిన ఉదాహరణ కోసం [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb) చూడండి. +ముందుకు మరియు వెనుకకు అవధారణ నిపుణుల సిస్టమ్‌లను అమలు చేసే ఉదాహరణ కోసం [Animals.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/Animals.ipynb) చూడండి. -> **గమనిక**: ఈ ఉదాహరణ చాలా సరళమైనది, మరియు నిపుణుల వ్యవస్థ ఎలా ఉంటుందో ఆలోచన ఇస్తుంది. మీరు ఇలాంటి వ్యవస్థను సృష్టించడం ప్రారంభించినప్పుడు, సుమారు 200+ నియ +> **గమనిక**: ఈ ఉదాహరణ చాలా సరళమైనది, మరియు నిపుణుల సిస్టమ్ ఎలా ఉంటుందో రోజు ఒక భావన మాత్రమే ఇస్తుంది. ఇలాంటి సిస్టమ్ ఆరంభించిన తర్వాత, మీరు కొన్ని రూల్స్ సంఖ్య సుమారు 200+ చేరిన తర్వాత మాత్రమే అదృష్టవంతమైన భాగం చూస్తారు. ఆ సమయంలో, రూల్స్ చాలా సంక్లిష్టమవుతాయి, వాటిని గుర్తుంచుకోవడం కష్టం, మరియు మీరు ఆ సిస్టమ్ నిర్ణయాలు ఎందుకు తీసుకుంటున్నాయనేది ఊహించవచ్చు. అయితే, జ్ఞాన-ఆధారిత సిస్టమ్‌ల ముఖ్య లక్షణం ఏదైతే అంటే మీరు ఎప్పుడైనా ఏ నిర్ణయం ఎలా తీసుకున్నదో *విభ్రాంతంగా* వివరించవచ్చు. + +## ఓంటాలజీలు మరియు సెమాంటిక్ వెబ్ + +20వ శతాబ్దం చివర్లో ఒక ప్రయత్నం జరిగింది, జ్ఞాన ప్రతినిధిత్వాన్ని ఉపయోగించి ఇంటర్నెట్ వనరులను అనోటేట్ చేయడానికి, దీని వలన చాలా ప్రత్యేక క్వెరీలకు సంబంధించిన వనరులు కనుగొనడం సాధ్యం అయ్యింది. ఈ ఉద్యమం **సెమాంటిక్ వెబ్** అని పిలవబడింది, ఇది కొన్ని భావాలపై ఆధారపడి ఉంది: + +- **[వివరణాత్మక తర్కాలు](https://en.wikipedia.org/wiki/Description_logic)** (DL) ఆధారమైన ప్రత్యేక జ్ఞాన ప్రతినిధిత్వం. ఇది ఫ్రేమ్ జ్ఞాన ప్రతినిధిత్వానికి సమానమైనది, ఎందుకంటే ఇది ఆబ్జెక్టుల హైరార్కీని ఆస్తులతో నిర్మిస్తుంది, కానీ దీని వద్ద సాంఘిక లాజిక్ సారాంశాలు మరియు అవధారణ ఉంటాయి. వివరణాత్మక తర్కాలు అనే సిస్టమ్‌లు లాజిక్ ప్రయోగంలో సమర్థత మరియు అర్థగర్భత మధ్య సరాసరి కలిగి ఉంటాయి. +- పంపిణీ చేయబడిన జ్ఞాన ప్రతినిధిత్వం, ఇందులో అన్ని భావనలు ఒక గ్లోబల్ URI గుర్తింపుతో సూచించబడతాయి, దీని వలన ఇంటర్నెట్ మొత్తం పరిమితులుగా ఉండే జ్ఞాన హైరార్కీలు సృష్టించవచ్చు. - జ్ఞాన వివరణ కోసం XML ఆధారిత భాషల కుటుంబం: RDF (Resource Description Framework), RDFS (RDF Schema), OWL (Ontology Web Language). -సెమాంటిక్ వెబ్‌లో ఒక ముఖ్యమైన భావన **ఆంటాలజీ**. ఇది ఒక సమస్య పరిధిని స్పష్టంగా నిర్వచించడానికి ఉపయోగించే ఫార్మల్ జ్ఞాన ప్రాతినిధ్యం. సులభమైన ఆంటాలజీ అంటే సమస్య పరిధిలోని వస్తువుల హైరార్కీ మాత్రమే కావచ్చు, కానీ క్లిష్టమైన ఆంటాలజీలు నిర్ధారణ కోసం ఉపయోగించే నియమాలను కూడా కలిగి ఉంటాయి. +సెమాంటిక్ వెబ్‌లో ఒక ముఖ్యమైన సిద్ధాంతం **Ontology**. ఇది కొన్ని అధికారిక జ్ఞాన ప్రాతినిధ్యం వాడి సమస్య డొమైన్ యొక్క స్పష్టమైన వివరణకు సంబంధించిఉంది. అత్యంత సులభమైన ontology సాధారణంగా సమస్య డొమైన్‌లోని వస్తువుల హైరార్కీ మాత్రమే ఉండవచ్చు, కాని మరింత సంక్లిష్టమైన ontologies inferencing కోసం ఉపయోగించే నిబంధనలను కలిగి ఉంటాయి. -సెమాంటిక్ వెబ్‌లో అన్ని ప్రాతినిధ్యాలు ట్రిప్లెట్లపై ఆధారపడి ఉంటాయి. ప్రతి వస్తువు మరియు ప్రతి సంబంధం ప్రత్యేకంగా URI ద్వారా గుర్తించబడతాయి. ఉదాహరణకు, ఈ AI పాఠ్యాంశం డిమిత్రి సోష్నికోవ్ 2022 జనవరి 1న అభివృద్ధి చేశారని చెప్పాలంటే, మనం ఉపయోగించగల ట్రిప్లెట్లు ఇవి: +సెమాంటిక్ వెబ్‌లో, అన్ని ప్రాతినిధ్యాలు ట్రిపుల్స్ (triplets) ఆధారంగా ఉంటాయి. ప్రతి వస్తువు మరియు ప్రతి సంబంధం యూనీక్ URI ద్వారా గుర్తించబడతాయి. ఉదాహరణకు, ఈ AI Curriculum ని Dmitry Soshnikov జనవరి 1, 2022 లో అభివృద్ధి చేశాడు అన్న వాస్తవాన్ని తెలియజేయాలంటే - క్రింది ట్రిపుల్స్ ఉపయోగించవచ్చు: ``` -http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 13, 2007” +http://github.com/microsoft/ai-for-beginners http://www.example.com/terms/creation-date “Jan 1, 2022” http://github.com/microsoft/ai-for-beginners http://purl.org/dc/elements/1.1/creator http://soshnikov.com ``` -> ✅ ఇక్కడ `http://www.example.com/terms/creation-date` మరియు `http://purl.org/dc/elements/1.1/creator` అనేవి *సృష్టికర్త* మరియు *సృష్టి తేదీ* భావాలను వ్యక్తం చేయడానికి ప్రసిద్ధి చెందిన, విశ్వవ్యాప్త URIలు. +> ✅ ఇక్కడ `http://www.example.com/terms/creation-date` మరియు `http://purl.org/dc/elements/1.1/creator` అనేవి *creator* మరియు *creation date* భావాలను వ్యక్తపరచడానికి బాగా తెలిసిన మరియు విశ్వసనీయ URIs. -మరింత క్లిష్టమైన సందర్భంలో, సృష్టికర్తల జాబితాను నిర్వచించాలంటే, RDFలో నిర్వచించిన కొన్ని డేటా నిర్మాణాలను ఉపయోగించవచ్చు. +కీలకంగా, సృష్టికర్తల జాబితాను నిర్వచించాలంటే RDFలో నిర్వచించిన కొన్ని డేటా గঠనలను ఉపయోగించవచ్చు. -> పై చిత్రాలు [డిమిత్రి సోష్నికోవ్](http://soshnikov.com) చేత రూపొందించబడ్డవి +> పై డాగ్రామ్‌లు [Dmitry Soshnikov](http://soshnikov.com) వారి వల్ల. -సెమాంటిక్ వెబ్ నిర్మాణం కొంతమేర ఆలస్యం అయినది, ఎందుకంటే సెర్చ్ ఇంజిన్లు మరియు సహజ భాషా ప్రాసెసింగ్ సాంకేతికతలు టెక్స్ట్ నుండి నిర్మిత డేటాను తీయగలవు. అయినప్పటికీ, కొన్ని రంగాలలో ఆంటాలజీలు మరియు జ్ఞాన భాండారాలను నిర్వహించడానికి గణనీయమైన ప్రయత్నాలు కొనసాగుతున్నాయి. కొన్ని ప్రాజెక్టులు: +సెమాంటిక్ వెబ్ నిర్మాణ పురోగతి కొంతమేర ఆలస్యం అయింది, ఇది సెర్చ్ ఇంజిన్లు మరియు సహజ భాషా ప్రాసెసింగ్ సాంకేతికతల విజయపు కారణంగా, వీటి ద్వారా పాఠ్యం నుండి నిర్మిత డేటాను పొందగలవు. అయినప్పటికీ, కొన్ని రంగాల్లో ఇంకా ontologies మరియు జ్ఞాన వనరుల నిర్వహణపై గణనీయమైన ప్రయత్నాలు జరుగుతున్నాయి. కొన్ని గమనించదగ్గ ప్రాజెక్టులు: -* [WikiData](https://wikidata.org/) అనేది వికీపీడియాతో సంబంధం ఉన్న యంత్రం చదవగలిగే జ్ఞాన భాండారాల సేకరణ. ఎక్కువ భాగం డేటా వికీపీడియా *ఇన్ఫోబాక్స్* నుండి సేకరించబడుతుంది, ఇవి వికీపీడియా పేజీలలోని నిర్మిత కంటెంట్ భాగాలు. మీరు [SPARQL](https://query.wikidata.org/) అనే ప్రత్యేక సెమాంటిక్ వెబ్ ప్రశ్న భాషలో వికిడేటాను ప్రశ్నించవచ్చు. ఇక్కడ మానవులలో అత్యంత ప్రాచుర్యం పొందిన కళ్ళ రంగులను చూపించే ఒక నమూనా ప్రశ్న ఉంది: +* [WikiData](https://wikidata.org/) అనేది వికీపీడియాతో సంబందిత యంత్రం చదువుకునే జ్ఞాన వనరుల సేకరణ. అధికంత డేటా వికీపీడియా *InfoBoxes* నుండి సేకరించబడింది, వీటివి వికీపీడియా పేజీలలోని నిర్మాణాత్మక కంటెంట్ భాగాలు. మీరు [query](https://query.wikidata.org/) wikidata ని SPARQL, సెమాంటిక్ వెబ్ సొంత ప్రత్యేక క్వెరి భాషలో చేయవచ్చు. ఇక్కడ మనుషుల లో అత్యంత ప్రజాదరణ పొందిన కనులు రంగులను చూపించే ఒక నమూనా క్వెరి ఉంది: ```sparql #defaultView:BubbleChart @@ -199,51 +206,51 @@ WHERE GROUP BY ?eyeColorLabel ``` -* [DBpedia](https://www.dbpedia.org/) కూడా WikiDataకు సమానమైన మరో ప్రయత్నం. +* [DBpedia](https://www.dbpedia.org/) కూడా WikiData సారమైన మరో ప్రయత్నం. -> ✅ మీ స్వంత ఆంటాలజీలు నిర్మించడానికి లేదా ఉన్న వాటిని తెరవడానికి, [Protégé](https://protege.stanford.edu/) అనే అద్భుతమైన విజువల్ ఆంటాలజీ ఎడిటర్ ఉంది. దాన్ని డౌన్లోడ్ చేసుకోండి లేదా ఆన్‌లైన్‌లో ఉపయోగించండి. +> ✅ మీరు మీ స్వంత ontologies నిర్మించేందుకు లేదా ఉన్న ontologies ను తెరవండి అని అనుకుంటే, ఒక అద్భుతమైన విజువల్ ontology ఎడిటర్ [Protégé](https://protege.stanford.edu/) ఉంది. దాన్ని డౌన్లోడ్ చేసుకోండి లేదా ఆన్‌లైన్ ఉపయోగించండి. -*Web Protégé ఎడిటర్ రోమానోవ్ కుటుంబ ఆంటాలజీతో తెరవబడింది. స్క్రీన్‌షాట్ డిమిత్రి సోష్నికోవ్ చేత* +*Web Protégé ఎడిటర్ Romanov కుటుంబ ontology తో తెరవబడింది. స్క్రీన్‌షాట్ Dmitry Soshnikov ద్వారా* -## ✍️ వ్యాయామం: కుటుంబ ఆంటాలజీ +## ✍️ వ్యాయామం: కుటుంబ Ontology -సెమాంటిక్ వెబ్ సాంకేతికతలను ఉపయోగించి కుటుంబ సంబంధాలపై తర్కం చేయడం ఎలా అనేది చూడటానికి [FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb) చూడండి. సాధారణ GEDCOM ఫార్మాట్‌లో ఉన్న కుటుంబ వృక్షాన్ని మరియు కుటుంబ సంబంధాల ఆంటాలజీని తీసుకుని, ఇచ్చిన వ్యక్తుల సమూహానికి సంబంధించిన అన్ని కుటుంబ సంబంధాల గ్రాఫ్‌ను నిర్మిస్తాము. +[FamilyOntology.ipynb](https://github.com/Ezana135/AI-For-Beginners/blob/main/lessons/2-Symbolic/FamilyOntology.ipynb) చూడండి, ఇది కుటుంబ సంబంధాల గురించి సెమాంటిక్ వెబ్ సాంకేతికతలను ఉపయోగించి వివరణ చేయడం ఎలా అనేది ఉదాహరణ. మనంGEDCOM ఫార్మాట్ లో ఉన్న కుటుంబ వృక్షాన్ని మరియు కుటుంబ సంబంధాల ontologyని తీసుకుని వ్యక్తుల సమూహానికి సంబంధించిన అందరి కుటుంబ సంబంధాల గ్రాఫ్‌ను నిర్మించబోతున్నాము. ## Microsoft Concept Graph -అధిక భాగం సందర్భాల్లో, ఆంటాలజీలు జాగ్రత్తగా చేతితో రూపొందించబడతాయి. అయితే, సహజ భాషా టెక్స్ట్‌ల నుండి కూడా ఆంటాలజీలను **మైన్** చేయవచ్చు. +చేతితో ontologies జాగ్రత్తగా తయారు చేయబడతాయి కొన్నిసార్లు. కానీ, అది కాకుండా అనేక సందర్భాలలో సహజ భాష పాఠ్యాల నుండి ontologies ను **ఉదకించడం** కూడా సాధ్యం. -మైక్రోసాఫ్ట్ రీసెర్చ్ చేసిన ఒక ప్రయత్నం [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste)గా ఫలితమైంది. +ఈ ప్రయత్నం Microsoft Research ద్వారా చేయబడింది, ఫలితంగా [Microsoft Concept Graph](https://blogs.microsoft.com/ai/microsoft-researchers-release-graph-that-helps-machines-conceptualize/?WT.mc_id=academic-77998-cacaste) వచ్చింది. -ఇది `is-a` వారసత్వ సంబంధం ఉపయోగించి సమూహీకరించిన పెద్ద ఎంటిటీ సేకరణ. "మైక్రోసాఫ్ట్ అంటే ఏమిటి?" అనే ప్రశ్నకు "0.87 సాదృశ్యంతో ఒక కంపెనీ, 0.75 సాదృశ్యంతో ఒక బ్రాండ్" వంటి సమాధానాలు ఇస్తుంది. +ఇది `is-a` వారసత్వ సంబంధంతో గుంపులు చేసిన పెద్ద ఎంటిటీల సేకరణ. ఇది "Microsoft అంటే ఏమిటి?" అనే ప్రశ్నలకు "0.87 అవకాశంతో సంస్థ, 0.75 అవకాశంతో బ్రాండ్" లాంటి సమాధానాలు ఇస్తుంది. -గ్రాఫ్ REST APIగా లేదా అన్ని ఎంటిటీ జంటలను జాబితా చేసే పెద్ద టెక్స్ట్ ఫైల్‌గా డౌన్లోడ్ చేసుకోవచ్చు. +గ్రాఫ్ REST API గా లేదా అన్ని ఎంటిటీ జంటలను జాబితా చేసే పెద్ద డౌన్లోడ్ చేయగలిగే టెక్స్ట్ ఫైల్‌గా అందుబాటులో ఉంటుంది. -## ✍️ వ్యాయామం: కాన్సెప్ట్ గ్రాఫ్ +## ✍️ వ్యాయామం: ఒక Concept Graph -మైక్రోసాఫ్ట్ కాన్సెప్ట్ గ్రాఫ్‌ను ఉపయోగించి వార్తా వ్యాసాలను వివిధ వర్గాలుగా ఎలా సమూహీకరించవచ్చో చూడటానికి [MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) నోట్‌బుక్ ప్రయత్నించండి. +[MSConceptGraph.ipynb](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/2-Symbolic/MSConceptGraph.ipynb) నోటుబుక్‌ని ప్రయత్నించి, Microsoft Concept Graph ని ఉపయోగించి వార్తా కథనాలు వివిధ వర్గాలుగా ఎలా బాగుచేయవచ్చునో చూడండి. ## ముగింపు -ఈ రోజుల్లో, AIను తరచుగా *మిషన్ లెర్నింగ్* లేదా *న్యూరల్ నెట్‌వర్క్స్*కు సమానంగా భావిస్తారు. అయితే, మనుషులు స్పష్టమైన తర్కాన్ని కూడా ప్రదర్శిస్తారు, ఇది ప్రస్తుతం న్యూరల్ నెట్‌వర్క్స్ చేత నిర్వహించబడడం లేదు. వాస్తవ ప్రపంచ ప్రాజెక్టుల్లో, వివరణలు అవసరమైన లేదా వ్యవస్థ ప్రవర్తనను నియంత్రితంగా మార్చగలిగే పనుల కోసం స్పష్టమైన తర్కం ఇంకా ఉపయోగించబడుతుంది. +ఈ రోజుల్లో, AIని తరచుగా *Machine Learning* లేదా *Neural Networks* కు సమానంగా భావిస్తారు. కానీ మనిషి కూడా స్పష్టమైన తర్కాన్ని ప్రదర్శిస్తాడు, ఇది ప్రస్తుత Neural Networks ద్వారా యంత్రవంతంగా చేపట్టలేదని భావిస్తున్నారు. నిజమైన ప్రాజెక్టులలో, వివరణ అవసరమయ్యే లేదా వ్యవస్థ ప్రవర్తనను నియంత్రిత మార్గంలో మార్చుకోవడం అవసరం ఉన్న పనుల కోసం ఇంకా explicit reasoning ఉపయోగిస్తున్నారు. ## 🚀 సవాలు -ఈ పాఠ్యాంశానికి సంబంధించిన కుటుంబ ఆంటాలజీ నోట్‌బుక్‌లో, ఇతర కుటుంబ సంబంధాలతో ప్రయోగం చేయవచ్చు. కుటుంబ వృక్షంలో వ్యక్తుల మధ్య కొత్త సంబంధాలను కనుగొనండి. +ఈ పాఠం తో సంబందించిన Family Ontology నోటుబుక్ లో, ఇతర కుటుంబ సంబంధాలతో ప్రయోగాలు చేయవచ్చు. కుటుంబ వృక్షంలో కొత్త వ్యక్తుల మధ్య అనుబంధాలను కనుగొనండి. ## [పోస్ట్-లెక్చర్ క్విజ్](https://ff-quizzes.netlify.app/en/ai/quiz/4) -## సమీక్ష & స్వీయ అధ్యయనం +## సమీక్ష & స్వయంఅభ్యాసం -ఇంటర్నెట్‌లో పరిశోధన చేసి, మనుషులు జ్ఞానాన్ని కొలవడానికి మరియు కోడిఫై చేయడానికి ప్రయత్నించిన ప్రాంతాలను కనుగొనండి. బ్లూమ్ టాక్సోనమీని పరిశీలించండి, మరియు చరిత్రలోకి వెళ్ళి మనుషులు తమ ప్రపంచాన్ని ఎలా అర్థం చేసుకున్నారు తెలుసుకోండి. లినియస్ యొక్క జీవుల వర్గీకరణ పనిని అన్వేషించండి, మరియు డిమిత్రి మెండెలీవ్ రసాయన మూలకాలను వర్ణించడానికి మరియు సమూహీకరించడానికి ఎలా పద్ధతి రూపొందించాడో గమనించండి. మీరు మరెలాంటి ఆసక్తికర ఉదాహరణలను కనుగొంటారు? +ఇంటర్నెట్‌లో కొన్ని పరిశోధనలు చేసి, మనిషులు ఎలా జ్ఞానాన్ని కొలిచేందుకు మరియు కోడిఫై చేయడానికి ప్రయత్నించారో తెలుసుకోండి. Bloom's Taxonomy ని చూడండి, మరియు చరిత్రలోకి వెళ్ళి మనిషి వారి ప్రపంచాన్ని ఎలా అర్థం చేసుకోడానికి ప్రయత్నించారో నేర్చుకోండి. Linnaeus జీవుల వర్గీకరణ Taxonomy సృష్టించడం ఎలా చేశాడో తెలుసుకోండి, Dmitri Mendeleev రసాయన మూలకాల వర్గీకరణ నిర్మాణంలో ఉపయోగించిన విధానాన్ని పరిశీలించండి. మీరు మరే ఇతర ఆసక్తికరమైన ఉదాహరణలు ఏవైనా కనుగొనగలరా? -**అసైన్‌మెంట్**: [ఆంటాలజీ నిర్మించండి](assignment.md) +**అసైన్‌మెంట్**: [ఒక Ontology నిర్మించండి](assignment.md) --- -**అస్పష్టత**: -ఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో పొరపాట్లు లేదా తప్పిదాలు ఉండవచ్చు. మూల పత్రం దాని స్వదేశీ భాషలోనే అధికారిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారానికి, ప్రొఫెషనల్ మానవ అనువాదం చేయించుకోవడం మంచిది. ఈ అనువాదం వలన కలిగే ఏవైనా అపార్థాలు లేదా తప్పుదారుల బాధ్యత మేము తీసుకోము. +**సవరణా నోట్**: +ఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితతపై శ్రద్ధ వహిస్తున్నప్పటికీ, సాంకేతిక అనువాదాల్లో దోషాలు లేదా లోపాలు ఉండవచ్చు. మౌలిక పత్రం దాని మూల భాషలో అధికారిక ఆధారం అని పరిగణించాలి. ముఖ్యమైన సమాచారానికి, సకలమైన మనుష్యా అనువాదాన్ని సలహా ఇస్తారు. ఈ అనువాదం వలన కలిగిన ఎటువంటి అర్ధం తీర్చుకోవడంలో గర్భితుల కోసం మేము బాధ్యత వహించము. \ No newline at end of file