diff --git a/translations/el/.co-op-translator.json b/translations/el/.co-op-translator.json
new file mode 100644
index 00000000..f8cbfbab
--- /dev/null
+++ b/translations/el/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:21:33+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "el"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T01:54:09+00:00",
+ "source_file": "README.md",
+ "language_code": "el"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-29T08:36:52+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "el"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-29T09:31:40+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "el"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-29T09:31:19+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "el"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-29T09:29:29+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "el"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-29T09:28:40+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "el"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-29T09:30:57+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "el"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-29T09:31:53+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "el"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:30:48+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "el"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-29T08:42:06+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "el"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-15T14:36:53+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "el"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:46:45+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "el"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:27:10+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "el"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:28:33+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-15T14:38:40+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "el"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-29T09:02:47+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T08:56:55+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-29T09:10:04+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T08:56:25+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-29T09:08:51+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T08:57:14+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-29T09:11:44+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:48:39+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T08:51:07+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-29T08:52:24+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T08:50:15+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T08:49:56+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:55:00+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T08:50:42+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-29T08:48:47+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-29T08:50:39+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T08:52:32+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T08:53:31+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T08:51:44+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-29T08:54:24+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T08:53:08+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-29T08:57:08+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-29T08:45:13+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T09:01:12+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-29T09:28:22+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T09:00:44+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-29T09:27:00+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T08:58:26+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-29T09:19:12+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T09:00:06+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-29T09:25:41+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T08:57:58+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-29T09:18:15+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T08:58:37+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-29T09:21:11+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T08:59:37+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-29T09:23:22+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T08:59:18+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "el"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-29T09:16:04+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "el"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T08:47:52+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "el"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T08:49:12+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "el"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-29T08:41:48+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "el"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T08:48:14+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "el"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-29T08:40:03+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "el"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-29T09:03:00+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "el"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-29T08:37:22+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "el"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-29T08:43:54+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "el"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-29T09:13:33+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "el"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-29T09:12:07+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "el"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:44:06+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "el"
+ }
+}
\ No newline at end of file
diff --git a/translations/el/AGENTS.md b/translations/el/AGENTS.md
index c02eb848..b6cfe136 100644
--- a/translations/el/AGENTS.md
+++ b/translations/el/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Επισκόπηση Έργου
diff --git a/translations/el/README.md b/translations/el/README.md
index c3546ad2..dfaaaba0 100644
--- a/translations/el/README.md
+++ b/translations/el/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -21,212 +12,214 @@ CO_OP_TRANSLATOR_METADATA:
[](https://discord.gg/nTYy5BXMWG)
-# Τεχνητή Νοημοσύνη για Αρχάριους - Ένα Πρόγραμμα Σπουδών
+# Τεχνητή Νοημοσύνη για Αρχάριους - Ένα Αναλυτικό Πρόγραμμα Σπουδών
-||
+||
|:---:|
-| Τεχνητή Νοημοσύνη για Αρχάριους - _Σχεδιάγραμμα από τη [@girlie_mac](https://twitter.com/girlie_mac)_ |
+| Τεχνητή Νοημοσύνη για Αρχάριους - _Σημειώσεις από [@girlie_mac](https://twitter.com/girlie_mac)_ |
-Εξερευνήστε τον κόσμο της **Τεχνητής Νοημοσύνης** (AI) με το 12-εβδομάδων, 24-μαθημάτων πρόγραμμα σπουδών μας! Περιλαμβάνει πρακτικά μαθήματα, κουίζ και εργαστήρια. Το πρόγραμμα είναι φιλικό για αρχάριους και καλύπτει εργαλεία όπως TensorFlow και PyTorch, καθώς και θέματα ηθικής στην AI.
+Εξερευνήστε τον κόσμο της **Τεχνητής Νοημοσύνης** (AI) με το 12-εβδομαδιαίο, 24-μαθημάτων πρόγραμμα σπουδών μας! Περιλαμβάνει πρακτικά μαθήματα, τεστ και εργαστήρια. Το πρόγραμμα είναι φιλικό για αρχάριους και καλύπτει εργαλεία όπως TensorFlow και PyTorch, καθώς και ζητήματα ηθικής στην AI
-### 🌐 Υποστήριξη Πολλών Γλωσσών
-#### Υποστηρίζεται μέσω GitHub Action (Αυτοματοποιημένο & Πάντα Ενημερωμένο)
+### 🌐 Υποστήριξη Πολλαπλών Γλωσσών
+
+#### Υποστηρίζεται μέσω GitHub Action (Αυτοματοποιημένη & Πάντα Ενημερωμένη)
-[Αραβικά](../ar/README.md) | [Βεγγαλικά](../bn/README.md) | [Βουλγαρικά](../bg/README.md) | [Βιρμανικά (Μιανμάρ)](../my/README.md) | [Κινέζικα (Απλοποιημένα)](../zh/README.md) | [Κινέζικα (Παραδοσιακά, Χονγκ Κονγκ)](../hk/README.md) | [Κινέζικα (Παραδοσιακά, Μακάου)](../mo/README.md) | [Κινέζικα (Παραδοσιακά, Ταϊβάν)](../tw/README.md) | [Κροατικά](../hr/README.md) | [Τσέχικα](../cs/README.md) | [Δανικά](../da/README.md) | [Ολλανδικά](../nl/README.md) | [Εσθονικά](../et/README.md) | [Φινλανδικά](../fi/README.md) | [Γαλλικά](../fr/README.md) | [Γερμανικά](../de/README.md) | [Ελληνικά](./README.md) | [Εβραϊκά](../he/README.md) | [Χίντι](../hi/README.md) | [Ουγγρικά](../hu/README.md) | [Ινδονησιακά](../id/README.md) | [Ιταλικά](../it/README.md) | [Ιαπωνικά](../ja/README.md) | [Κανάντα](../kn/README.md) | [Κορεατικά](../ko/README.md) | [Λιθουανικά](../lt/README.md) | [Μαλαισιανά](../ms/README.md) | [Μαλαγιαλάμ](../ml/README.md) | [Μαραθικά](../mr/README.md) | [Νεπάλι](../ne/README.md) | [Νιγηριανά Πίνγκιν](../pcm/README.md) | [Νορβηγικά](../no/README.md) | [Περσικά (Φαρσί)](../fa/README.md) | [Πολωνικά](../pl/README.md) | [Πορτογαλικά (Βραζιλίας)](../br/README.md) | [Πορτογαλικά (Πορτογαλίας)](../pt/README.md) | [Πουντζαμπικά (Gurmukhi)](../pa/README.md) | [Ρουμανικά](../ro/README.md) | [Ρωσικά](../ru/README.md) | [Σερβικά (Κυριλλικά)](../sr/README.md) | [Σλοβακικά](../sk/README.md) | [Σλοβενικά](../sl/README.md) | [Ισπανικά](../es/README.md) | [Σουαχίλι](../sw/README.md) | [Σουηδικά](../sv/README.md) | [Ταγκάλιγκ (Φιλιππινέζικα)](../tl/README.md) | [Ταμίλ](../ta/README.md) | [Τελούγκου](../te/README.md) | [Ταϊλανδικά](../th/README.md) | [Τουρκικά](../tr/README.md) | [Ουκρανικά](../uk/README.md) | [Ουρντού](../ur/README.md) | [Βιετναμικά](../vi/README.md)
+[Αραβικά](../ar/README.md) | [Μπενγκάλι](../bn/README.md) | [Βουλγαρικά](../bg/README.md) | [Βιρμανικά (Μιανμάρ)](../my/README.md) | [Κινέζικα (Απλοποιημένα)](../zh-CN/README.md) | [Κινέζικα (Παραδοσιακά, Χονγκ Κονγκ)](../zh-HK/README.md) | [Κινέζικα (Παραδοσιακά, Μακάο)](../zh-MO/README.md) | [Κινέζικα (Παραδοσιακά, Ταϊβάν)](../zh-TW/README.md) | [Κροατικά](../hr/README.md) | [Τσέχικα](../cs/README.md) | [Δανικά](../da/README.md) | [Ολλανδικά](../nl/README.md) | [Εσθονικά](../et/README.md) | [Φινλανδικά](../fi/README.md) | [Γαλλικά](../fr/README.md) | [Γερμανικά](../de/README.md) | [Ελληνικά](./README.md) | [Εβραϊκά](../he/README.md) | [Χίντι](../hi/README.md) | [Ουγγρικά](../hu/README.md) | [Ινδονησιακά](../id/README.md) | [Ιταλικά](../it/README.md) | [Ιαπωνικά](../ja/README.md) | [Κανάντα](../kn/README.md) | [Κορεατικά](../ko/README.md) | [Λιθουανικά](../lt/README.md) | [Μαλαισιανά](../ms/README.md) | [Μαλαγιάλαμ](../ml/README.md) | [Μαράθι](../mr/README.md) | [Νεπάλ](../ne/README.md) | [Νιγηριανή Πίτζιν](../pcm/README.md) | [Νορβηγικά](../no/README.md) | [Περσικά (Φαρσί)](../fa/README.md) | [Πολωνικά](../pl/README.md) | [Πορτογαλικά (Βραζιλία)](../pt-BR/README.md) | [Πορτογαλικά (Πορτογαλία)](../pt-PT/README.md) | [Πουντζαμπικά (Γκουρμούκι)](../pa/README.md) | [Ρουμανικά](../ro/README.md) | [Ρωσικά](../ru/README.md) | [Σερβικά (Κυριλλικά)](../sr/README.md) | [Σλοβακικά](../sk/README.md) | [Σλοβενικά](../sl/README.md) | [Ισπανικά](../es/README.md) | [Σουαχίλι](../sw/README.md) | [Σουηδικά](../sv/README.md) | [Ταγκαλόγκ (Φιλιππινέζικα)](../tl/README.md) | [Ταμίλ](../ta/README.md) | [Τελούγκου](../te/README.md) | [Ταϊλανδικά](../th/README.md) | [Τούρκικα](../tr/README.md) | [Ουκρανικά](../uk/README.md) | [Ουρντού](../ur/README.md) | [Βιετναμέζικα](../vi/README.md)
-> **Προτιμάτε να Κλωνοποιήσετε Τοπικά;**
+> **Προτιμάτε να κάνετε τοποθέτηση τοπικά;**
-> Αυτό το αποθετήριο περιλαμβάνει 50+ μεταφράσεις γλωσσών, οι οποίες αυξάνουν σημαντικά το μέγεθος λήψης. Για κλωνοποίηση χωρίς μεταφράσεις, χρησιμοποιήστε sparse checkout:
+> Αυτό το αποθετήριο περιλαμβάνει 50+ μεταφράσεις γλωσσών που αυξάνουν σημαντικά το μέγεθος λήψης. Για να κάνετε τοποθέτηση χωρίς τις μεταφράσεις, χρησιμοποιήστε sparse checkout:
> ```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'
> ```
-> Αυτό σας δίνει όλα όσα χρειάζεστε για να ολοκληρώσετε το μάθημα με πολύ γρηγορότερη λήψη.
+> Με αυτόν τον τρόπο έχετε όλα όσα χρειάζεστε για να ολοκληρώσετε το μάθημα με πολύ πιο γρήγορη λήψη.
-**Αν επιθυμείτε να υποστηριχθούν επιπλέον γλώσσες μεταφράσεων, αυτές αναγράφονται [εδώ](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
+**Αν θέλετε να υποστηριχθούν επιπλέον γλώσσες μετάφρασης, αυτές αναφέρονται [εδώ](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Εγγραφείτε στην Κοινότητα
[](https://discord.gg/nTYy5BXMWG)
## Τι θα μάθετε
-**[Εννοιολογικός Χάρτης του Μαθήματος](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
+**[Χάρτης Εννοιών του Μαθήματος](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
Σε αυτό το πρόγραμμα σπουδών, θα μάθετε:
-* Διαφορετικές προσεγγίσεις στην Τεχνητή Νοημοσύνη, συμπεριλαμβανομένης της "παραδοσιακής" συμβολικής προσέγγισης με **Αναπαράσταση Γνώσης** και λογική ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
-* **Νευρωνικά Δίκτυα** και **Βαθιά Μάθηση**, που βρίσκονται στον πυρήνα της σύγχρονης AI. Θα αναδείξουμε τις έννοιες πίσω από αυτά τα σημαντικά θέματα χρησιμοποιώντας κώδικα σε δύο από τα πιο δημοφιλή πλαίσια - [TensorFlow](http://Tensorflow.org) και [PyTorch](http://pytorch.org).
-* **Νευρωνικές Αρχιτεκτονικές** για εργασία με εικόνες και κείμενο. Θα καλύψουμε πρόσφατα μοντέλα, αλλά ίσως λείπει λίγη από την τελευταία λέξη της τεχνολογίας.
-* Λιγότερο δημοφιλείς προσεγγίσεις AI, όπως **Γενετικοί Αλγόριθμοι** και **Συστήματα Πολυ-Πρακτόρων**.
+* Διαφορετικές προσεγγίσεις στην Τεχνητή Νοημοσύνη, συμπεριλαμβανομένης της "παλιάς καλής" συμβολικής προσέγγισης με **Αναπαράσταση Γνώσης** και συλλογισμό ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* **Νευρωνικά Δίκτυα** και **Βαθιά Μάθηση**, που αποτελούν τον πυρήνα της σύγχρονης AI. Θα απεικονίσουμε τις έννοιες πίσω από αυτά τα σημαντικά θέματα με κώδικα σε δύο από τα πιο δημοφιλή frameworks - [TensorFlow](http://Tensorflow.org) και [PyTorch](http://pytorch.org).
+* **Νευρωνικές Αρχιτεκτονικές** για επεξεργασία εικόνων και κειμένου. Θα καλύψουμε πρόσφατα μοντέλα, αλλά ίσως να μην είναι πλήρως state-of-the-art.
+* Λιγότερο δημοφιλείς προσεγγίσεις AI, όπως **Γενετικοί Αλγόριθμοι** και **Πολυ-πρακτορικά Συστήματα**.
Τι δεν θα καλυφθεί σε αυτό το πρόγραμμα σπουδών:
-> [Βρείτε όλους τους επιπλέον πόρους για αυτό το μάθημα στη συλλογή μας στο Microsoft Learn](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Βρείτε όλους τους επιπλέον πόρους για αυτό το μάθημα στη συλλογή Microsoft Learn μας](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* Επιχειρηματικά παραδείγματα χρήσης της **AI στις Επιχειρήσεις**. Σκεφτείτε να παρακολουθήσετε τη διαδρομή μάθησης [Εισαγωγή στην AI για επιχειρηματικούς χρήστες](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) στο Microsoft Learn, ή το [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), που αναπτύχθηκε σε συνεργασία με το [INSEAD](https://www.insead.edu/).
-* **Κλασική Μηχανική Μάθηση**, που περιγράφεται καλά στο πρόγραμμα σπουδών μας [Machine Learning for Beginners](http://github.com/Microsoft/ML-for-Beginners).
-* Πρακτικές εφαρμογές AI που χρησιμοποιούν **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Για αυτό, προτείνουμε να ξεκινήσετε με τα μονοπάτια Microsoft Learn για [όραση](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [επεξεργασία φυσικής γλώσσας](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Γεννητική AI με το Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** και άλλα.
-* Συγκεκριμένα πλαίσια ML στο cloud, όπως [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), ή [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Σκεφτείτε να χρησιμοποιήσετε τα μονοπάτια μάθησης [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) και [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).
-* **Συνομιλητική AI** και **Chat Bots**. Υπάρχει ξεχωριστό μονοπάτι μάθησης [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), και μπορείτε επίσης να ανατρέξετε σε [αυτό το blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) για περισσότερες λεπτομέρειες.
-* **Βαθιά Μαθηματικά** πίσω από τη βαθιά μάθηση. Για αυτό, προτείνουμε το βιβλίο [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) από τους Ian Goodfellow, Yoshua Bengio και Aaron Courville, που είναι διαθέσιμο και online στο [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
+* Επιχειρηματικές περιπτώσεις χρήσης της **AI στις Επιχειρήσεις**. Σκεφτείτε να ακολουθήσετε την εκπαιδευτική διαδρομή [Εισαγωγή στην AI για επιχειρηματικούς χρήστες](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) στο Microsoft Learn, ή το [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), που αναπτύχθηκε σε συνεργασία με το [INSEAD](https://www.insead.edu/).
+* **Κλασική Μηχανική Μάθηση**, που περιγράφεται καλά στο [Πρόγραμμα Σπουδών Μηχανικής Μάθησης για Αρχάριους](http://github.com/Microsoft/ML-for-Beginners).
+* Πρακτικές εφαρμογές AI που βασίζονται σε **[Υπηρεσίες Γνώσης](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Για αυτό, προτείνουμε να ξεκινήσετε με τα μαθήματα στο Microsoft Learn για [όραση](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [επεξεργασία φυσικής γλώσσας](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Γενετική AI με Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** και άλλα.
+* Ειδικά **Cloud Frameworks** για ML, όπως [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), ή [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Σκεφτείτε να χρησιμοποιήσετε τις εκπαιδευτικές διαδρομές [Κατασκευή και λειτουργία λύσεων μηχανικής μάθησης με Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) και [Κατασκευή και Λειτουργία Λύσεων Μηχανικής Μάθησης με Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
+* **Συνομιλητική AI** και **Chat Bots**. Υπάρχει ξεχωριστή εκπαιδευτική διαδρομή [Δημιουργία συνομιλητικών λύσεων AI](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), και μπορείτε επίσης να αναφερθείτε σε [αυτό το άρθρο ιστολογίου](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) για περισσότερες λεπτομέρειες.
+* **Βαθιά Μαθηματικά** πίσω από τη βαθιά μάθηση. Για αυτό, προτείνουμε το βιβλίο [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) των Ian Goodfellow, Yoshua Bengio και Aaron Courville, που είναι επίσης διαθέσιμο online στο [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
-Για μια απλή εισαγωγή στα θέματα _AI στο Cloud_ μπορείτε να παρακολουθήσετε το Μονοπάτι Μάθησης [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).
+Για μια απλή εισαγωγή στα θέματα _AI στο Cloud_ μπορείτε να ακολουθήσετε την Εκπαιδευτική Διαδρομή [Ξεκινήστε με τεχνητή νοημοσύνη στο Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
# Περιεχόμενο
| | Σύνδεσμος Μαθήματος | PyTorch/Keras/TensorFlow | Εργαστήριο |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
-| 0 | [Ρύθμιση Μαθήματος](./lessons/0-course-setup/setup.md) | [Ρύθμιση του περιβάλλοντος ανάπτυξής σας](./lessons/0-course-setup/how-to-run.md) | |
+| 0 | [Ρύθμιση Μαθήματος](./lessons/0-course-setup/setup.md) | [Ρύθμιση Περιβάλλοντος Ανάπτυξης](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Εισαγωγή στην AI**](./lessons/1-Intro/README.md) | | |
| 01 | [Εισαγωγή και Ιστορία της AI](./lessons/1-Intro/README.md) | - | - |
| II | **Συμβολική AI** |
-| 02 | [Αναπαράσταση Γνώσης και Συστήματα Ειδικών](./lessons/2-Symbolic/README.md) | [Συστήματα Ειδικών](./lessons/2-Symbolic/Animals.ipynb) / [Οντολογία](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Γράφημα Εννοιών](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
+| 02 | [Αναπαράσταση Γνώσης και Ειδικά Συστήματα](./lessons/2-Symbolic/README.md) | [Ειδικά Συστήματα](./lessons/2-Symbolic/Animals.ipynb) / [Οντολογία](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Γράφος Εννοιών](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Εισαγωγή στα Νευρωνικά Δίκτυα**](./lessons/3-NeuralNetworks/README.md) |||
-| 03 | [Περσέπτρων](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Τετράδιο](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Εργαστήριο](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
-| 04 | [Πολυεπίπεδο Περσέπτρων και Δημιουργία του δικού μας Πλαισίου Εργασίας](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Τετράδιο](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Εργαστήριο](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
-| 05 | [Εισαγωγή σε Πλαίσια Εργασίας (PyTorch/TensorFlow) και Υπερεκπαίδευση](./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) | [Εργαστήριο](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
-| IV | [**Υπολογιστική Όραση**](./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)| [Εξερευνήστε την Υπολογιστική Όραση στο Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
-| 06 | [Εισαγωγή στην Υπολογιστική Όραση. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Τετράδιο](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
+| 03 | [Περσέπτoν](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Σημειωματάριο](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Εργαστήριο](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
+| 04 | [Πολυεπίπεδο Περσέπτoν και Δημιουργία του δικού μας Πλαισίου](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Σημειωματάριο](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Εργαστήριο](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 05 | [Εισαγωγή στα Πλαίσια (PyTorch/TensorFlow) και Υπερπροσαρμογή](./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) | [Εργαστήριο](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
+| IV | [**Επιστήμη Υπολογιστών Όρασης**](./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)| [Εξερευνήστε την Επιστήμη Υπολογιστών Όρασης στο Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
+| 06 | [Εισαγωγή στην Επιστήμη Υπολογιστών Όρασης. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Σημειωματάριο](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
| 07 | [Συνελικτικά Νευρωνικά Δίκτυα](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Αρχιτεκτονικές CNN](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
-| 08 | [Προεκπαιδευμένα Δίκτυα και Μεταφορά Μάθησης](./lessons/4-ComputerVision/08-TransferLearning/README.md) και [Τεχνάσματα Εκπαίδευσης](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
+| 08 | [Προεκπαιδευμένα Δίκτυα και Μεταφορά Μάθησης](./lessons/4-ComputerVision/08-TransferLearning/README.md) και [Τεχνικές Εκπαίδευσης](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
| 09 | [Αυτόματοι Κωδικοποιητές και 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 | [Γενετικά Ανταγωνιστικά Δίκτυα & Μεταφορά Καλλιτεχνικού Στυλ](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Ανίχνευση Αντικειμένων](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Εργαστήριο](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
-| 12 | [Σημασιολογική Τμηματοποίηση. 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) | |
+| 12 | [Σημασιολογικός Διαχωρισμός. 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 | [**Επεξεργασία Φυσικής Γλώσσας**](./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) | [Εξερευνήστε την Επεξεργασία Φυσικής Γλώσσας στο Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Αναπαράσταση Κειμένου. 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 | [Σημασιολογικές Ενσωματώσεις Λέξεων. Word2Vec και 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 | [Μοντελοποίηση Γλώσσας. Εκπαίδευση των δικών σου ενσωματώσεων](./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) | [Εργαστήριο](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
-| 16 | [Επαναλαμβανόμενα Νευρωνικά Δίκτυα](./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 | [Γενετικά Επαναλαμβανόμενα Δίκτυα](./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) | [Εργαστήριο](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
+| 15 | [Μοντελοποίηση Γλώσσας. Εκπαίδευση των δικών σας Ενσωματώσεων](./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) | [Εργαστήριο](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
+| 16 | [Επαναφορικά Νευρωνικά Δίκτυα](./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 | [Γενετικά Επαναφορικά Δίκτυα](./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) | [Εργαστήριο](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
| 18 | [Μετασχηματιστές. 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 | [Αναγνώριση Οντοτήτων με Όνομα](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Εργαστήριο](./lessons/5-NLP/19-NER/lab/README.md) |
-| 20 | [Μεγάλα Μοντέλα Γλώσσας, Προγραμματισμός Προτροπών και Εργασίες με Λίγα Παραδείγματα](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| 19 | [Αναγνώριση Ονομαστικών Οντοτήτων](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Εργαστήριο](./lessons/5-NLP/19-NER/lab/README.md) |
+| 20 | [Μεγάλα Μοντέλα Γλώσσας, Προγραμματισμός Εντολών και Ασκήσεις με Λίγα Παραδείγματα](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Άλλες Τεχνικές Τεχνητής Νοημοσύνης** || |
-| 21 | [Γενετικοί Αλγόριθμοι](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Τετράδιο](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
-| 22 | [Βαθιά Ενισχυτική Μάθηση](./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) | [Εργαστήριο](./lessons/6-Other/22-DeepRL/lab/README.md) |
-| 23 | [Συστήματα Πολυ-Πρακτόρων](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
+| 21 | [Γενετικοί Αλγόριθμοι](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Σημειωματάριο](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
+| 22 | [Ενισχυτική Μάθηση Βαθιάς Μάθησης](./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) | [Εργαστήριο](./lessons/6-Other/22-DeepRL/lab/README.md) |
+| 23 | [Πολυπρακτορικά Συστήματα](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **Ηθική της Τεχνητής Νοημοσύνης** | | |
-| 24 | [Ηθική της AI και Υπεύθυνη Τεχνητή Νοημοσύνη](./lessons/7-Ethics/README.md) | [Microsoft Learn: Αρχές Υπεύθυνης AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
+| 24 | [Ηθική της Τεχνητής Νοημοσύνης και Υπεύθυνη Τεχνητή Νοημοσύνη](./lessons/7-Ethics/README.md) | [Microsoft Learn: Αρχές Υπεύθυνης Τεχνητής Νοημοσύνης](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
| IX | **Επιπλέον** | | |
-| 25 | [Πολυμορφικά Δίκτυα, CLIP και VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Τετράδιο](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
+| 25 | [Πολυτροπικά Δίκτυα, CLIP και VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Σημειωματάριο](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Κάθε μάθημα περιλαμβάνει
* Υλικό προανάγνωσης
-* Εκτελέσιμα Jupyter Notebooks, τα οποία συχνά είναι ειδικά για το πλαίσιο εργασίας (**PyTorch** ή **TensorFlow**). Το εκτελέσιμο τετράδιο περιέχει επίσης πολύ θεωρητικό υλικό, ώστε για να κατανοήσετε το θέμα πρέπει να περάσετε τουλάχιστον από μία έκδοση του τετραδίου (είτε PyTorch είτε TensorFlow).
-* **Εργαστήρια** διαθέσιμα για ορισμένα θέματα, που σας δίνουν την ευκαιρία να δοκιμάσετε την εφαρμογή του υλικού που μάθατε σε ένα συγκεκριμένο πρόβλημα.
-* Κάποιες ενότητες περιέχουν συνδέσμους σε [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) ενότητες που καλύπτουν συναφή θέματα.
+* Εκτελέσιμα Σημειωματάρια Jupyter, που συχνά είναι συγκεκριμένα για το πλαίσιο (**PyTorch** ή **TensorFlow**). Το εκτελέσιμο σημειωματάριο περιέχει επίσης πολύ θεωρητικό υλικό, οπότε για να κατανοήσετε το θέμα χρειάζεται να περάσετε τουλάχιστον από μία έκδοση του σημειωματάριου (είτε PyTorch είτε TensorFlow).
+* **Εργαστήρια** διαθέσιμα σε ορισμένα θέματα, που σας δίνουν την ευκαιρία να δοκιμάσετε την εφαρμογή του υλικού που έχετε μάθει σε ένα συγκεκριμένο πρόβλημα.
+* Ορισμένα τμήματα περιέχουν συνδέσμους σε μονάδες [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) που καλύπτουν σχετικές θεματικές.
## Ξεκινώντας
-### 🎯 Νέος στα AI; Ξεκίνα Εδώ!
+### 🎯 Είστε νέοι στην Τεχνητή Νοημοσύνη; Ξεκινήστε Εδώ!
-Αν είστε εντελώς νέος στα AI και θέλετε γρήγορα, πρακτικά παραδείγματα, δείτε τα [**Φιλικά για Αρχάριους Παραδείγματα**](./examples/README.md)! Αυτά περιλαμβάνουν:
+Εάν είστε εντελώς νέοι στην Τεχνητή Νοημοσύνη και θέλετε γρήγορα, πρακτικά παραδείγματα, ρίξτε μια ματιά στα [**Φιλικά προς Αρχάριους Παραδείγματα**](./examples/README.md)! Αυτά περιλαμβάνουν:
-- 🌟 **Γεια σου Κόσμε AI** - Το πρώτο σου πρόγραμμα AI (αναγνώριση προτύπων)
+- 🌟 **Γεια σου Κόσμε AI** - Το πρώτο σας πρόγραμμα τεχνητής νοημοσύνης (ανίχνευση προτύπων)
- 🧠 **Απλό Νευρωνικό Δίκτυο** - Δημιουργία ενός νευρωνικού δικτύου από το μηδέν
-- 🖼️ **Ταξινομητής Εικόνων** - Ταξινόμηση εικόνων με λεπτομερή σχόλια
-- 💬 **Συναισθηματική Ανάλυση Κειμένου** - Ανάλυση θετικού/αρνητικού κειμένου
-Αυτά τα παραδείγματα έχουν σχεδιαστεί για να σας βοηθήσουν να κατανοήσετε τις έννοιες της ΤΝ πριν βουτήξετε στο πλήρες πρόγραμμα σπουδών.
+- 🖼️ **Ταξινομητής Εικόνων** - Ταξινομήστε εικόνες με λεπτομερή σχόλια
+- 💬 **Συναισθηματική Ανάλυση Κειμένου** - Αναλύστε θετικό/αρνητικό κείμενο
+
+Αυτά τα παραδείγματα έχουν σχεδιαστεί για να σας βοηθήσουν να κατανοήσετε τις έννοιες της τεχνητής νοημοσύνης πριν προχωρήσετε στο πλήρες πρόγραμμα σπουδών.
### 📚 Ρύθμιση Πλήρους Προγράμματος Σπουδών
-- Έχουμε δημιουργήσει ένα [μάθημα ρύθμισης](./lessons/0-course-setup/setup.md) για να σας βοηθήσουμε με τη ρύθμιση του περιβάλλοντος ανάπτυξής σας. - Για εκπαιδευτικούς, έχουμε επίσης δημιουργήσει ένα [μάθημα ρύθμισης προγράμματος σπουδών](./lessons/0-course-setup/for-teachers.md)!
-- Πώς να [τρέξετε τον κώδικα σε VSCode ή Codespace](./lessons/0-course-setup/how-to-run.md)
+- Έχουμε δημιουργήσει ένα [μάθημα ρύθμισης](./lessons/0-course-setup/setup.md) για να σας βοηθήσουμε με την εγκατάσταση του περιβάλλοντος ανάπτυξής σας. - Για τους εκπαιδευτικούς, έχουμε επίσης δημιουργήσει ένα [μάθημα ρύθμισης προγράμματος σπουδών](./lessons/0-course-setup/for-teachers.md)!
+- Πώς να [Τρέξετε τον κώδικα σε VSCode ή Codespace](./lessons/0-course-setup/how-to-run.md)
-Ακολουθήστε αυτά τα βήματα:
+Ακολουθήστε τα παρακάτω βήματα:
-Κλωνοποιήστε το Αποθετήριο: Κάντε κλικ στο κουμπί "Fork" στην πάνω δεξιά γωνία αυτής της σελίδας.
+Δημιουργήστε Fork στο Αποθετήριο: Κάντε κλικ στο κουμπί "Fork" στην πάνω δεξιά γωνία αυτής της σελίδας.
Κλωνοποιήστε το Αποθετήριο: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-Μην ξεχάσετε να βάλετε αστέρι (🌟) σε αυτό το αποθετήριο για να το βρείτε πιο εύκολα αργότερα.
+Μην ξεχάσετε να βάλετε αστέρι (🌟) σε αυτό το αποθετήριο για να το βρίσκετε πιο εύκολα αργότερα.
## Γνωρίστε άλλους Μαθητές
-Εγγραφείτε στον [επίσημο Discord server για ΤΝ](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) για να γνωρίσετε και να δικτυωθείτε με άλλους μαθητές που παρακολουθούν αυτό το μάθημα και να λάβετε υποστήριξη.
+Εγγραφείτε στο [επίσημο Discord server AI](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) για να γνωρίσετε και να δικτυωθείτε με άλλους μαθητές που παρακολουθούν αυτό το μάθημα και λάβετε υποστήριξη.
-Εάν έχετε σχόλια για το προϊόν ή ερωτήσεις κατά την κατασκευή, επισκεφτείτε το [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
+Αν έχετε σχόλια ή ερωτήσεις κατά την ανάπτυξη, επισκεφτείτε το [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
-## Κουίζ
+## Κουίζ
-> **Σημείωση για τα κουίζ**: Όλα τα κουίζ περιέχονται στον φάκελο Quiz-app στο etc\quiz-app, ή [Online Εδώ](https://ff-quizzes.netlify.app/) Συνδέονται από μέσα στα μαθήματα, η εφαρμογή κουίζ μπορεί να τρέξει τοπικά ή να αναπτυχθεί στο Azure· ακολουθήστε τις οδηγίες στον φάκελο `quiz-app`. Σταδιακά το υλικό μεταφράζεται.
+> **Σημείωση για τα κουίζ**: Όλα τα κουίζ βρίσκονται στον φάκελο Quiz-app στο etc\quiz-app, ή [Online Εδώ](https://ff-quizzes.netlify.app/) Συνδέονται μέσα από τα μαθήματα και η εφαρμογή κουίζ μπορεί να τρέξει τοπικά ή να αναπτυχθεί στο Azure· ακολουθήστε τις οδηγίες στον φάκελο `quiz-app`. Βρίσκονται σταδιακά σε διαδικασία τοπικοποίησης.
## Ζητείται Βοήθεια
-Έχετε προτάσεις ή βρήκατε ορθογραφικά ή σφάλματα κώδικα; Δημιουργήστε ένα θέμα ή μια αίτηση pull.
+Έχετε προτάσεις ή έχετε βρει ορθογραφικά ή κωδικογραφικά λάθη; Δημιουργήστε ένα issue ή κάντε pull request.
## Ειδικές Ευχαριστίες
-* **✍️ Κύριος Συγγραφέας:** [Dmitry Soshnikov](http://soshnikov.com), PhD
-* **🔥 Επιμελήτρια:** [Jen Looper](https://twitter.com/jenlooper), PhD
-* **🎨 Εικονογράφος Σημειώσεων:** [Tomomi Imura](https://twitter.com/girlie_mac)
-* **✅ Δημιουργός Κουίζ:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
-* **🙏 Κύριοι Συνεισφέροντες:** [Evgenii Pishchik](https://github.com/Pe4enIks)
+* **✍️ Κύριος Συγγραφέας:** [Dmitry Soshnikov](http://soshnikov.com), PhD
+* **🔥 Επιμελητής:** [Jen Looper](https://twitter.com/jenlooper), PhD
+* **🎨 Εικονογράφος Sketchnote:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **✅ Δημιουργός Κουίζ:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
+* **🙏 Κύριοι Συνεισφέροντες:** [Evgenii Pishchik](https://github.com/Pe4enIks)
## Άλλα Προγράμματα Σπουδών
-Η ομάδα μας παράγει και άλλα προγράμματα σπουδών! Δείτε:
+Η ομάδα μας παράγει και άλλα προγράμματα σπουδών! Δείτε τα:
-### LangChain
-[](https://aka.ms/langchain4j-for-beginners)
-[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
+### LangChain
+[](https://aka.ms/langchain4j-for-beginners)
+[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
---
-### Azure / Edge / MCP / Agents
-[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
+### Azure / Edge / MCP / Agents
+[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-### Σειρά Γενετικής ΤΝ
-[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
-[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
-[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
+### Σειρά Γενετικής Τεχνητής Νοημοσύνης
+[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
+[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
+[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
---
-### Βασική Μάθηση
-[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
+### Βασική Μάθηση
+[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-### Σειρά Copilot
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+### Σειρά Copilot
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
## Λήψη Βοήθειας
-Αν κολλήσετε ή έχετε ερωτήσεις σχετικά με την κατασκευή εφαρμογών ΤΝ. Ενταχθείτε σε συζητήσεις με άλλους μαθητές και έμπειρους προγραμματιστές για το MCP. Είναι μια υποστηρικτική κοινότητα όπου οι ερωτήσεις είναι ευπρόσδεκτες και η γνώση μοιράζεται ελεύθερα.
+Αν κολλήσετε ή έχετε οποιεσδήποτε ερωτήσεις σχετικά με την ανάπτυξη εφαρμογών AI. Συμμετάσχετε με άλλους μαθητές και έμπειρους προγραμματιστές σε συζητήσεις για το MCP. Είναι μια υποστηρικτική κοινότητα όπου οι ερωτήσεις είναι ευπρόσδεκτες και η γνώση μοιράζεται ελεύθερα.
[](https://discord.gg/nTYy5BXMWG)
-Εάν έχετε σχόλια ή λάθη κατά την κατασκευή, επισκεφτείτε:
+Αν έχετε σχόλια ή σφάλματα κατά την ανάπτυξη επισκεφτείτε:
[](https://aka.ms/foundry/forum)
---
-**Αποποίηση Ευθύνης**:
-Αυτό το έγγραφο έχει μεταφραστεί χρησιμοποιώντας την υπηρεσία αυτόματης μετάφρασης AI [Co-op Translator](https://github.com/Azure/co-op-translator). Παρόλο που επιδιώκουμε την ακρίβεια, παρακαλούμε να έχετε υπόψη ότι οι αυτόματες μεταφράσεις ενδέχεται να περιέχουν λάθη ή ανακρίβειες. Το πρωτότυπο έγγραφο στη μητρική του γλώσσα θα πρέπει να θεωρείται η επίσημη πηγή. Για κρίσιμες πληροφορίες, συνιστάται επαγγελματική μετάφραση από ανθρώπους. Δεν φέρουμε ευθύνη για οποιεσδήποτε παρανοήσεις ή λανθασμένες ερμηνείες που προκύπτουν από τη χρήση αυτής της μετάφρασης.
+**Αποποίηση ευθυνών**:
+Αυτό το έγγραφο έχει μεταφραστεί χρησιμοποιώντας την υπηρεσία αυτόματης μετάφρασης AI [Co-op Translator](https://github.com/Azure/co-op-translator). Ενώ προσπαθούμε για ακρίβεια, παρακαλώ σημειώστε ότι οι αυτοματοποιημένες μεταφράσεις ενδέχεται να περιέχουν λάθη ή ανακρίβειες. Το πρωτότυπο έγγραφο στην αρχική του γλώσσα πρέπει να θεωρείται η αυθεντική πηγή. Για κρίσιμες πληροφορίες, συνιστάται επαγγελματική ανθρώπινη μετάφραση. Δεν φέρουμε ευθύνη για τυχόν παρεξηγήσεις ή λανθασμένες ερμηνείες που προκύπτουν από τη χρήση αυτής της μετάφρασης.
\ No newline at end of file
diff --git a/translations/el/SECURITY.md b/translations/el/SECURITY.md
index afb0dd54..6ddbf222 100644
--- a/translations/el/SECURITY.md
+++ b/translations/el/SECURITY.md
@@ -1,12 +1,3 @@
-
## Ασφάλεια
Η Microsoft λαμβάνει σοβαρά υπόψη την ασφάλεια των προϊόντων και υπηρεσιών λογισμικού της, συμπεριλαμβανομένων όλων των αποθετηρίων πηγαίου κώδικα που διαχειρίζεται μέσω των οργανισμών της στο GitHub, όπως οι [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) και [οι οργανισμοί μας στο GitHub](https://opensource.microsoft.com/).
diff --git a/translations/el/etc/CODE_OF_CONDUCT.md b/translations/el/etc/CODE_OF_CONDUCT.md
index a78c2d27..41ca2843 100644
--- a/translations/el/etc/CODE_OF_CONDUCT.md
+++ b/translations/el/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Κώδικας Δεοντολογίας Ανοιχτού Κώδικα της Microsoft
Αυτό το έργο έχει υιοθετήσει τον [Κώδικα Δεοντολογίας Ανοιχτού Κώδικα της Microsoft](https://opensource.microsoft.com/codeofconduct/).
diff --git a/translations/el/etc/CONTRIBUTING.md b/translations/el/etc/CONTRIBUTING.md
index 6a19a285..291bf1b6 100644
--- a/translations/el/etc/CONTRIBUTING.md
+++ b/translations/el/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Συμμετοχή
Αυτό το έργο καλωσορίζει συνεισφορές και προτάσεις. Οι περισσότερες συνεισφορές απαιτούν να συμφωνήσετε με μια Συμφωνία Άδειας Χρήσης Συνεισφέροντα (CLA), δηλώνοντας ότι έχετε το δικαίωμα και πράγματι παραχωρείτε σε εμάς τα δικαιώματα να χρησιμοποιήσουμε τη συνεισφορά σας. Για λεπτομέρειες, επισκεφθείτε τη διεύθυνση https://cla.microsoft.com.
diff --git a/translations/el/etc/Mindmap.md b/translations/el/etc/Mindmap.md
index dc37866a..3676af97 100644
--- a/translations/el/etc/Mindmap.md
+++ b/translations/el/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# Τεχνητή Νοημοσύνη (AI)
## [Εισαγωγή στην Τεχνητή Νοημοσύνη](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/el/etc/SUPPORT.md b/translations/el/etc/SUPPORT.md
index 5f400db0..802422d4 100644
--- a/translations/el/etc/SUPPORT.md
+++ b/translations/el/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Υποστήριξη
## Πώς να αναφέρετε προβλήματα και να λάβετε βοήθεια
diff --git a/translations/el/etc/TRANSLATIONS.md b/translations/el/etc/TRANSLATIONS.md
index 02217098..96bdc8a4 100644
--- a/translations/el/etc/TRANSLATIONS.md
+++ b/translations/el/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Συμβάλετε μεταφράζοντας μαθήματα
Καλωσορίζουμε μεταφράσεις για τα μαθήματα αυτού του προγράμματος σπουδών!
diff --git a/translations/el/etc/quiz-app/README.md b/translations/el/etc/quiz-app/README.md
index 491aa477..af7f0ed0 100644
--- a/translations/el/etc/quiz-app/README.md
+++ b/translations/el/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Κουίζ
Αυτά τα κουίζ είναι τα κουίζ πριν και μετά τις διαλέξεις για το πρόγραμμα σπουδών AI στο https://aka.ms/ai-beginners
diff --git a/translations/el/examples/README.md b/translations/el/examples/README.md
index 8f96ed56..71dbe17b 100644
--- a/translations/el/examples/README.md
+++ b/translations/el/examples/README.md
@@ -1,12 +1,3 @@
-
# Παραδείγματα AI για Αρχάριους
Καλώς ήρθατε! Αυτός ο κατάλογος περιέχει απλά, αυτόνομα παραδείγματα για να σας βοηθήσει να ξεκινήσετε με την τεχνητή νοημοσύνη και τη μηχανική μάθηση. Κάθε παράδειγμα είναι σχεδιασμένο για αρχάριους, με λεπτομερή σχόλια και βήμα-βήμα εξηγήσεις.
diff --git a/translations/el/lessons/0-course-setup/for-teachers.md b/translations/el/lessons/0-course-setup/for-teachers.md
index ee96b1db..3b61157c 100644
--- a/translations/el/lessons/0-course-setup/for-teachers.md
+++ b/translations/el/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# Για Εκπαιδευτικούς
Θα θέλατε να χρησιμοποιήσετε αυτό το πρόγραμμα σπουδών στην τάξη σας; Μη διστάσετε!
diff --git a/translations/el/lessons/0-course-setup/how-to-run.md b/translations/el/lessons/0-course-setup/how-to-run.md
index b63378c4..e609d49e 100644
--- a/translations/el/lessons/0-course-setup/how-to-run.md
+++ b/translations/el/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Πώς να Εκτελέσετε τον Κώδικα
Αυτή η διδακτέα ύλη περιέχει πολλά εκτελέσιμα παραδείγματα και εργαστήρια που θα θέλατε να τρέξετε. Για να το κάνετε αυτό, χρειάζεστε τη δυνατότητα εκτέλεσης κώδικα Python σε Jupyter Notebooks που παρέχονται ως μέρος αυτής της διδακτέας ύλης. Έχετε αρκετές επιλογές για να τρέξετε τον κώδικα:
diff --git a/translations/el/lessons/0-course-setup/setup.md b/translations/el/lessons/0-course-setup/setup.md
index 3dbdfaa0..46fca93d 100644
--- a/translations/el/lessons/0-course-setup/setup.md
+++ b/translations/el/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Ξεκινώντας με αυτό το Πρόγραμμα Σπουδών
## Είσαι μαθητής;
diff --git a/translations/el/lessons/1-Intro/README.md b/translations/el/lessons/1-Intro/README.md
index cbb72537..5dd7169c 100644
--- a/translations/el/lessons/1-Intro/README.md
+++ b/translations/el/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Εισαγωγή στην Τεχνητή Νοημοσύνη
diff --git a/translations/el/lessons/1-Intro/assignment.md b/translations/el/lessons/1-Intro/assignment.md
index 506458b4..9f22705d 100644
--- a/translations/el/lessons/1-Intro/assignment.md
+++ b/translations/el/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Game Jam
Τα παιχνίδια είναι ένας τομέας που έχει επηρεαστεί σημαντικά από τις εξελίξεις στην Τεχνητή Νοημοσύνη (AI) και τη Μηχανική Μάθηση (ML). Σε αυτήν την εργασία, γράψτε ένα σύντομο κείμενο για ένα παιχνίδι που σας αρέσει και έχει επηρεαστεί από την εξέλιξη της AI. Θα πρέπει να είναι ένα αρκετά παλιό παιχνίδι ώστε να έχει επηρεαστεί από διάφορους τύπους συστημάτων επεξεργασίας υπολογιστών. Ένα καλό παράδειγμα είναι το Σκάκι ή το Go, αλλά εξετάστε επίσης βιντεοπαιχνίδια όπως το Pong ή το Pac-Man. Γράψτε ένα δοκίμιο που να συζητά το παρελθόν, το παρόν και το μέλλον του παιχνιδιού σε σχέση με την AI.
diff --git a/translations/el/lessons/2-Symbolic/README.md b/translations/el/lessons/2-Symbolic/README.md
index cc4fb55e..cfb8a0de 100644
--- a/translations/el/lessons/2-Symbolic/README.md
+++ b/translations/el/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Αναπαράσταση Γνώσης και Ειδικά Συστήματα
-
+
> Σκίτσο από [Tomomi Imura](https://twitter.com/girlie_mac)
@@ -41,7 +32,7 @@ CO_OP_TRANSLATOR_METADATA:
Έτσι, το πρόβλημα της **αναπαράστασης γνώσης** είναι να βρεθεί ένας αποτελεσματικός τρόπος να αναπαρασταθεί η γνώση μέσα σε έναν υπολογιστή με τη μορφή δεδομένων, ώστε να μπορεί να χρησιμοποιηθεί αυτόματα. Αυτό μπορεί να θεωρηθεί ως ένα φάσμα:
-
+
> Εικόνα από [Dmitry Soshnikov](http://soshnikov.com)
@@ -94,7 +85,7 @@ Python | σύνταξη-μπλοκ | εσοχή
Μια από τις πρώτες επιτυχίες της συμβολικής ΤΝ ήταν τα λεγόμενα **ειδικά συστήματα** - υπολογιστικά συστήματα σχεδιασμένα να λειτουργούν ως ειδικοί σε έναν περιορισμένο τομέα προβλημάτων. Βασίζονταν σε μια **βάση γνώσης** που εξήχθη από έναν ή περισσότερους ανθρώπινους ειδικούς, και περιείχαν μια **μηχανή συλλογιστικής** που εκτελούσε συλλογισμούς πάνω σε αυτήν.
- | 
+ | 
-------------------------------------------------------|----------------------------------------------
Απλοποιημένη δομή του ανθρώπινου νευρικού συστήματος | Αρχιτεκτονική συστήματος βασισμένου σε γνώση
@@ -106,7 +97,7 @@ Python | σύνταξη-μπλοκ | εσοχή
Ένα παράδειγμα είναι το παρακάτω ειδικό σύστημα για την αναγνώριση ενός ζώου βάσει των φυσικών του χαρακτηριστικών:
-
+
> Εικόνα από [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/el/lessons/2-Symbolic/assignment.md b/translations/el/lessons/2-Symbolic/assignment.md
index 11bde5e8..15c1a2a9 100644
--- a/translations/el/lessons/2-Symbolic/assignment.md
+++ b/translations/el/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Δημιουργία Οντολογίας
Η δημιουργία μιας βάσης γνώσεων αφορά την κατηγοριοποίηση ενός μοντέλου που αντιπροσωπεύει γεγονότα σχετικά με ένα θέμα. Επιλέξτε ένα θέμα - όπως ένα άτομο, ένα μέρος ή ένα αντικείμενο - και στη συνέχεια δημιουργήστε ένα μοντέλο για αυτό το θέμα. Χρησιμοποιήστε μερικές από τις τεχνικές και στρατηγικές δημιουργίας μοντέλων που περιγράφονται σε αυτό το μάθημα. Ένα παράδειγμα θα μπορούσε να είναι η δημιουργία μιας οντολογίας για ένα σαλόνι με έπιπλα, φώτα και ούτω καθεξής. Πώς διαφέρει το σαλόνι από την κουζίνα; Το μπάνιο; Πώς ξέρετε ότι είναι σαλόνι και όχι τραπεζαρία; Χρησιμοποιήστε το [Protégé](https://protege.stanford.edu/) για να δημιουργήσετε την οντολογία σας.
diff --git a/translations/el/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/el/lessons/3-NeuralNetworks/03-Perceptron/README.md
index dd83a0e7..859a0a95 100644
--- a/translations/el/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Εισαγωγή στα Νευρωνικά Δίκτυα: Perceptron
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ CO_OP_TRANSLATOR_METADATA:
| | |
|--------------|-----------|
-|
| 
|
+|
| 
|
> Εικόνες [από τη Wikipedia](https://en.wikipedia.org/wiki/Perceptron)
@@ -34,7 +25,7 @@ y(x) = f(wTx)
όπου f είναι μια συνάρτηση ενεργοποίησης βήματος
-
+
## Εκπαίδευση του Perceptron
diff --git a/translations/el/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/el/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index 24445e3c..3a4cd271 100644
--- a/translations/el/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Πολυταξική Ταξινόμηση με Perceptron
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index eb58467a..1f8a86cd 100644
--- a/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Εισαγωγή στα Νευρωνικά Δίκτυα. Πολυεπίπεδος Perceptron
Στην προηγούμενη ενότητα, μάθατε για το πιο απλό μοντέλο νευρωνικού δικτύου - τον μονοεπίπεδο perceptron, ένα γραμμικό μοντέλο ταξινόμησης δύο κατηγοριών.
@@ -65,7 +56,7 @@ CO_OP_TRANSLATOR_METADATA:
Σημειώστε ότι το αριστερότερο μέρος όλων αυτών των εκφράσεων είναι το ίδιο, και έτσι μπορούμε να υπολογίσουμε αποτελεσματικά τις παραγώγους ξεκινώντας από τη συνάρτηση απώλειας και πηγαίνοντας "προς τα πίσω" μέσω του γραφήματος υπολογισμού. Έτσι, η μέθοδος εκπαίδευσης ενός πολυεπίπεδου perceptron ονομάζεται **backpropagation**, ή 'backprop'.
-
+
> TODO: αναφορά εικόνας
diff --git a/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 1fdc705f..0e636d24 100644
--- a/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# Ταξινόμηση MNIST με το Δικό μας Πλαίσιο
Εργαστηριακή Άσκηση από το [Πρόγραμμα Σπουδών AI για Αρχάριους](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/el/lessons/3-NeuralNetworks/05-Frameworks/README.md
index 9de09a22..92405a6f 100644
--- a/translations/el/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Πλαίσια Νευρωνικών Δικτύων
Όπως έχουμε ήδη μάθει, για να μπορέσουμε να εκπαιδεύσουμε νευρωνικά δίκτυα αποτελεσματικά, πρέπει να κάνουμε δύο πράγματα:
diff --git a/translations/el/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/el/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index aaa976f0..410c4762 100644
--- a/translations/el/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Ταξινόμηση με PyTorch/TensorFlow
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/3-NeuralNetworks/README.md b/translations/el/lessons/3-NeuralNetworks/README.md
index acfcd0f5..3c00115b 100644
--- a/translations/el/lessons/3-NeuralNetworks/README.md
+++ b/translations/el/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Εισαγωγή στα Νευρωνικά Δίκτυα
diff --git a/translations/el/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/el/lessons/4-ComputerVision/06-IntroCV/README.md
index 52db44ac..f65311b0 100644
--- a/translations/el/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/el/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Εισαγωγή στην Υπολογιστική Όραση
[Η Υπολογιστική Όραση](https://wikipedia.org/wiki/Computer_vision) είναι ένας τομέας που στοχεύει να επιτρέψει στους υπολογιστές να αποκτήσουν υψηλού επιπέδου κατανόηση ψηφιακών εικόνων. Αυτή είναι μια αρκετά ευρεία έννοια, καθώς η *κατανόηση* μπορεί να σημαίνει πολλά διαφορετικά πράγματα, όπως την εύρεση ενός αντικειμένου σε μια εικόνα (**ανίχνευση αντικειμένου**), την κατανόηση του τι συμβαίνει (**ανίχνευση γεγονότων**), την περιγραφή μιας εικόνας με κείμενο ή την ανακατασκευή μιας σκηνής σε 3D. Υπάρχουν επίσης ειδικές εργασίες που σχετίζονται με ανθρώπινες εικόνες: εκτίμηση ηλικίας και συναισθημάτων, ανίχνευση και αναγνώριση προσώπου, και εκτίμηση στάσης σε 3D, για να αναφέρουμε μερικές.
@@ -115,7 +106,7 @@ im = cv2.cvtColor(im,cv2.COLOR_BGR2RGB)
Σε αυτό το εργαστήριο, θα τραβήξετε ένα βίντεο με απλές χειρονομίες, και ο στόχος σας είναι να εξάγετε κινήσεις πάνω/κάτω/αριστερά/δεξιά χρησιμοποιώντας οπτική ροή.
-
+
---
diff --git a/translations/el/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/el/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 66ad9357..486d6cb6 100644
--- a/translations/el/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/el/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Ανίχνευση Κινήσεων με Χρήση Optical Flow
Εργαστηριακή Άσκηση από το [Πρόγραμμα Σπουδών AI for Beginners](https://aka.ms/ai-beginners).
diff --git a/translations/el/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/el/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 395450e6..ca2255c2 100644
--- a/translations/el/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/el/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Γνωστές Αρχιτεκτονικές CNN
### VGG-16
@@ -25,7 +16,7 @@ CO_OP_TRANSLATOR_METADATA:
Το ResNet είναι μια οικογένεια μοντέλων που προτάθηκε από τη Microsoft Research το 2015. Η βασική ιδέα του ResNet είναι η χρήση **residual blocks**:
-
+
> Εικόνα από [αυτό το άρθρο](https://arxiv.org/pdf/1512.03385.pdf)
@@ -37,7 +28,7 @@ CO_OP_TRANSLATOR_METADATA:
Η αρχιτεκτονική Google Inception προχωρά αυτή την ιδέα ένα βήμα παραπέρα, και κατασκευάζει κάθε στρώση του δικτύου ως συνδυασμό πολλών διαφορετικών διαδρομών:
-
+
> Εικόνα από [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)
diff --git a/translations/el/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/el/lessons/4-ComputerVision/07-ConvNets/README.md
index 173527b8..d03cd8da 100644
--- a/translations/el/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/el/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Συνελικτικά Νευρωνικά Δίκτυα
Έχουμε δει προηγουμένως ότι τα νευρωνικά δίκτυα είναι αρκετά καλά στην επεξεργασία εικόνων, και ακόμη και ένα perceptron με μία μόνο στρώση μπορεί να αναγνωρίσει χειρόγραφα ψηφία από το σύνολο δεδομένων MNIST με ικανοποιητική ακρίβεια. Ωστόσο, το σύνολο δεδομένων MNIST είναι πολύ ιδιαίτερο, καθώς όλα τα ψηφία είναι κεντραρισμένα μέσα στην εικόνα, γεγονός που απλοποιεί την εργασία.
@@ -24,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
Για παράδειγμα, αν εφαρμόσουμε φίλτρα κάθετης και οριζόντιας άκρης 3x3 στα ψηφία του MNIST, μπορούμε να πάρουμε επισημάνσεις (π.χ. υψηλές τιμές) όπου υπάρχουν κάθετες και οριζόντιες άκρες στην αρχική μας εικόνα. Έτσι, αυτά τα δύο φίλτρα μπορούν να χρησιμοποιηθούν για να "αναζητήσουν" άκρες. Παρομοίως, μπορούμε να σχεδιάσουμε διαφορετικά φίλτρα για να αναζητήσουμε άλλα μοτίβα χαμηλού επιπέδου:
-
+
> Εικόνα από [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/el/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/el/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index 316bc794..4bd393ad 100644
--- a/translations/el/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/el/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Ταξινόμηση Προσώπων Κατοικίδιων
Εργαστηριακή Άσκηση από το [Πρόγραμμα Σπουδών AI για Αρχάριους](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/el/lessons/4-ComputerVision/08-TransferLearning/README.md
index a13c2204..1d5cc90a 100644
--- a/translations/el/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/el/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Προεκπαιδευμένα Δίκτυα και Μεταφορά Μάθησης
Η εκπαίδευση CNNs μπορεί να απαιτήσει πολύ χρόνο και μεγάλο όγκο δεδομένων. Ωστόσο, μεγάλο μέρος του χρόνου δαπανάται για την εκμάθηση των καλύτερων φίλτρων χαμηλού επιπέδου που μπορεί να χρησιμοποιήσει ένα δίκτυο για να εξάγει μοτίβα από εικόνες. Ένα φυσικό ερώτημα που προκύπτει είναι: μπορούμε να χρησιμοποιήσουμε ένα νευρωνικό δίκτυο που έχει εκπαιδευτεί σε ένα σύνολο δεδομένων και να το προσαρμόσουμε για να ταξινομήσει διαφορετικές εικόνες χωρίς να απαιτείται πλήρης διαδικασία εκπαίδευσης;
diff --git a/translations/el/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/el/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 3a5e7549..3733d235 100644
--- a/translations/el/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/el/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Τεχνικές Εκπαίδευσης Βαθιάς Μάθησης
Καθώς τα νευρωνικά δίκτυα γίνονται πιο βαθιά, η διαδικασία της εκπαίδευσής τους γίνεται όλο και πιο απαιτητική. Ένα σημαντικό πρόβλημα είναι τα λεγόμενα [vanishing gradients](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) ή [exploding gradients](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Αυτό το άρθρο](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) παρέχει μια καλή εισαγωγή σε αυτά τα προβλήματα.
diff --git a/translations/el/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/el/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index ba591ce4..7524b20e 100644
--- a/translations/el/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/el/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Ταξινόμηση των Κατοικίδιων της Οξφόρδης με Χρήση Μεταφοράς Μάθησης
Εργαστηριακή Άσκηση από το [Πρόγραμμα Σπουδών AI για Αρχάριους](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/el/lessons/4-ComputerVision/09-Autoencoders/README.md
index d747ae5d..382ea063 100644
--- a/translations/el/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/el/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Αυτόματοι Κωδικοποιητές
Κατά την εκπαίδευση CNNs, ένα από τα προβλήματα είναι ότι χρειαζόμαστε πολλά δεδομένα με ετικέτες. Στην περίπτωση της ταξινόμησης εικόνων, πρέπει να διαχωρίσουμε τις εικόνες σε διαφορετικές κατηγορίες, κάτι που απαιτεί χειροκίνητη προσπάθεια.
@@ -46,7 +37,7 @@ CO_OP_TRANSLATOR_METADATA:
* Δειγματοληπτούμε ένα διάνυσμα `sample` από την κατανομή N(zmean,exp(zlog\_sigma))
* Ο αποκωδικοποιητής προσπαθεί να αποκωδικοποιήσει την αρχική εικόνα χρησιμοποιώντας το `sample` ως διάνυσμα εισόδου
- 
+ 
> Εικόνα από [αυτό το άρθρο](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) του Isaak Dykeman
@@ -57,13 +48,13 @@ CO_OP_TRANSLATOR_METADATA:
Ένα σημαντικό πλεονέκτημα των VAEs είναι ότι μας επιτρέπουν να δημιουργούμε νέες εικόνες σχετικά εύκολα, επειδή γνωρίζουμε από ποια κατανομή να δειγματοληπτήσουμε λανθάνοντες διανύσματα. Για παράδειγμα, αν εκπαιδεύσουμε έναν VAE με 2D λανθάνον διάνυσμα στο MNIST, μπορούμε στη συνέχεια να μεταβάλλουμε τα συστατικά του λανθάνοντος διανύσματος για να πάρουμε διαφορετικούς αριθμούς:
-
+
> Εικόνα από τον [Dmitry Soshnikov](http://soshnikov.com)
Παρατηρήστε πώς οι εικόνες συγχωνεύονται μεταξύ τους, καθώς αρχίζουμε να παίρνουμε λανθάνοντες διανύσματα από διαφορετικά μέρη του λανθάνοντος χώρου παραμέτρων. Μπορούμε επίσης να οπτικοποιήσουμε αυτόν τον χώρο σε 2D:
-
+
> Εικόνα από τον [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/el/lessons/4-ComputerVision/10-GANs/README.md b/translations/el/lessons/4-ComputerVision/10-GANs/README.md
index 9cce1794..0800d174 100644
--- a/translations/el/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/el/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Γενετικοί Ανταγωνιστικοί Δίκτυα
Στην προηγούμενη ενότητα, μάθαμε για τα **γενετικά μοντέλα**: μοντέλα που μπορούν να δημιουργήσουν νέες εικόνες παρόμοιες με αυτές του συνόλου εκπαίδευσης. Το VAE ήταν ένα καλό παράδειγμα γενετικού μοντέλου.
@@ -17,7 +8,7 @@ CO_OP_TRANSLATOR_METADATA:
Η βασική ιδέα ενός GAN είναι να έχουμε δύο νευρωνικά δίκτυα που θα εκπαιδεύονται το ένα ενάντια στο άλλο:
-
+
> Εικόνα από [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ CO_OP_TRANSLATOR_METADATA:
> ✅ Επειδή το συνελικτικό επίπεδο υλοποιείται ως γραμμικό φίλτρο που διατρέχει την εικόνα, η αποσυνελικτική λειτουργία είναι ουσιαστικά παρόμοια με τη συνελικτική και μπορεί να υλοποιηθεί χρησιμοποιώντας την ίδια λογική επιπέδου.
-
+
> Εικόνα από [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/el/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/el/lessons/4-ComputerVision/11-ObjectDetection/README.md
index fd4264a7..7a7a576e 100644
--- a/translations/el/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/el/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Ανίχνευση Αντικειμένων
Τα μοντέλα ταξινόμησης εικόνων που έχουμε εξετάσει μέχρι τώρα λαμβάνουν μια εικόνα και παράγουν ένα κατηγορηματικό αποτέλεσμα, όπως η κατηγορία 'αριθμός' σε ένα πρόβλημα MNIST. Ωστόσο, σε πολλές περιπτώσεις δεν θέλουμε απλώς να γνωρίζουμε ότι μια εικόνα απεικονίζει αντικείμενα - θέλουμε να μπορούμε να προσδιορίσουμε την ακριβή τους θέση. Αυτό ακριβώς είναι το νόημα της **ανίχνευσης αντικειμένων**.
diff --git a/translations/el/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/el/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index 0023aaca..06c8a3e8 100644
--- a/translations/el/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/el/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Ανίχνευση Κεφαλών με το Hollywood Heads Dataset
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/el/lessons/4-ComputerVision/12-Segmentation/README.md
index 55a64cc9..9da78514 100644
--- a/translations/el/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/el/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Τμηματοποίηση
Έχουμε ήδη μάθει για την Ανίχνευση Αντικειμένων, η οποία μας επιτρέπει να εντοπίζουμε αντικείμενα στην εικόνα προβλέποντας τα *περιγράμματα* τους. Ωστόσο, για ορισμένες εργασίες δεν χρειαζόμαστε μόνο περιγράμματα, αλλά και πιο ακριβή εντοπισμό αντικειμένων. Αυτή η εργασία ονομάζεται **τμηματοποίηση**.
@@ -20,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
Για την τμηματοποίηση παραδειγμάτων, αυτά τα πρόβατα είναι διαφορετικά αντικείμενα, αλλά για τη σημασιολογική τμηματοποίηση όλα τα πρόβατα αντιπροσωπεύονται από μία κατηγορία.
-
+
> Εικόνα από [αυτήν την ανάρτηση στο blog](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@@ -29,7 +20,7 @@ CO_OP_TRANSLATOR_METADATA:
* **Κωδικοποιητής** εξάγει χαρακτηριστικά από την είσοδο της εικόνας.
* **Αποκωδικοποιητής** μετατρέπει αυτά τα χαρακτηριστικά στην **εικόνα μάσκας**, με το ίδιο μέγεθος και αριθμό καναλιών που αντιστοιχούν στον αριθμό των κατηγοριών.
-
+
> Εικόνα από [αυτήν τη δημοσίευση](https://arxiv.org/pdf/2001.05566.pdf)
@@ -43,7 +34,7 @@ CO_OP_TRANSLATOR_METADATA:
> ✅ Αυτή η τεχνική είναι ιδιαίτερα κατάλληλη για αυτόν τον τύπο ιατρικής απεικόνισης, αλλά ποιες άλλες εφαρμογές στον πραγματικό κόσμο μπορείτε να φανταστείτε;
-
+
> Εικόνα από τη Βάση Δεδομένων PH2
diff --git a/translations/el/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/el/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index fb63d5c6..f835bb9c 100644
--- a/translations/el/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/el/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# Τμηματοποίηση Ανθρώπινου Σώματος
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/4-ComputerVision/README.md b/translations/el/lessons/4-ComputerVision/README.md
index cc55aa73..cc59f7f0 100644
--- a/translations/el/lessons/4-ComputerVision/README.md
+++ b/translations/el/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Υπολογιστική Όραση
diff --git a/translations/el/lessons/5-NLP/13-TextRep/README.md b/translations/el/lessons/5-NLP/13-TextRep/README.md
index 7900a3d1..98c6bffe 100644
--- a/translations/el/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/el/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Αναπαράσταση Κειμένου ως Τετραγωνικά Πίνακες
## [Προ-μάθημα κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ CO_OP_TRANSLATOR_METADATA:
Αν θέλουμε να λύσουμε εργασίες Επεξεργασίας Φυσικής Γλώσσας (NLP) με νευρωνικά δίκτυα, χρειαζόμαστε έναν τρόπο να αναπαραστήσουμε το κείμενο ως τετραγωνικούς πίνακες. Οι υπολογιστές ήδη αναπαριστούν τους χαρακτήρες κειμένου ως αριθμούς που αντιστοιχούν σε γραμματοσειρές στην οθόνη σας χρησιμοποιώντας κωδικοποιήσεις όπως ASCII ή UTF-8.
-
+
> [Πηγή εικόνας](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ CO_OP_TRANSLATOR_METADATA:
Όταν λύνουμε εργασίες όπως η κατηγοριοποίηση κειμένου, πρέπει να μπορούμε να αναπαραστήσουμε το κείμενο με έναν σταθερού μεγέθους πίνακα, τον οποίο θα χρησιμοποιήσουμε ως είσοδο στον τελικό πυκνό ταξινομητή. Ένας από τους απλούστερους τρόπους να το κάνουμε αυτό είναι να συνδυάσουμε όλες τις ατομικές αναπαραστάσεις λέξεων, π.χ. προσθέτοντάς τες. Αν προσθέσουμε τις one-hot κωδικοποιήσεις κάθε λέξης, θα καταλήξουμε με έναν πίνακα συχνοτήτων, που δείχνει πόσες φορές εμφανίζεται κάθε λέξη μέσα στο κείμενο. Αυτή η αναπαράσταση του κειμένου ονομάζεται **bag of words** (BoW).
-
+
> Εικόνα από τον συγγραφέα
diff --git a/translations/el/lessons/5-NLP/13-TextRep/assignment.md b/translations/el/lessons/5-NLP/13-TextRep/assignment.md
index 98a115b6..f2d77b67 100644
--- a/translations/el/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/el/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Ανάθεση: Σημειωματάρια
Χρησιμοποιώντας τα σημειωματάρια που σχετίζονται με αυτό το μάθημα (είτε την έκδοση PyTorch είτε την έκδοση TensorFlow), εκτελέστε τα ξανά χρησιμοποιώντας το δικό σας σύνολο δεδομένων, ίσως κάποιο από το Kaggle, με την κατάλληλη αναφορά. Αναδιαμορφώστε το σημειωματάριο για να υπογραμμίσετε τα δικά σας ευρήματα. Δοκιμάστε κάποια καινοτόμα σύνολα δεδομένων που μπορεί να αποδειχθούν ενδιαφέροντα, όπως [αυτό για θεάσεις UFO](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) από το NUFORC.
diff --git a/translations/el/lessons/5-NLP/14-Embeddings/README.md b/translations/el/lessons/5-NLP/14-Embeddings/README.md
index 1e2b8179..16a4e508 100644
--- a/translations/el/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/el/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Ενσωματώσεις
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/el/lessons/5-NLP/14-Embeddings/assignment.md b/translations/el/lessons/5-NLP/14-Embeddings/assignment.md
index 2d986186..cb36d662 100644
--- a/translations/el/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/el/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Ανάθεση: Σημειωματάρια
Χρησιμοποιώντας τα σημειωματάρια που σχετίζονται με αυτό το μάθημα (είτε την έκδοση PyTorch είτε την έκδοση TensorFlow), εκτελέστε τα ξανά χρησιμοποιώντας το δικό σας σύνολο δεδομένων, ίσως κάποιο από το Kaggle, χρησιμοποιώντας το με την κατάλληλη αναφορά. Ξαναγράψτε το σημειωματάριο για να υπογραμμίσετε τα δικά σας ευρήματα. Δοκιμάστε έναν διαφορετικό τύπο συνόλου δεδομένων και τεκμηριώστε τα ευρήματά σας, χρησιμοποιώντας κείμενο όπως [αυτοί οι στίχοι των Beatles](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
diff --git a/translations/el/lessons/5-NLP/15-LanguageModeling/README.md b/translations/el/lessons/5-NLP/15-LanguageModeling/README.md
index 9d0de00c..25663986 100644
--- a/translations/el/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/el/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Μοντελοποίηση Γλώσσας
Οι σημασιολογικές ενσωματώσεις, όπως το Word2Vec και το GloVe, αποτελούν στην πραγματικότητα το πρώτο βήμα προς τη **μοντελοποίηση γλώσσας** - τη δημιουργία μοντέλων που με κάποιο τρόπο *κατανοούν* (ή *αναπαριστούν*) τη φύση της γλώσσας.
diff --git a/translations/el/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/el/lessons/5-NLP/15-LanguageModeling/lab/README.md
index c2c2902b..fafaff58 100644
--- a/translations/el/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/el/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Εκπαίδευση Μοντέλου Skip-Gram
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/5-NLP/16-RNN/README.md b/translations/el/lessons/5-NLP/16-RNN/README.md
index 8b802012..2566cd85 100644
--- a/translations/el/lessons/5-NLP/16-RNN/README.md
+++ b/translations/el/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Επαναλαμβανόμενα Νευρωνικά Δίκτυα
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ CO_OP_TRANSLATOR_METADATA:
Ένα απλό κελί RNN έχει δύο πίνακες βαρών στο εσωτερικό του: ένας μετασχηματίζει ένα σύμβολο εισόδου (ας τον ονομάσουμε W) και ένας άλλος μετασχηματίζει μια κατάσταση εισόδου (H). Σε αυτή την περίπτωση, η έξοδος του δικτύου υπολογίζεται ως σ(W×Xi+H×Si-1+b), όπου σ είναι η συνάρτηση ενεργοποίησης και b είναι μια πρόσθετη προκατάληψη.
-
+
> Εικόνα από τον συγγραφέα
diff --git a/translations/el/lessons/5-NLP/16-RNN/assignment.md b/translations/el/lessons/5-NLP/16-RNN/assignment.md
index 1f4cc339..e6dcfe8d 100644
--- a/translations/el/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/el/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Ανάθεση: Σημειωματάρια
Χρησιμοποιώντας τα σημειωματάρια που σχετίζονται με αυτό το μάθημα (είτε την έκδοση PyTorch είτε την έκδοση TensorFlow), εκτελέστε τα ξανά χρησιμοποιώντας το δικό σας σύνολο δεδομένων, ίσως κάποιο από το Kaggle, χρησιμοποιώντας το με την κατάλληλη αναφορά. Ξαναγράψτε το σημειωματάριο για να υπογραμμίσετε τα δικά σας ευρήματα. Δοκιμάστε έναν διαφορετικό τύπο συνόλου δεδομένων και τεκμηριώστε τα ευρήματά σας, χρησιμοποιώντας κείμενο όπως [αυτό το σύνολο δεδομένων από διαγωνισμό του Kaggle σχετικά με tweets για τον καιρό](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
diff --git a/translations/el/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/el/lessons/5-NLP/17-GenerativeNetworks/README.md
index 0bd39cf7..744c0752 100644
--- a/translations/el/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/el/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Γενετικά Δίκτυα
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ CO_OP_TRANSLATOR_METADATA:
Κατά τη δημιουργία κειμένου (κατά την πρόβλεψη), ξεκινάμε με κάποιο **προτροπή**, η οποία περνά μέσα από τα RNN cells για να δημιουργήσει την ενδιάμεση κατάσταση, και στη συνέχεια από αυτή την κατάσταση ξεκινά η δημιουργία. Παράγουμε έναν χαρακτήρα τη φορά και περνάμε την κατάσταση και τον παραγόμενο χαρακτήρα σε άλλο RNN cell για να δημιουργήσουμε τον επόμενο, μέχρι να δημιουργήσουμε αρκετούς χαρακτήρες.
-
+
> Εικόνα από τον συγγραφέα
diff --git a/translations/el/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/el/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index 62077081..b4fe9db4 100644
--- a/translations/el/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/el/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Δημιουργία Κειμένου σε Επίπεδο Λέξεων με RNNs
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/5-NLP/18-Transformers/README.md b/translations/el/lessons/5-NLP/18-Transformers/README.md
index 99c9af3c..19bf3aa9 100644
--- a/translations/el/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/el/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Μηχανισμοί Προσοχής και Transformers
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ CO_OP_TRANSLATOR_METADATA:
* Εκπαιδεύσιμη ενσωμάτωση, παρόμοια με την ενσωμάτωση token. Αυτή είναι η προσέγγιση που εξετάζουμε εδώ. Εφαρμόζουμε επίπεδα ενσωμάτωσης τόσο στα tokens όσο και στις θέσεις τους, με αποτέλεσμα διανύσματα ενσωμάτωσης των ίδιων διαστάσεων, τα οποία στη συνέχεια προσθέτουμε.
* Σταθερή συνάρτηση κωδικοποίησης θέσης, όπως προτείνεται στο αρχικό άρθρο.
-
+
> Εικόνα από τον συγγραφέα
diff --git a/translations/el/lessons/5-NLP/18-Transformers/assignment.md b/translations/el/lessons/5-NLP/18-Transformers/assignment.md
index 44a343c8..2f4efa38 100644
--- a/translations/el/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/el/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Ανάθεση: Transformers
Πειραματιστείτε με τους Transformers στο HuggingFace! Δοκιμάστε κάποια από τα σενάρια που παρέχουν για να δουλέψετε με τα διάφορα μοντέλα που είναι διαθέσιμα στον ιστότοπό τους: https://huggingface.co/docs/transformers/run_scripts. Δοκιμάστε ένα από τα σύνολα δεδομένων τους και στη συνέχεια εισάγετε ένα δικό σας από αυτό το πρόγραμμα σπουδών ή από το Kaggle και δείτε αν μπορείτε να δημιουργήσετε ενδιαφέροντα κείμενα. Δημιουργήστε ένα notebook με τα ευρήματά σας.
diff --git a/translations/el/lessons/5-NLP/19-NER/README.md b/translations/el/lessons/5-NLP/19-NER/README.md
index c1e7ab85..cbd2d1d5 100644
--- a/translations/el/lessons/5-NLP/19-NER/README.md
+++ b/translations/el/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Αναγνώριση Ονομαστικών Οντοτήτων
Μέχρι τώρα, έχουμε επικεντρωθεί κυρίως σε μία εργασία NLP - την ταξινόμηση. Ωστόσο, υπάρχουν και άλλες εργασίες NLP που μπορούν να επιτευχθούν με νευρωνικά δίκτυα. Μία από αυτές τις εργασίες είναι η **[Αναγνώριση Ονομαστικών Οντοτήτων](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), η οποία ασχολείται με την αναγνώριση συγκεκριμένων οντοτήτων μέσα σε κείμενο, όπως τοποθεσίες, ονόματα προσώπων, χρονικά διαστήματα, χημικές φόρμουλες και άλλα.
@@ -17,7 +8,7 @@ CO_OP_TRANSLATOR_METADATA:
Ας υποθέσουμε ότι θέλετε να αναπτύξετε ένα chatbot φυσικής γλώσσας, παρόμοιο με το Amazon Alexa ή το Google Assistant. Ο τρόπος που λειτουργούν τα έξυπνα chatbots είναι να *κατανοούν* τι θέλει ο χρήστης, κάνοντας ταξινόμηση κειμένου στη φράση εισόδου. Το αποτέλεσμα αυτής της ταξινόμησης είναι η λεγόμενη **πρόθεση**, η οποία καθορίζει τι πρέπει να κάνει το chatbot.
-
+
> Εικόνα από τον συγγραφέα
diff --git a/translations/el/lessons/5-NLP/19-NER/lab/README.md b/translations/el/lessons/5-NLP/19-NER/lab/README.md
index 8c60bf4a..75d478e9 100644
--- a/translations/el/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/el/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
Εργαστηριακή Άσκηση από το [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/el/lessons/5-NLP/20-LangModels/README.md b/translations/el/lessons/5-NLP/20-LangModels/README.md
index 78dc4934..32166747 100644
--- a/translations/el/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/el/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Προεκπαιδευμένα Μεγάλα Γλωσσικά Μοντέλα
Σε όλες τις προηγούμενες εργασίες μας, εκπαιδεύαμε ένα νευρωνικό δίκτυο για να εκτελέσει μια συγκεκριμένη εργασία χρησιμοποιώντας ένα σύνολο δεδομένων με ετικέτες. Με τα μεγάλα μοντέλα μετασχηματιστών, όπως το BERT, χρησιμοποιούμε τη μοντελοποίηση γλώσσας με αυτοεπιβλεπόμενο τρόπο για να δημιουργήσουμε ένα γλωσσικό μοντέλο, το οποίο στη συνέχεια εξειδικεύεται για συγκεκριμένες εργασίες μέσω περαιτέρω εκπαίδευσης σε δεδομένα συγκεκριμένου τομέα. Ωστόσο, έχει αποδειχθεί ότι τα μεγάλα γλωσσικά μοντέλα μπορούν επίσης να λύσουν πολλές εργασίες χωρίς ΚΑΜΙΑ εκπαίδευση συγκεκριμένου τομέα. Μια οικογένεια μοντέλων που μπορεί να το κάνει αυτό ονομάζεται **GPT**: Generative Pre-Trained Transformer.
diff --git a/translations/el/lessons/5-NLP/README.md b/translations/el/lessons/5-NLP/README.md
index 60c3cbdb..faea1243 100644
--- a/translations/el/lessons/5-NLP/README.md
+++ b/translations/el/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Επεξεργασία Φυσικής Γλώσσας
diff --git a/translations/el/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/el/lessons/6-Other/21-GeneticAlgorithms/README.md
index 393e161c..cf7fa90f 100644
--- a/translations/el/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/el/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Γενετικοί Αλγόριθμοι
## [Προ-διάλεξης κουίζ](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/el/lessons/6-Other/22-DeepRL/README.md b/translations/el/lessons/6-Other/22-DeepRL/README.md
index 0f189dbd..ec456ada 100644
--- a/translations/el/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/el/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Βαθιά Ενισχυτική Μάθηση
Η ενισχυτική μάθηση (Reinforcement Learning - RL) θεωρείται ένα από τα βασικά παραδείγματα μηχανικής μάθησης, δίπλα στη supervised learning και την unsupervised learning. Ενώ στη supervised learning βασιζόμαστε σε ένα σύνολο δεδομένων με γνωστά αποτελέσματα, η RL βασίζεται στη **μάθηση μέσω πράξης**. Για παράδειγμα, όταν βλέπουμε για πρώτη φορά ένα παιχνίδι στον υπολογιστή, ξεκινάμε να παίζουμε, ακόμα και αν δεν γνωρίζουμε τους κανόνες, και σύντομα βελτιώνουμε τις ικανότητές μας απλώς μέσω της διαδικασίας του παιχνιδιού και της προσαρμογής της συμπεριφοράς μας.
@@ -34,7 +25,7 @@ CO_OP_TRANSLATOR_METADATA:
Μια απλοποιημένη έκδοση της ισορροπίας είναι γνωστή ως πρόβλημα **CartPole**. Στον κόσμο του CartPole, έχουμε έναν οριζόντιο ολισθητήρα που μπορεί να κινηθεί αριστερά ή δεξιά, και ο στόχος είναι να ισορροπήσουμε ένα κάθετο κοντάρι πάνω στον ολισθητήρα καθώς αυτός κινείται.
-
+
Για να δημιουργήσουμε και να χρησιμοποιήσουμε αυτό το περιβάλλον, χρειαζόμαστε μερικές γραμμές κώδικα Python:
diff --git a/translations/el/lessons/6-Other/22-DeepRL/lab/README.md b/translations/el/lessons/6-Other/22-DeepRL/lab/README.md
index 170da566..283a56a7 100644
--- a/translations/el/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/el/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## Το Περιβάλλον
Το περιβάλλον Mountain Car αποτελείται από ένα αυτοκίνητο παγιδευμένο μέσα σε μια κοιλάδα. Ο στόχος σας είναι να πηδήξετε έξω από την κοιλάδα και να φτάσετε στη σημαία. Οι ενέργειες που μπορείτε να εκτελέσετε είναι να επιταχύνετε προς τα αριστερά, προς τα δεξιά ή να μην κάνετε τίποτα. Μπορείτε να παρατηρήσετε τη θέση του αυτοκινήτου κατά μήκος του άξονα x, καθώς και την ταχύτητά του.
diff --git a/translations/el/lessons/6-Other/23-MultiagentSystems/README.md b/translations/el/lessons/6-Other/23-MultiagentSystems/README.md
index dd341817..2b5b353b 100644
--- a/translations/el/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/el/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Πολυπρακτορικά Συστήματα
Ένας από τους πιθανούς τρόπους επίτευξης νοημοσύνης είναι η λεγόμενη **αναδυόμενη** (ή **συνεργιστική**) προσέγγιση, η οποία βασίζεται στο γεγονός ότι η συνδυασμένη συμπεριφορά πολλών σχετικά απλών πρακτόρων μπορεί να οδηγήσει σε πιο σύνθετη (ή ευφυή) συμπεριφορά του συστήματος συνολικά. Θεωρητικά, αυτό βασίζεται στις αρχές της [Συλλογικής Νοημοσύνης](https://en.wikipedia.org/wiki/Collective_intelligence), του [Αναδυτισμού](https://en.wikipedia.org/wiki/Global_brain) και της [Εξελικτικής Κυβερνητικής](https://en.wikipedia.org/wiki/Global_brain), που υποστηρίζουν ότι τα συστήματα ανώτερου επιπέδου αποκτούν κάποια προστιθέμενη αξία όταν συνδυάζονται σωστά από συστήματα κατώτερου επιπέδου (η λεγόμενη *αρχή της μετάβασης μετασυστήματος*).
@@ -60,7 +51,7 @@ ask turtles [
Ένα εξαιρετικό χαρακτηριστικό του NetLogo είναι ότι περιέχει μια βιβλιοθήκη έτοιμων μοντέλων που μπορείτε να δοκιμάσετε. Μεταβείτε στο **File → Models Library**, και θα βρείτε πολλές κατηγορίες μοντέλων για να επιλέξετε.
-
+
> Στιγμιότυπο οθόνης της βιβλιοθήκης μοντέλων από τον Dmitry Soshnikov
diff --git a/translations/el/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/el/lessons/6-Other/23-MultiagentSystems/assignment.md
index 391c6b74..c4be8f84 100644
--- a/translations/el/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/el/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# Εργασία NetLogo
Πάρτε ένα από τα μοντέλα στη βιβλιοθήκη του NetLogo και χρησιμοποιήστε το για να προσομοιώσετε μια πραγματική κατάσταση όσο το δυνατόν πιο πιστά. Ένα καλό παράδειγμα θα ήταν να τροποποιήσετε το μοντέλο Virus στον φάκελο Alternative Visualizations για να δείξετε πώς μπορεί να χρησιμοποιηθεί για να μοντελοποιήσει τη διάδοση του COVID-19. Μπορείτε να δημιουργήσετε ένα μοντέλο που να μιμείται τη διάδοση ενός ιού στην πραγματική ζωή;
diff --git a/translations/el/lessons/7-Ethics/README.md b/translations/el/lessons/7-Ethics/README.md
index 86b846bd..bfcd7e14 100644
--- a/translations/el/lessons/7-Ethics/README.md
+++ b/translations/el/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Ηθική και Υπεύθυνη Τεχνητή Νοημοσύνη
Έχετε σχεδόν ολοκληρώσει αυτό το μάθημα και ελπίζω ότι μέχρι τώρα βλέπετε ξεκάθαρα πως η Τεχνητή Νοημοσύνη (AI) βασίζεται σε έναν αριθμό από επίσημες μαθηματικές μεθόδους που μας επιτρέπουν να βρίσκουμε σχέσεις στα δεδομένα και να εκπαιδεύουμε μοντέλα ώστε να αναπαράγουν ορισμένες πτυχές της ανθρώπινης συμπεριφοράς. Σε αυτό το σημείο της ιστορίας, θεωρούμε την AI ως ένα πολύ ισχυρό εργαλείο για την εξαγωγή προτύπων από δεδομένα και την εφαρμογή αυτών των προτύπων για την επίλυση νέων προβλημάτων.
diff --git a/translations/el/lessons/README.md b/translations/el/lessons/README.md
index 6494fa10..754701bc 100644
--- a/translations/el/lessons/README.md
+++ b/translations/el/lessons/README.md
@@ -1,12 +1,3 @@
-
# Επισκόπηση
diff --git a/translations/el/lessons/X-Extras/X1-MultiModal/README.md b/translations/el/lessons/X-Extras/X1-MultiModal/README.md
index 3b3fd2d4..c941f333 100644
--- a/translations/el/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/el/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Δίκτυα Πολλαπλών Τρόπων
Μετά την επιτυχία των μοντέλων transformer για την επίλυση εργασιών NLP, οι ίδιες ή παρόμοιες αρχιτεκτονικές έχουν εφαρμοστεί σε εργασίες υπολογιστικής όρασης. Υπάρχει αυξανόμενο ενδιαφέρον για την ανάπτυξη μοντέλων που θα *συνδυάζουν* δυνατότητες όρασης και φυσικής γλώσσας. Μία από αυτές τις προσπάθειες έγινε από την OpenAI και ονομάζεται CLIP και DALL.E.
diff --git a/translations/el/lessons/sketchnotes/LICENSE.md b/translations/el/lessons/sketchnotes/LICENSE.md
index e1e6aec9..da8c2d5f 100644
--- a/translations/el/lessons/sketchnotes/LICENSE.md
+++ b/translations/el/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Δημιουργική Αναφορά-Παρόμοια Άδεια 4.0 Διεθνής
=======================================================================
diff --git a/translations/el/lessons/sketchnotes/README.md b/translations/el/lessons/sketchnotes/README.md
index a7c8c2f5..1417e378 100644
--- a/translations/el/lessons/sketchnotes/README.md
+++ b/translations/el/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Όλες οι σημειώσεις σκίτσων του προγράμματος σπουδών μπορούν να ληφθούν εδώ.
🎨 Δημιουργήθηκε από: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/el/troubleshoot.md b/translations/el/troubleshoot.md
index 0379b9a1..36a34ea4 100644
--- a/translations/el/troubleshoot.md
+++ b/translations/el/troubleshoot.md
@@ -1,12 +1,3 @@
-
# Οδηγός Αντιμετώπισης Προβλημάτων για το AI-For-Beginners
Αυτός ο οδηγός σας βοηθά να επιλύσετε κοινά προβλήματα που προκύπτουν κατά τη χρήση ή τη συνεισφορά στο αποθετήριο [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners). Κάθε πρόβλημα περιλαμβάνει υπόβαθρο, συμπτώματα, εξηγήσεις και βήμα-βήμα λύσεις.
diff --git a/translations/pl/.co-op-translator.json b/translations/pl/.co-op-translator.json
new file mode 100644
index 00000000..bce3dda6
--- /dev/null
+++ b/translations/pl/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:20:42+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "pl"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T01:49:37+00:00",
+ "source_file": "README.md",
+ "language_code": "pl"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-24T10:10:02+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "pl"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-24T10:50:22+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "pl"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-24T10:50:54+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "pl"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-24T10:51:24+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "pl"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-24T10:50:10+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "pl"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-24T10:50:36+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "pl"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-24T10:51:59+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "pl"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:30:24+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "pl"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-24T10:49:27+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "pl"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-15T14:27:45+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "pl"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:42:56+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "pl"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:23:13+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "pl"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:24:21+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-15T14:28:10+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "pl"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-24T10:48:31+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T13:57:13+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-31T12:25:22+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T13:56:46+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-24T10:41:00+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T13:57:32+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-24T10:42:13+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:47:45+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T13:52:01+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-24T10:32:41+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T13:51:18+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T13:51:01+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:54:42+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T13:51:34+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-24T10:34:20+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-24T10:35:06+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T13:53:01+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T13:53:49+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T13:52:29+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-24T10:29:17+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T13:53:29+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-24T10:26:51+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-24T10:25:01+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T14:00:39+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-24T10:16:07+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T14:00:17+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-24T10:14:12+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T13:58:26+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-24T10:16:57+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T13:59:51+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-24T10:13:11+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T13:58:05+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-24T10:15:07+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T13:58:43+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-24T10:19:59+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T13:59:35+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-24T10:22:59+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T13:59:10+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "pl"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-24T10:11:53+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "pl"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T13:49:18+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "pl"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T13:50:30+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "pl"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-24T10:38:32+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "pl"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T13:49:40+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "pl"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-24T10:37:21+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "pl"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-24T10:10:42+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "pl"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-24T10:10:19+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "pl"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-24T10:39:09+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "pl"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-24T10:45:40+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "pl"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-24T10:43:17+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "pl"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:43:07+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "pl"
+ }
+}
\ No newline at end of file
diff --git a/translations/pl/AGENTS.md b/translations/pl/AGENTS.md
index 61bcdb4d..0dbf179b 100644
--- a/translations/pl/AGENTS.md
+++ b/translations/pl/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Przegląd projektu
diff --git a/translations/pl/README.md b/translations/pl/README.md
index f6bd7c34..99f1afaa 100644
--- a/translations/pl/README.md
+++ b/translations/pl/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -23,32 +14,32 @@ CO_OP_TRANSLATOR_METADATA:
# Sztuczna inteligencja dla początkujących - program nauczania
-||
+||
|:---:|
-| AI For Beginners - _Sketchnote autorstwa [@girlie_mac](https://twitter.com/girlie_mac)_ |
+| AI dla początkujących - _Sketchnote autorstwa [@girlie_mac](https://twitter.com/girlie_mac)_ |
-Odkryj świat **Sztucznej Inteligencji** (AI) z naszym 12-tygodniowym, 24-lekcyjnym programem nauczania! Zawiera on praktyczne lekcje, quizy oraz laboratoria. Program jest przyjazny dla początkujących i obejmuje narzędzia takie jak TensorFlow i PyTorch, a także etykę w AI
+Odkryj świat **Sztucznej Inteligencji** (AI) z naszym 12-tygodniowym, 24-lekcyjnym programem nauczania! Zawiera praktyczne lekcje, quizy i laboratoria. Program jest przyjazny dla początkujących i obejmuje narzędzia takie jak TensorFlow i PyTorch, a także etykę w AI.
### 🌐 Wsparcie wielojęzyczne
-#### Wspierane poprzez akcję GitHub (automatyczna i zawsze aktualna)
+#### Obsługiwane za pomocą GitHub Action (automatyczne i zawsze aktualne)
-[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](./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)
+[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-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](./README.md) | [Portuguese (Brazil)](../pt-BR/README.md) | [Portuguese (Portugal)](../pt-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)
-> **Wolisz klonować lokalnie?**
+> **Wolisz sklonować lokalnie?**
-> To repozytorium zawiera ponad 50 tłumaczeń językowych, co znacznie zwiększa rozmiar pobieranego pliku. Aby sklonować bez tłumaczeń, użyj sparse checkout:
+> To repozytorium zawiera ponad 50 tłumaczeń językowych, co znacznie zwiększa rozmiar pobierania. Aby sklonować bez tłumaczeń, użyj sparsowanego checkoutu:
> ```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'
> ```
-> To zapewni ci wszystko, co potrzebne do ukończenia kursu z dużo szybszym pobieraniem.
+> To zapewnia wszystko, czego potrzebujesz, aby ukończyć kurs, przy znacznie szybszym pobieraniu.
-**Jeśli chcesz, aby obsługiwane były dodatkowe języki tłumaczeń są one wymienione [tutaj](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
+**Jeśli chcesz, aby obsługiwane były dodatkowe języki tłumaczeń, są one wymienione [tutaj](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Dołącz do społeczności
[](https://discord.gg/nTYy5BXMWG)
@@ -59,175 +50,176 @@ Odkryj świat **Sztucznej Inteligencji** (AI) z naszym 12-tygodniowym, 24-lekcyj
W tym programie nauczania nauczysz się:
-* Różnych podejść do sztucznej inteligencji, w tym "dobrej starej" symbolicznej metody z **Reprezentacją Wiedzy** i wnioskowaniem ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
-* **Sieci neuronowych** i **uczenia głębokiego**, które są u podstaw nowoczesnej AI. Pokażemy koncepcje stojące za tymi ważnymi tematami używając kodu w dwóch najpopularniejszych frameworkach - [TensorFlow](http://Tensorflow.org) i [PyTorch](http://pytorch.org).
-* **Architektury neuronowe** do pracy z obrazami i tekstem. Omówimy najnowsze modele, choć mogą one nie obejmować najnowszych osiągnięć.
-* Mniej popularne podejścia AI, takie jak **algorytmy genetyczne** i **systemy wieloagentowe**.
+* Różnych podejść do Sztucznej Inteligencji, w tym "dawnego dobrego" podejścia symbolicznego z **Reprezentacją Wiedzy** i wnioskowaniem ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* **Sieci neuronowych** i **Uczenia głębokiego**, które są sednem nowoczesnej AI. Pokażemy koncepcje stojące za tymi ważnymi tematami, używając kodu w dwóch najpopularniejszych frameworkach - [TensorFlow](http://Tensorflow.org) oraz [PyTorch](http://pytorch.org).
+* **Neuronalnych architektur** do pracy z obrazami i tekstem. Omówimy najnowsze modele, choć mogą być nieco mniej aktualne względem stanu wiedzy.
+* Mniej popularne podejścia do AI, takie jak **algorytmy genetyczne** i **systemy wieloagentowe**.
-Czego nie obejmuje ten program nauczania:
+Czego nie omówimy w tym programie:
-> [Znajdź wszystkie dodatkowe zasoby do tego kursu w naszej kolekcji Microsoft Learn](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Znajdź wszystkie dodatkowe zasoby dla tego kursu w naszej kolekcji Microsoft Learn](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* Przypadki biznesowe zastosowania **AI w biznesie**. Rozważ podjęcie ścieżki nauki [Wprowadzenie do AI dla użytkowników biznesowych](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) na Microsoft Learn lub [Szkołę AI dla Biznesu](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), opracowaną we współpracy z [INSEAD](https://www.insead.edu/).
-* **Klasyczne uczenie maszynowe**, które jest dobrze opisane w naszym programie [Uczenie maszynowe dla początkujących](http://github.com/Microsoft/ML-for-Beginners).
-* Praktyczne zastosowania AI zbudowane przy użyciu **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. W tym celu zalecamy rozpoczęcie od modułów Microsoft Learn dotyczących [wizji komputerowej](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [przetwarzania języka naturalnego](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generatywnej AI z Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** i innych.
-* Specyficzne ML **frameworki chmurowe**, takie jak [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) lub [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Rozważ użycie ścieżek nauki [Budowanie i obsługa rozwiązań uczenia maszynowego z Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) oraz [Budowanie i obsługa rozwiązań uczenia maszynowego z Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
-* **Konwersacyjne AI** i **chatboty**. Istnieje osobna ścieżka nauki [Tworzenie rozwiązań konwersacyjnej AI](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), a także możesz odnieść się do [tego wpisu na blogu](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) po więcej szczegółów.
-* **Głęboka matematyka** stojąca za uczeniem głębokim. W tym celu polecamy [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) autorstwa Iana Goodfellowa, Yoshua Bengio i Aarona Courville, która jest również dostępna online na [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
+* Przypadki biznesowe wykorzystania **AI w biznesie**. Rozważ rozpoczęcie ścieżki nauczania [Wprowadzenie do AI dla użytkowników biznesowych](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) na Microsoft Learn lub [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), opracowaną we współpracy z [INSEAD](https://www.insead.edu/).
+* **Klasyczne uczenie maszynowe**, które jest dobrze opisane w naszym [Programie nauczania dla początkujących z uczenia maszynowego](http://github.com/Microsoft/ML-for-Beginners).
+* Praktycznych zastosowań AI zbudowanych przy użyciu **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. W tym celu zalecamy rozpoczęcie od modułów Microsoft Learn dotyczących [wizji komputerowej](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [przetwarzania języka naturalnego](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generative AI z Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** i innych.
+* Specyficznych frameworków ML w chmurze, takich jak [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) lub [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Rozważ użycie ścieżek edukacyjnych [Buduj i obsługuj rozwiązania uczenia maszynowego z Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) oraz [Buduj i obsługuj rozwiązania uczenia maszynowego z Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
+* **Konwersacyjne AI** i **Chatboty**. Istnieje osobna ścieżka nauczania [Twórz rozwiązania konwersacyjne AI](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), a także możesz odnieść się do [tego wpisu na blogu](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) dla szczegółów.
+* **Głębokiej matematyki** stojącej za uczeniem głębokim. W tym celu polecamy książkę [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) autorstwa Iana Goodfellowa, Yoshua Bengio oraz Aarona Courville, dostępną również online pod adresem [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
-Dla łagodnego wprowadzenia do tematów _AI w chmurze_ możesz rozważyć odbycie ścieżki nauki [Rozpocznij przygodę ze sztuczną inteligencją w Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
+Dla łagodniejszego wprowadzenia do tematów _AI w chmurze_ możesz rozważyć ścieżkę nauczania [Pierwsze kroki ze sztuczną inteligencją na Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
# Zawartość
| | Link do lekcji | PyTorch/Keras/TensorFlow | Laboratorium |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
-| 0 | [Konfiguracja kursu](./lessons/0-course-setup/setup.md) | [Skonfiguruj swoje środowisko programistyczne](./lessons/0-course-setup/how-to-run.md) | |
+| 0 | [Konfiguracja kursu](./lessons/0-course-setup/setup.md) | [Konfiguracja środowiska developerskiego](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Wprowadzenie do AI**](./lessons/1-Intro/README.md) | | |
| 01 | [Wprowadzenie i historia AI](./lessons/1-Intro/README.md) | - | - |
| II | **Symboliczne AI** |
-| 02 | [Reprezentacja wiedzy i systemy eksperckie](./lessons/2-Symbolic/README.md) | [Systemy eksperckie](./lessons/2-Symbolic/Animals.ipynb) / [Ontologia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Graf pojęć](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
+| 02 | [Reprezentacja wiedzy i systemy ekspertowe](./lessons/2-Symbolic/README.md) | [Systemy ekspertowe](./lessons/2-Symbolic/Animals.ipynb) / [Ontologia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Graf pojęć](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Wprowadzenie do sieci neuronowych**](./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 | [Wielowarstwowy perceptron i tworzenie własnego frameworka](./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 | [Wprowadzenie do frameworków (PyTorch/TensorFlow) i przeuczenie](./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) |
+| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notatnik](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Laboratorium](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
+| 04 | [Wielowarstwowy perceptron i tworzenie własnego frameworku](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notatnik](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Laboratorium](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 05 | [Wprowadzenie do frameworków (PyTorch/TensorFlow) i nadmierne dopasowanie](./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) | [Laboratorium](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
| IV | [**Wizja komputerowa**](./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)| [Poznaj wizję komputerową na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
-| 06 | [Wprowadzenie do wizji komputerowej. 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 | [Splotowe sieci neuronowe](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Architektury CNN](./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 | [Sieci wstępnie wytrenowane i uczenie transferowe](./lessons/4-ComputerVision/08-TransferLearning/README.md) oraz [Sztuczki treningowe](./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) |
+| 06 | [Wprowadzenie do wizji komputerowej. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notatnik](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Laboratorium](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
+| 07 | [Splotowe sieci neuronowe](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Architektury CNN](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Laboratorium](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
+| 08 | [Sieci wstępnie wytrenowane i transfer learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) i [Sztuczki treningowe](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Laboratorium](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
| 09 | [Autoenkodery i VAE](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
-| 10 | [Generatywne sieci przeciwstawne i transfer stylu](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
-| 11 | [Detekcja obiektów](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
+| 10 | [Generatywne sieci przeciwstawne i transfer stylu artystycznego](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
+| 11 | [Detekcja obiektów](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Laboratorium](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
| 12 | [Segmentacja semantyczna. 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 | [**Przetwarzanie języka naturalnego**](./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) | [Poznaj przetwarzanie języka naturalnego na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Reprezentacja tekstu. 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 | [Semantyczne osadzenia słów. Word2Vec i 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 | [Modelowanie języka. Trenowanie własnych osadzeń](./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) |
+| 15 | [Modelowanie języka. Trenowanie własnych osadzeń](./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) | [Laboratorium](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 16 | [Rekurencyjne sieci neuronowe](./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 | [Generatywne sieci rekurencyjne](./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) |
+| 17 | [Generatywne sieci rekurencyjne](./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) | [Laboratorium](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
| 18 | [Transformery. 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 | [Rozpoznawanie nazwanych jednostek](./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 | [Duże modele językowe, programowanie promptów i zadania few-shot](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| 19 | [Rozpoznawanie nazwanych jednostek](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Laboratorium](./lessons/5-NLP/19-NER/lab/README.md) |
+| 20 | [Duże modele językowe, programowanie podpowiedzi i zadania few-shot](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Inne techniki AI** || |
-| 21 | [Algorytmy genetyczne](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
-| 22 | [Głębokie uczenie ze wzmocnieniem](./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) |
+| 21 | [Algorytmy genetyczne](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notatnik](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
+| 22 | [Głębokie uczenie ze wzmocnieniem](./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) | [Laboratorium](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Systemy wieloagentowe](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **Etyka AI** | | |
-| 24 | [Etyka AI i odpowiedzialna sztuczna inteligencja](./lessons/7-Ethics/README.md) | [Microsoft Learn: Zasady odpowiedzialnej AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
+| 24 | [Etyka AI i odpowiedzialne AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Zasady odpowiedzialnej AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
| IX | **Dodatki** | | |
-| 25 | [Sieci multimodalne, CLIP i VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
+| 25 | [Sieci multimodalne, CLIP i VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notatnik](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Każda lekcja zawiera
* Materiały do wstępnej lektury
-* Wykonywalne notatniki Jupyter, często specyficzne dla frameworka (**PyTorch** lub **TensorFlow**). Wykonywalny notatnik zawiera również dużo materiału teoretycznego, więc aby zrozumieć temat, należy przejrzeć przynajmniej jedną wersję notatnika (PyTorch lub TensorFlow).
-* **Laboratoria** dostępne dla niektórych tematów, które dają możliwość spróbowania zastosowania poznanego materiału do konkretnego problemu.
-* Niektóre sekcje zawierają linki do modułów [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum), które obejmują powiązane tematy.
+* Wykonywalne notatniki Jupyter, które często są specyficzne dla frameworku (**PyTorch** lub **TensorFlow**). Wykonywalny notatnik zawiera również dużo materiału teoretycznego, więc aby zrozumieć temat, należy przejść przez przynajmniej jedną wersję notatnika (PyTorch lub TensorFlow).
+* **Laboratoria** dostępne dla niektórych tematów, które dają możliwość zastosowania materiału, którego się nauczyłeś, do konkretnego problemu.
+* Niektóre sekcje zawierają linki do modułów [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) omawiających powiązane tematy.
## Rozpoczęcie pracy
### 🎯 Nowy w AI? Zacznij tutaj!
-Jeśli jesteś całkowicie nowy w AI i chcesz szybko poznać praktyczne przykłady, sprawdź nasze [**Przykłady dla początkujących**](./examples/README.md)! Obejmują one:
+Jeśli jesteś zupełnie nowy w AI i chcesz szybkie, praktyczne przykłady, sprawdź nasze [**Przyjazne dla początkujących przykłady**](./examples/README.md)! Zawierają one:
- 🌟 **Hello AI World** - Twój pierwszy program AI (rozpoznawanie wzorców)
-- 🧠 **Prosta sieć neuronowa** - Budowa sieci neuronowej od podstaw
-- 🖼️ **Klasyfikator obrazów** - Klasyfikacja obrazów z szczegółowymi komentarzami
-- 💬 **Analiza nastroju tekstu** - Analiza tekstu pod kątem pozytywnego/negatywnego wydźwięku
+- 🧠 **Prosta sieć neuronowa** - Zbuduj sieć neuronową od podstaw
-Te przykłady mają na celu pomóc Ci zrozumieć koncepty AI zanim zagłębisz się w pełny program nauczania.
+- 🖼️ **Klasyfikator obrazów** - Klasyfikuj obrazy z szczegółowymi komentarzami
+- 💬 **Analiza sentymentu tekstu** - Analizuj tekst pod kątem pozytywnych/negatywnych emocji
-### 📚 Pełna konfiguracja programu nauczania
+Te przykłady mają pomóc zrozumieć koncepcje AI przed rozpoczęciem pełnego kursu.
-- Stworzyliśmy [lekcję konfiguracji](./lessons/0-course-setup/setup.md), która pomoże Ci w ustawieniu środowiska programistycznego. - Dla nauczycieli przygotowaliśmy także [lekcję konfiguracji programu nauczania](./lessons/0-course-setup/for-teachers.md)!
-- Jak [uruchomić kod w VSCode lub Codespace](./lessons/0-course-setup/how-to-run.md)
+### 📚 Pełna konfiguracja kursu
-Postępuj według tych kroków:
+- Stworzyliśmy [lekcję konfiguracji](./lessons/0-course-setup/setup.md), aby pomóc Ci z uruchomieniem środowiska programistycznego. - Dla nauczycieli przygotowaliśmy także [lekcję konfiguracji programu nauczania](./lessons/0-course-setup/for-teachers.md)!
+- Jak [uruchomić kod w VSCode lub Codespace](./lessons/0-course-setup/how-to-run.md)
-Forkuj repozytorium: Kliknij przycisk "Fork" w prawym górnym rogu tej strony.
+Wykonaj następujące kroki:
-Sklonuj repozytorium: `git clone https://github.com/microsoft/AI-For-Beginners.git`
+Forkuj repozytorium: Kliknij przycisk "Fork" w prawym górnym rogu tej strony.
-Nie zapomnij oznaczyć repozytorium gwiazdką (🌟), żeby łatwiej je potem znaleźć.
+Sklonuj repozytorium: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-## Poznaj innych uczących się
+Nie zapomnij dodać gwiazdki (🌟) temu repozytorium, aby łatwiej je znaleźć później.
-Dołącz do naszego [oficjalnego serwera Discord AI](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum), aby spotkać i nawiązać kontakty z innymi uczestnikami kursu oraz uzyskać wsparcie.
+## Poznaj innych uczących się
-Jeśli masz opinie o produkcie lub pytania podczas tworzenia, odwiedź nasz [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
+Dołącz do naszego [oficjalnego serwera Discord AI](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum), aby poznać i nawiązać kontakty z innymi uczestnikami kursu oraz uzyskać wsparcie.
-## Quizy
+Jeśli masz opinie o produkcie lub pytania podczas tworzenia, odwiedź nasz [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
-> **Informacja o quizach**: Wszystkie quizy znajdują się w folderze Quiz-app w etc\quiz-app lub [online tutaj](https://ff-quizzes.netlify.app/) Są zlinkowane z lekcji; aplikacja quizowa może być uruchomiona lokalnie lub wdrożona na Azure; postępuj według instrukcji w folderze `quiz-app`. Są stopniowo lokalizowane.
+## Quizy
-## Poszukujemy pomocy
+> **Uwaga o quizach**: Wszystkie quizy znajdują się w folderze Quiz-app w etc\quiz-app, lub [Online Tutaj](https://ff-quizzes.netlify.app/) Są one powiązane z lekcjami, aplikację quizową można uruchomić lokalnie lub wdrożyć na Azure; postępuj zgodnie z instrukcjami w folderze `quiz-app`. Są one stopniowo lokalizowane.
-Masz sugestie lub znalazłeś błędy ortograficzne lub w kodzie? Zgłoś problem lub stwórz pull request.
+## Potrzebujemy pomocy
-## Specjalne podziękowania
+Masz sugestie albo znalazłeś błędy pisowni lub w kodzie? Zgłoś problem lub stwórz pull request.
-* **✍️ Główny autor:** [Dmitry Soshnikov](http://soshnikov.com), PhD
-* **🔥 Redaktor:** [Jen Looper](https://twitter.com/jenlooper), PhD
-* **🎨 Ilustrator sketchnotek:** [Tomomi Imura](https://twitter.com/girlie_mac)
-* **✅ Twórca quizów:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
-* **🙏 Główni współtwórcy:** [Evgenii Pishchik](https://github.com/Pe4enIks)
+## Specjalne podziękowania
-## Inne programy nauczania
+* **✍️ Główny autor:** [Dmitry Soshnikov](http://soshnikov.com), PhD
+* **🔥 Redaktor:** [Jen Looper](https://twitter.com/jenlooper), PhD
+* **🎨 Ilustrator sketchnotów:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **✅ Twórca quizów:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
+* **🙏 Główni współtwórcy:** [Evgenii Pishchik](https://github.com/Pe4enIks)
-Nasz zespół tworzy inne programy! Sprawdź:
+## Inne programy nauczania
-
-### LangChain
-[](https://aka.ms/langchain4j-for-beginners)
-[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
+Nasz zespół tworzy także inne programy nauczania! Sprawdź:
----
+
+### LangChain
+[](https://aka.ms/langchain4j-for-beginners)
+[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
-### Azure / Edge / MCP / Agenci
-[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
+---
----
+### Azure / Edge / MCP / Agenci
+[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
-### Seria Generatywnego AI
-[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
-[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
-[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
+---
+
+### Seria Generatywnej AI
+[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
+[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
+[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
----
+---
+
+### Podstawowa nauka
+[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
-### Podstawowe nauczanie
-[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
+---
+
+### Seria Copilot
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+
----
+## Uzyskaj pomoc
-### Seria Copilot
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
-
+Jeśli utkniesz lub masz pytania dotyczące tworzenia aplikacji AI. Dołącz do innych uczących się i doświadczonych programistów w dyskusjach o MCP. To wspierająca społeczność, gdzie pytania są mile widziane, a wiedza jest swobodnie dzielona.
-## Uzyskaj pomoc
+[](https://discord.gg/nTYy5BXMWG)
-Jeśli utkniesz lub masz pytania dotyczące tworzenia aplikacji AI, dołącz do innych uczących się i doświadczonych programistów w dyskusjach o MCP. To wspierająca społeczność, gdzie pytania są mile widziane, a wiedza jest swobodnie dzielona.
-
-[](https://discord.gg/nTYy5BXMWG)
-
-Jeśli masz opinie o produkcie lub błędy podczas tworzenia, odwiedź:
+Jeśli masz opinie o produkcie lub błędy podczas tworzenia, odwiedź:
[](https://aka.ms/foundry/forum)
---
-**Zastrzeżenie**:
-Niniejszy dokument został przetłumaczony za pomocą usługi tłumaczenia AI [Co-op Translator](https://github.com/Azure/co-op-translator). Mimo że dbamy o dokładność, prosimy mieć na uwadze, że tłumaczenia automatyczne mogą zawierać błędy lub niedokładności. Oryginalny dokument w jego języku źródłowym należy traktować jako źródło autorytatywne. W przypadku istotnych informacji zalecane jest skorzystanie z profesjonalnego tłumaczenia wykonanego przez człowieka. Nie ponosimy odpowiedzialności za jakiekolwiek nieporozumienia lub błędne interpretacje wynikające z korzystania z tego tłumaczenia.
+**Wyłączenie odpowiedzialności**:
+Niniejszy dokument został przetłumaczony za pomocą usługi tłumaczenia AI [Co-op Translator](https://github.com/Azure/co-op-translator). Mimo że dokładamy starań, aby tłumaczenie było jak najbardziej precyzyjne, prosimy pamiętać, że automatyczne tłumaczenia mogą zawierać błędy lub nieścisłości. Oryginalny dokument w języku źródłowym należy traktować jako źródło wiążące. W przypadku istotnych informacji zaleca się skorzystanie z profesjonalnego tłumaczenia wykonanego przez człowieka. Nie ponosimy odpowiedzialności za jakiekolwiek nieporozumienia lub błędne interpretacje wynikające z korzystania z tego tłumaczenia.
\ No newline at end of file
diff --git a/translations/pl/SECURITY.md b/translations/pl/SECURITY.md
index 923bd08f..80aa51cc 100644
--- a/translations/pl/SECURITY.md
+++ b/translations/pl/SECURITY.md
@@ -1,12 +1,3 @@
-
## Bezpieczeństwo
Microsoft traktuje bezpieczeństwo swoich produktów i usług bardzo poważnie, w tym wszystkich repozytoriów kodu źródłowego zarządzanych w ramach naszych organizacji na GitHub, takich jak [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) oraz [nasze organizacje na GitHub](https://opensource.microsoft.com/).
diff --git a/translations/pl/etc/CODE_OF_CONDUCT.md b/translations/pl/etc/CODE_OF_CONDUCT.md
index 3163c0b7..106014b2 100644
--- a/translations/pl/etc/CODE_OF_CONDUCT.md
+++ b/translations/pl/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Kodeks postępowania Microsoft Open Source
Ten projekt przyjął [Kodeks postępowania Microsoft Open Source](https://opensource.microsoft.com/codeofconduct/).
diff --git a/translations/pl/etc/CONTRIBUTING.md b/translations/pl/etc/CONTRIBUTING.md
index 0225f8f6..cd03b5c8 100644
--- a/translations/pl/etc/CONTRIBUTING.md
+++ b/translations/pl/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Współtworzenie
Ten projekt zaprasza do współtworzenia i składania sugestii. Większość wkładów wymaga od Ciebie
diff --git a/translations/pl/etc/Mindmap.md b/translations/pl/etc/Mindmap.md
index 0deda1a1..423eba68 100644
--- a/translations/pl/etc/Mindmap.md
+++ b/translations/pl/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# AI
## [Wprowadzenie do AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/pl/etc/SUPPORT.md b/translations/pl/etc/SUPPORT.md
index a7e9c6ec..0b4ae4d6 100644
--- a/translations/pl/etc/SUPPORT.md
+++ b/translations/pl/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Wsparcie
## Jak zgłaszać problemy i uzyskiwać pomoc
diff --git a/translations/pl/etc/TRANSLATIONS.md b/translations/pl/etc/TRANSLATIONS.md
index f3835142..d28b25a5 100644
--- a/translations/pl/etc/TRANSLATIONS.md
+++ b/translations/pl/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Współtwórz, tłumacząc lekcje
Zapraszamy do tłumaczenia lekcji w tym programie nauczania!
diff --git a/translations/pl/etc/quiz-app/README.md b/translations/pl/etc/quiz-app/README.md
index 576a1492..084feff6 100644
--- a/translations/pl/etc/quiz-app/README.md
+++ b/translations/pl/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Quizy
Te quizy to quizy przed i po wykładach w ramach programu nauczania AI dostępnego na https://aka.ms/ai-beginners
diff --git a/translations/pl/examples/README.md b/translations/pl/examples/README.md
index 7e026905..3b14d3f2 100644
--- a/translations/pl/examples/README.md
+++ b/translations/pl/examples/README.md
@@ -1,12 +1,3 @@
-
# Przykłady AI dla Początkujących
Witaj! Ten katalog zawiera proste, samodzielne przykłady, które pomogą Ci rozpocząć przygodę z AI i uczeniem maszynowym. Każdy przykład został zaprojektowany z myślą o początkujących, z dokładnymi komentarzami i wyjaśnieniami krok po kroku.
diff --git a/translations/pl/lessons/0-course-setup/for-teachers.md b/translations/pl/lessons/0-course-setup/for-teachers.md
index 550f893e..a59ebd93 100644
--- a/translations/pl/lessons/0-course-setup/for-teachers.md
+++ b/translations/pl/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# Dla Edukatorów
Chcesz wykorzystać ten program nauczania w swojej klasie? Śmiało, zapraszamy!
diff --git a/translations/pl/lessons/0-course-setup/how-to-run.md b/translations/pl/lessons/0-course-setup/how-to-run.md
index 4ba5effd..90b49689 100644
--- a/translations/pl/lessons/0-course-setup/how-to-run.md
+++ b/translations/pl/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Jak Uruchomić Kod
Ten program nauczania zawiera wiele wykonalnych przykładów i laboratoriów, które będziesz chciał uruchomić. Aby to zrobić, musisz mieć możliwość wykonywania kodu Python w Jupyter Notebooks dostarczonych w ramach tego programu nauczania. Masz kilka opcji uruchamiania kodu:
diff --git a/translations/pl/lessons/0-course-setup/setup.md b/translations/pl/lessons/0-course-setup/setup.md
index 150c82e3..545ca99e 100644
--- a/translations/pl/lessons/0-course-setup/setup.md
+++ b/translations/pl/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Rozpoczęcie pracy z tym programem nauczania
## Jesteś studentem?
diff --git a/translations/pl/lessons/1-Intro/README.md b/translations/pl/lessons/1-Intro/README.md
index d1ec59b4..022f638e 100644
--- a/translations/pl/lessons/1-Intro/README.md
+++ b/translations/pl/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Wprowadzenie do AI
diff --git a/translations/pl/lessons/1-Intro/assignment.md b/translations/pl/lessons/1-Intro/assignment.md
index 2954f6cc..f24f4f14 100644
--- a/translations/pl/lessons/1-Intro/assignment.md
+++ b/translations/pl/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Game Jam
Gry to dziedzina, która została mocno wpłynięta przez rozwój AI i ML. W tym zadaniu napisz krótką pracę na temat gry, którą lubisz, a która została ukształtowana przez ewolucję AI. Powinna to być gra na tyle stara, aby była pod wpływem różnych typów systemów przetwarzania komputerowego. Dobrym przykładem jest szachy lub Go, ale warto również przyjrzeć się grom wideo, takim jak Pong czy Pac-Man. Napisz esej omawiający przeszłość, teraźniejszość i przyszłość AI w kontekście tej gry.
diff --git a/translations/pl/lessons/2-Symbolic/README.md b/translations/pl/lessons/2-Symbolic/README.md
index 3e939917..1105b0c1 100644
--- a/translations/pl/lessons/2-Symbolic/README.md
+++ b/translations/pl/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Reprezentacja Wiedzy i Systemy Eksperckie
-
+
> Sketchnote autorstwa [Tomomi Imura](https://twitter.com/girlie_mac)
@@ -41,7 +32,7 @@ Najczęściej nie definiujemy wiedzy ściśle, ale wyrównujemy ją z innymi pok
Problematyka **reprezentacji wiedzy** polega zatem na znalezieniu skutecznego sposobu przedstawienia wiedzy w komputerze w formie danych, aby mogła być automatycznie wykorzystywana. Można to zobaczyć jako spektrum:
-
+
> Obraz autorstwa [Dmitry Soshnikov](http://soshnikov.com)
@@ -94,7 +85,7 @@ Składnia bloku | Wcięcie | | |
Jednym z wczesnych sukcesów symbolicznej AI były tzw. **systemy eksperckie** - systemy komputerowe zaprojektowane do działania jako ekspert w ograniczonym obszarze problemowym. Opierały się na **bazie wiedzy** wydobytej od jednego lub więcej ekspertów oraz zawierały **silnik wnioskowania**, który wykonywał pewne rozumowania na jej podstawie.
- | 
+ | 
---------------------------------------------|------------------------------------------------
Uproszczona struktura ludzkiego systemu nerwowego | Architektura systemu opartego na wiedzy
@@ -106,7 +97,7 @@ Systemy eksperckie są budowane na wzór ludzkiego systemu rozumowania, który z
Na przykład rozważmy system ekspercki do identyfikacji zwierzęcia na podstawie jego cech fizycznych:
-
+
> Obraz autorstwa [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/pl/lessons/2-Symbolic/assignment.md b/translations/pl/lessons/2-Symbolic/assignment.md
index a0c00dc7..47325392 100644
--- a/translations/pl/lessons/2-Symbolic/assignment.md
+++ b/translations/pl/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Budowanie Ontologii
Budowanie bazy wiedzy polega na kategoryzowaniu modelu, który reprezentuje fakty na dany temat. Wybierz temat – na przykład osobę, miejsce lub rzecz – a następnie stwórz model tego tematu. Skorzystaj z technik i strategii budowania modeli opisanych w tej lekcji. Przykładem może być stworzenie ontologii salonu z meblami, oświetleniem i innymi elementami. Czym salon różni się od kuchni? Łazienki? Skąd wiesz, że to salon, a nie jadalnia? Użyj [Protégé](https://protege.stanford.edu/), aby zbudować swoją ontologię.
diff --git a/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/README.md
index fdfb9b8e..2eb2b354 100644
--- a/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Wprowadzenie do sieci neuronowych: Perceptron
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ Jednym z pierwszych prób stworzenia czegoś podobnego do współczesnej sieci n
| | |
|--------------|-----------|
-| | |
+|
| 
|
> Obrazy [z Wikipedii](https://en.wikipedia.org/wiki/Perceptron)
@@ -34,7 +25,7 @@ y(x) = f(wTx)
gdzie f to funkcja aktywacji typu schodkowego
-
+
## Trenowanie perceptronu
diff --git a/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index bb1180fc..35e5ddcb 100644
--- a/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Klasyfikacja wieloklasowa za pomocą perceptronu
Zadanie laboratoryjne z [Kursu AI dla początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index 03c810c1..54e0df17 100644
--- a/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Wprowadzenie do sieci neuronowych. Wielowarstwowy perceptron
W poprzedniej sekcji poznaliśmy najprostszy model sieci neuronowej - jednowarstwowy perceptron, liniowy model klasyfikacji dla dwóch klas.
@@ -65,7 +56,7 @@ Algorytm gradientu prostego pozostanie taki sam, ale obliczanie gradientów będ
Zauważ, że lewa część wszystkich tych wyrażeń jest taka sama, dzięki czemu możemy efektywnie obliczać pochodne, zaczynając od funkcji straty i przechodząc "wstecz" przez graf obliczeniowy. Dlatego metoda treningu wielowarstwowego perceptronu nazywana jest **propagacją wsteczną**, lub 'backprop'.
-
+
> TODO: cytowanie obrazu
diff --git a/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 52d49d87..39e0da1a 100644
--- a/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# Klasyfikacja MNIST z Naszym Własnym Frameworkiem
Zadanie laboratoryjne z [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/README.md
index 34331b5d..b07d3eeb 100644
--- a/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Frameworky Sieci Neuronowych
Jak już się nauczyliśmy, aby efektywnie trenować sieci neuronowe, musimy zrobić dwie rzeczy:
diff --git a/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index d31eee7e..ce991438 100644
--- a/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Klasyfikacja z PyTorch/TensorFlow
Zadanie laboratoryjne z [Kursu AI dla Początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/3-NeuralNetworks/README.md b/translations/pl/lessons/3-NeuralNetworks/README.md
index 758f7d3f..6d3003eb 100644
--- a/translations/pl/lessons/3-NeuralNetworks/README.md
+++ b/translations/pl/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Wprowadzenie do sieci neuronowych
diff --git a/translations/pl/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/pl/lessons/4-ComputerVision/06-IntroCV/README.md
index ef433345..aa1b8fc0 100644
--- a/translations/pl/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/pl/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Wprowadzenie do wizji komputerowej
[Wizja komputerowa](https://wikipedia.org/wiki/Computer_vision) to dziedzina, której celem jest umożliwienie komputerom uzyskania wysokopoziomowego zrozumienia obrazów cyfrowych. Jest to dość szeroka definicja, ponieważ *zrozumienie* może oznaczać wiele różnych rzeczy, takich jak znalezienie obiektu na zdjęciu (**detekcja obiektów**), zrozumienie, co się dzieje (**detekcja zdarzeń**), opisanie obrazu w formie tekstu czy rekonstrukcja sceny w 3D. Istnieją również specjalne zadania związane z obrazami ludzi: szacowanie wieku i emocji, detekcja i identyfikacja twarzy oraz estymacja pozycji 3D, by wymienić tylko kilka.
@@ -115,7 +106,7 @@ Przeczytaj więcej o optycznym przepływie [w tym świetnym tutorialu](https://l
W tym laboratorium nagrasz wideo z prostymi gestami, a Twoim celem będzie wyodrębnienie ruchów góra/dół/lewo/prawo za pomocą optycznego przepływu.
-
+
---
diff --git a/translations/pl/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/pl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 09b84a43..476a0a4e 100644
--- a/translations/pl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/pl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Wykrywanie ruchów za pomocą optycznego przepływu
Zadanie laboratoryjne z [Kursu AI dla początkujących](https://aka.ms/ai-beginners).
diff --git a/translations/pl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/pl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 4f6099b8..29fe1181 100644
--- a/translations/pl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/pl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Znane Architektury CNN
### VGG-16
@@ -25,7 +16,7 @@ Jak widać, VGG stosuje tradycyjną architekturę piramidy, czyli sekwencję war
ResNet to rodzina modeli zaproponowana przez Microsoft Research w 2015 roku. Główną ideą ResNet jest wykorzystanie **bloków resztkowych**:
-
+
> Obraz z [tego artykułu](https://arxiv.org/pdf/1512.03385.pdf)
@@ -37,7 +28,7 @@ Można również pomyśleć o tej sieci jako o zdolnej do dostosowania swojej z
Architektura Google Inception idzie o krok dalej i buduje każdą warstwę sieci jako kombinację kilku różnych ścieżek:
-
+
> Obraz z [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)
diff --git a/translations/pl/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/pl/lessons/4-ComputerVision/07-ConvNets/README.md
index 23181e28..7d330dc1 100644
--- a/translations/pl/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/pl/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Konwolucyjne Sieci Neuronowe
Wcześniej widzieliśmy, że sieci neuronowe całkiem dobrze radzą sobie z obrazami, a nawet perceptron jednopoziomowy potrafi rozpoznawać odręczne cyfry z zestawu danych MNIST z zadowalającą dokładnością. Jednak zestaw danych MNIST jest wyjątkowy, ponieważ wszystkie cyfry są wyśrodkowane na obrazie, co upraszcza zadanie.
@@ -24,7 +15,7 @@ Aby wyodrębnić wzory, użyjemy pojęcia **filtrów konwolucyjnych**. Jak wiado
Na przykład, jeśli zastosujemy filtry krawędzi pionowych i poziomych o rozmiarze 3x3 do cyfr z MNIST, możemy uzyskać wyróżnienia (np. wysokie wartości) tam, gdzie w oryginalnym obrazie występują krawędzie pionowe i poziome. Te dwa filtry mogą być używane do "wyszukiwania" krawędzi. Podobnie, możemy zaprojektować różne filtry, aby wyszukiwać inne wzory niskiego poziomu:
-
+
> Obraz [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/pl/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/pl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index 48a3ac6a..b63b040d 100644
--- a/translations/pl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/pl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Klasyfikacja Twarzy Zwierząt Domowych
Zadanie laboratoryjne z [Kursu AI dla Początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/README.md
index 8850aaec..5e065b3b 100644
--- a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Wstępnie wytrenowane sieci i transfer uczenia
Trenowanie CNN może zająć dużo czasu, a do tego zadania potrzebne są duże ilości danych. Jednak większość czasu poświęca się na naukę najlepszych filtrów niskiego poziomu, które sieć może wykorzystać do wyodrębniania wzorców z obrazów. Pojawia się naturalne pytanie - czy możemy użyć sieci neuronowej wytrenowanej na jednym zbiorze danych i dostosować ją do klasyfikacji innych obrazów bez konieczności pełnego procesu trenowania?
diff --git a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 392288f5..93abe33f 100644
--- a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Triki w trenowaniu głębokich sieci neuronowych
Wraz z pogłębianiem się sieci neuronowych, proces ich trenowania staje się coraz bardziej wymagający. Jednym z głównych problemów są tzw. [zanikające gradienty](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) lub [eksplodujące gradienty](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Ten artykuł](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) dobrze wprowadza w te zagadnienia.
diff --git a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index 3a00f933..f37f27ff 100644
--- a/translations/pl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/pl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Klasyfikacja zwierząt domowych z Oxfordu za pomocą transferu uczenia
Zadanie laboratoryjne z [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/pl/lessons/4-ComputerVision/09-Autoencoders/README.md
index a83bc57a..b15b67ab 100644
--- a/translations/pl/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/pl/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Autoenkodery
Podczas trenowania CNN jednym z problemów jest potrzeba dużej ilości danych oznaczonych. W przypadku klasyfikacji obrazów musimy podzielić obrazy na różne klasy, co wymaga ręcznego wysiłku.
@@ -46,7 +37,7 @@ Podsumowując:
* Pobieramy próbkę wektora `sample` z rozkładu N(zmean,exp(zlog\_sigma))
* Dekoder próbuje odtworzyć oryginalny obraz, używając `sample` jako wektora wejściowego
-
+ 
> Obraz z [tego wpisu na blogu](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) autorstwa Isaaka Dykemana
@@ -57,13 +48,13 @@ Wariacyjne autoenkodery używają złożonej funkcji strat, która składa się
Jedną z ważnych zalet VAE jest to, że pozwalają na stosunkowo łatwe generowanie nowych obrazów, ponieważ wiemy, z jakiego rozkładu pobierać wektory latentne. Na przykład, jeśli przeszkolimy VAE z 2-wymiarowym wektorem latentnym na MNIST, możemy następnie zmieniać komponenty wektora latentnego, aby uzyskać różne cyfry:
-
+
> Obraz autorstwa [Dmitrija Soshnikova](http://soshnikov.com)
Zauważ, jak obrazy płynnie przechodzą jeden w drugi, gdy zaczynamy pobierać wektory latentne z różnych części przestrzeni parametrów latentnych. Możemy również zwizualizować tę przestrzeń w 2D:
-
+
> Obraz autorstwa [Dmitrija Soshnikova](http://soshnikov.com)
diff --git a/translations/pl/lessons/4-ComputerVision/10-GANs/README.md b/translations/pl/lessons/4-ComputerVision/10-GANs/README.md
index 26f92f08..a82d40cc 100644
--- a/translations/pl/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/pl/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Generative Adversarial Networks
W poprzedniej sekcji poznaliśmy **modele generatywne**: modele, które potrafią generować nowe obrazy podobne do tych z zestawu treningowego. VAE był dobrym przykładem modelu generatywnego.
@@ -17,7 +8,7 @@ Jednakże, jeśli spróbujemy wygenerować coś naprawdę znaczącego, na przyk
Główna idea GAN polega na wykorzystaniu dwóch sieci neuronowych, które będą trenowane przeciwko sobie:
-
+
> Obraz autorstwa [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ Generator jest nieco bardziej skomplikowany. Można go traktować jako odwrócon
> ✅ Ponieważ warstwa konwolucyjna jest implementowana jako filtr liniowy przesuwający się po obrazie, dekonwolucja jest zasadniczo podobna do konwolucji i może być zaimplementowana przy użyciu tej samej logiki warstwy.
-
+
> Obraz autorstwa [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/README.md
index dc907077..7b1399b6 100644
--- a/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Wykrywanie Obiektów
Modele klasyfikacji obrazów, które omawialiśmy do tej pory, przyjmowały obraz i zwracały wynik kategoryczny, na przykład klasę 'liczba' w problemie MNIST. Jednak w wielu przypadkach nie wystarczy nam wiedzieć, że na zdjęciu znajdują się obiekty – chcemy również określić ich dokładną lokalizację. Na tym właśnie polega **wykrywanie obiektów**.
diff --git a/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index d74bcc33..6613d907 100644
--- a/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/pl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Wykrywanie głów za pomocą zbioru danych Hollywood Heads
Zadanie laboratoryjne z [Kursu AI dla początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/pl/lessons/4-ComputerVision/12-Segmentation/README.md
index f9252218..b953b930 100644
--- a/translations/pl/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/pl/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Segmentacja
Wcześniej nauczyliśmy się o Detekcji Obiektów, która pozwala na lokalizację obiektów na obrazie poprzez przewidywanie ich *ramki ograniczającej*. Jednak w niektórych zadaniach potrzebujemy nie tylko ramek ograniczających, ale także bardziej precyzyjnej lokalizacji obiektów. To zadanie nazywa się **segmentacją**.
@@ -20,7 +11,7 @@ Segmentację można postrzegać jako **klasyfikację pikseli**, gdzie dla **każ
W przypadku segmentacji instancji te owce są różnymi obiektami, ale w segmentacji semantycznej wszystkie owce są reprezentowane jako jedna klasa.
-
+
> Obraz z [tego wpisu na blogu](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@@ -29,7 +20,7 @@ Istnieją różne architektury neuronowe do segmentacji, ale wszystkie mają pod
* **Enkoder** wyodrębnia cechy z obrazu wejściowego.
* **Dekoder** przekształca te cechy w **obraz maski**, o tym samym rozmiarze i liczbie kanałów odpowiadających liczbie klas.
-
+
> Obraz z [tej publikacji](https://arxiv.org/pdf/2001.05566.pdf)
@@ -43,7 +34,7 @@ W tej lekcji zobaczymy segmentację w praktyce, trenując sieć do rozpoznawania
> ✅ Ta technika jest szczególnie odpowiednia dla tego typu obrazowania medycznego, ale jakie inne zastosowania w rzeczywistym świecie możesz sobie wyobrazić?
-
+
> Obraz z Bazy Danych PH2
diff --git a/translations/pl/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/pl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index 9f61559e..cf35872f 100644
--- a/translations/pl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/pl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# Segmentacja Ciała Ludzkiego
Zadanie laboratoryjne z [Kursu AI dla Początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/4-ComputerVision/README.md b/translations/pl/lessons/4-ComputerVision/README.md
index 7bdcc2ad..ac7b7173 100644
--- a/translations/pl/lessons/4-ComputerVision/README.md
+++ b/translations/pl/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Komputerowe Rozpoznawanie Obrazów
diff --git a/translations/pl/lessons/5-NLP/13-TextRep/README.md b/translations/pl/lessons/5-NLP/13-TextRep/README.md
index ed09dc21..93b0cadb 100644
--- a/translations/pl/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/pl/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Reprezentowanie tekstu jako tensory
## [Pre-quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ Naszym celem będzie sklasyfikowanie artykułu prasowego do jednej z kategorii n
Aby rozwiązywać zadania związane z przetwarzaniem języka naturalnego (NLP) za pomocą sieci neuronowych, musimy znaleźć sposób na reprezentowanie tekstu jako tensory. Komputery już teraz reprezentują znaki tekstowe jako liczby, które mapują na czcionki na ekranie, używając kodowań takich jak ASCII czy UTF-8.
-
+
> [Źródło obrazu](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ W niektórych przypadkach możemy rozważyć użycie tri-gramów — kombinacji
Podczas rozwiązywania zadań takich jak klasyfikacja tekstu musimy być w stanie reprezentować tekst za pomocą jednego wektora o stałym rozmiarze, który będzie używany jako wejście do końcowego klasyfikatora gęstego. Jednym z najprostszych sposobów na to jest połączenie wszystkich indywidualnych reprezentacji słów, np. przez ich dodanie. Jeśli dodamy kodowania one-hot każdego słowa, otrzymamy wektor częstotliwości, pokazujący, ile razy każde słowo pojawia się w tekście. Taka reprezentacja tekstu nazywana jest **bag-of-words** (BoW).
-
+
> Obraz autorstwa autora
diff --git a/translations/pl/lessons/5-NLP/13-TextRep/assignment.md b/translations/pl/lessons/5-NLP/13-TextRep/assignment.md
index 1ce22dea..a6e14cd7 100644
--- a/translations/pl/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/pl/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Zadanie: Notatniki
Korzystając z notatników powiązanych z tą lekcją (w wersji PyTorch lub TensorFlow), uruchom je ponownie, używając własnego zestawu danych, na przykład z Kaggle, z odpowiednim przypisaniem źródła. Przepisz notatnik, aby podkreślić swoje własne wnioski. Spróbuj użyć innowacyjnych zestawów danych, które mogą okazać się zaskakujące, takich jak [ten o obserwacjach UFO](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) od NUFORC.
diff --git a/translations/pl/lessons/5-NLP/14-Embeddings/README.md b/translations/pl/lessons/5-NLP/14-Embeddings/README.md
index ddbec807..80586497 100644
--- a/translations/pl/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/pl/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Osadzenia
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/pl/lessons/5-NLP/14-Embeddings/assignment.md b/translations/pl/lessons/5-NLP/14-Embeddings/assignment.md
index ccca73d7..4fa10398 100644
--- a/translations/pl/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/pl/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Zadanie: Notatniki
Korzystając z notatników powiązanych z tą lekcją (zarówno w wersji PyTorch, jak i TensorFlow), uruchom je ponownie, używając własnego zestawu danych, na przykład z Kaggle, z odpowiednim przypisaniem źródła. Przepisz notatnik, aby podkreślić swoje własne wnioski. Spróbuj użyć innego rodzaju zestawu danych i udokumentuj swoje spostrzeżenia, korzystając z tekstów takich jak [te teksty piosenek Beatlesów](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
diff --git a/translations/pl/lessons/5-NLP/15-LanguageModeling/README.md b/translations/pl/lessons/5-NLP/15-LanguageModeling/README.md
index 16412598..dc2deea8 100644
--- a/translations/pl/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/pl/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Modelowanie języka
Semantyczne osadzenia, takie jak Word2Vec i GloVe, są w rzeczywistości pierwszym krokiem w kierunku **modelowania języka** - tworzenia modeli, które w pewien sposób *rozumieją* (lub *reprezentują*) naturę języka.
diff --git a/translations/pl/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/pl/lessons/5-NLP/15-LanguageModeling/lab/README.md
index 61f037a5..a08dfe8b 100644
--- a/translations/pl/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/pl/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Trenowanie modelu Skip-Gram
Zadanie laboratoryjne z [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/5-NLP/16-RNN/README.md b/translations/pl/lessons/5-NLP/16-RNN/README.md
index 3c62bb48..ceb55965 100644
--- a/translations/pl/lessons/5-NLP/16-RNN/README.md
+++ b/translations/pl/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Sieci Neuronowe Rekurencyjne
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ Przyjrzyjmy się, jak zorganizowana jest prosta komórka RNN. Przyjmuje ona popr
Prosta komórka RNN ma wewnątrz dwie macierze wag: jedna przekształca symbol wejściowy (nazwijmy ją W), a druga przekształca stan wejściowy (H). W takim przypadku wyjście sieci obliczane jest jako σ(W×Xi+H×Si-1+b), gdzie σ to funkcja aktywacji, a b to dodatkowe przesunięcie.
-
+
> Obraz autorstwa autora
diff --git a/translations/pl/lessons/5-NLP/16-RNN/assignment.md b/translations/pl/lessons/5-NLP/16-RNN/assignment.md
index 89abfd56..c6d8a0a2 100644
--- a/translations/pl/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/pl/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Zadanie: Notatniki
Korzystając z notatników powiązanych z tą lekcją (w wersji PyTorch lub TensorFlow), uruchom je ponownie, używając własnego zestawu danych, na przykład z Kaggle, z odpowiednim przypisaniem źródła. Przepisz notatnik, aby podkreślić swoje własne wnioski. Spróbuj użyć innego rodzaju zestawu danych i udokumentuj swoje spostrzeżenia, korzystając z tekstu, takiego jak [ten zestaw danych z konkursu Kaggle dotyczący tweetów o pogodzie](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
diff --git a/translations/pl/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/pl/lessons/5-NLP/17-GenerativeNetworks/README.md
index 3a2da89b..cb2dc56b 100644
--- a/translations/pl/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/pl/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Generatywne sieci
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ Wytrenujemy tę RNN do generowania tekstu krok po kroku. Na każdym kroku weźmi
Podczas generowania tekstu (w trakcie inferencji) zaczynamy od jakiegoś **podpowiedzi** (prompt), która jest przepuszczana przez komórki RNN, aby wygenerować jej stan pośredni, a następnie z tego stanu rozpoczyna się generowanie. Generujemy jeden znak na raz, przekazujemy stan i wygenerowany znak do kolejnej komórki RNN, aby wygenerować następny znak, aż wygenerujemy wystarczającą liczbę znaków.
-
+
> Obraz autorstwa autora
diff --git a/translations/pl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/pl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index 7913e075..580c5395 100644
--- a/translations/pl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/pl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Generowanie tekstu na poziomie słów za pomocą RNN
Zadanie laboratoryjne z [Kursu AI dla Początkujących](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/5-NLP/18-Transformers/README.md b/translations/pl/lessons/5-NLP/18-Transformers/README.md
index 934910f5..256f06d9 100644
--- a/translations/pl/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/pl/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Mechanizmy uwagi i modele Transformer
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ Pomysł kodowania pozycji jest następujący:
* Osadzanie uczone, podobne do osadzania tokenów. To podejście rozważamy tutaj. Nakładamy warstwy osadzania zarówno na tokeny, jak i ich pozycje, uzyskując wektory osadzania o tych samych wymiarach, które następnie dodajemy do siebie.
* Funkcja kodowania pozycji stałej, jak zaproponowano w oryginalnym artykule.
-
+
> Obraz autorstwa autora
diff --git a/translations/pl/lessons/5-NLP/18-Transformers/assignment.md b/translations/pl/lessons/5-NLP/18-Transformers/assignment.md
index 5a6fe320..5747487b 100644
--- a/translations/pl/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/pl/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Zadanie: Transformers
Eksperymentuj z Transformerami na HuggingFace! Wypróbuj niektóre z udostępnionych przez nich skryptów, aby pracować z różnymi modelami dostępnymi na ich stronie: https://huggingface.co/docs/transformers/run_scripts. Wypróbuj jeden z ich zestawów danych, a następnie zaimportuj jeden z własnych z tego programu nauczania lub z Kaggle i sprawdź, czy uda Ci się wygenerować interesujące teksty. Przygotuj notatnik z wynikami swoich badań.
diff --git a/translations/pl/lessons/5-NLP/19-NER/README.md b/translations/pl/lessons/5-NLP/19-NER/README.md
index 6b0fb2bb..a87dc387 100644
--- a/translations/pl/lessons/5-NLP/19-NER/README.md
+++ b/translations/pl/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Rozpoznawanie nazwanych jednostek
Do tej pory skupialiśmy się głównie na jednym zadaniu NLP - klasyfikacji. Jednak istnieją również inne zadania NLP, które można realizować za pomocą sieci neuronowych. Jednym z takich zadań jest **[Rozpoznawanie nazwanych jednostek](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), które polega na identyfikowaniu konkretnych jednostek w tekście, takich jak miejsca, imiona i nazwiska, przedziały czasowe, wzory chemiczne i inne.
@@ -17,7 +8,7 @@ Do tej pory skupialiśmy się głównie na jednym zadaniu NLP - klasyfikacji. Je
Załóżmy, że chcesz stworzyć chatbot oparty na języku naturalnym, podobny do Amazon Alexa czy Google Assistant. Inteligentne chatboty działają w ten sposób, że *rozumieją*, czego użytkownik chce, poprzez klasyfikację tekstu w zdaniu wejściowym. Wynikiem tej klasyfikacji jest tak zwany **intencja**, która określa, co chatbot powinien zrobić.
-
+
> Obraz autorstwa autora
diff --git a/translations/pl/lessons/5-NLP/19-NER/lab/README.md b/translations/pl/lessons/5-NLP/19-NER/lab/README.md
index d073269c..caa1ac5e 100644
--- a/translations/pl/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/pl/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
Zadanie laboratoryjne z [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/pl/lessons/5-NLP/20-LangModels/README.md b/translations/pl/lessons/5-NLP/20-LangModels/README.md
index 423987f4..a1024e93 100644
--- a/translations/pl/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/pl/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Wstępnie Wytrenowane Duże Modele Językowe
We wszystkich naszych wcześniejszych zadaniach trenowaliśmy sieć neuronową, aby wykonywała określone zadanie, korzystając z oznaczonego zbioru danych. W przypadku dużych modeli transformatorowych, takich jak BERT, wykorzystujemy modelowanie języka w trybie samonadzorowanym, aby zbudować model językowy, który następnie jest specjalizowany do konkretnych zadań za pomocą dalszego treningu specyficznego dla danej dziedziny. Jednakże wykazano, że duże modele językowe mogą również rozwiązywać wiele zadań bez jakiegokolwiek treningu specyficznego dla dziedziny. Rodzina modeli zdolnych do tego nazywa się **GPT**: Generative Pre-Trained Transformer.
diff --git a/translations/pl/lessons/5-NLP/README.md b/translations/pl/lessons/5-NLP/README.md
index 20dc7145..518c0fc4 100644
--- a/translations/pl/lessons/5-NLP/README.md
+++ b/translations/pl/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Przetwarzanie Języka Naturalnego
diff --git a/translations/pl/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/pl/lessons/6-Other/21-GeneticAlgorithms/README.md
index 2443df83..8dfff715 100644
--- a/translations/pl/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/pl/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Algorytmy Genetyczne
## [Quiz przed wykładem](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/pl/lessons/6-Other/22-DeepRL/README.md b/translations/pl/lessons/6-Other/22-DeepRL/README.md
index e6176042..df06fe5d 100644
--- a/translations/pl/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/pl/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Deep Reinforcement Learning
Uczenie przez wzmacnianie (RL) jest uważane za jeden z podstawowych paradygmatów uczenia maszynowego, obok uczenia nadzorowanego i nienadzorowanego. Podczas gdy w uczeniu nadzorowanym opieramy się na zbiorze danych z określonymi wynikami, RL bazuje na **uczeniu się przez działanie**. Na przykład, gdy po raz pierwszy widzimy grę komputerową, zaczynamy grać, nawet nie znając zasad, a wkrótce jesteśmy w stanie poprawić swoje umiejętności dzięki samemu procesowi grania i dostosowywania swojego zachowania.
@@ -34,7 +25,7 @@ Prawdopodobnie wszyscy widzieliście nowoczesne urządzenia balansujące, takie
Uproszczona wersja balansowania jest znana jako problem **CartPole**. W świecie CartPole mamy poziomy suwak, który może poruszać się w lewo lub w prawo, a celem jest balansowanie pionowego drążka na szczycie suwaka podczas jego ruchu.
-
+
Aby stworzyć i używać tego środowiska, potrzebujemy kilku linii kodu w Pythonie:
diff --git a/translations/pl/lessons/6-Other/22-DeepRL/lab/README.md b/translations/pl/lessons/6-Other/22-DeepRL/lab/README.md
index dfd2f427..29eb063c 100644
--- a/translations/pl/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/pl/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## Środowisko
Środowisko Mountain Car składa się z samochodu uwięzionego w dolinie. Twoim celem jest wyskoczyć z doliny i dotrzeć do flagi. Możesz wykonywać następujące akcje: przyspieszać w lewo, w prawo lub nic nie robić. Możesz obserwować pozycję samochodu na osi x oraz jego prędkość.
diff --git a/translations/pl/lessons/6-Other/23-MultiagentSystems/README.md b/translations/pl/lessons/6-Other/23-MultiagentSystems/README.md
index bfd21a07..dc1b5809 100644
--- a/translations/pl/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/pl/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Systemy Wieloagentowe
Jednym z możliwych sposobów osiągnięcia inteligencji jest tak zwane podejście **emergentne** (lub **synergetyczne**), które opiera się na fakcie, że połączone zachowanie wielu stosunkowo prostych agentów może prowadzić do bardziej złożonego (lub inteligentnego) zachowania całego systemu. Teoretycznie opiera się to na zasadach [Inteligencji Kolektywnej](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentyzmu](https://en.wikipedia.org/wiki/Global_brain) i [Ewolucyjnej Cybernetyki](https://en.wikipedia.org/wiki/Global_brain), które zakładają, że systemy wyższego poziomu zyskują pewną wartość dodaną, gdy są odpowiednio połączone z systemami niższego poziomu (tak zwana *zasada przejścia metasystemowego*).
@@ -60,7 +51,7 @@ Możesz [pobrać](https://ccl.northwestern.edu/netlogo/download.shtml) i zainsta
Wspaniałą rzeczą w NetLogo jest to, że zawiera bibliotekę działających modeli, które możesz wypróbować. Przejdź do **File → Models Library**, gdzie znajdziesz wiele kategorii modeli do wyboru.
-
+
> Zrzut ekranu biblioteki modeli autorstwa Dmitry Soshnikov
diff --git a/translations/pl/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/pl/lessons/6-Other/23-MultiagentSystems/assignment.md
index d18e4873..50ba7e11 100644
--- a/translations/pl/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/pl/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# Zadanie NetLogo
Wybierz jeden z modeli z biblioteki NetLogo i użyj go do jak najdokładniejszego zasymulowania rzeczywistej sytuacji. Dobrym przykładem byłoby dostosowanie modelu Virus z folderu Alternative Visualizations, aby pokazać, jak można go wykorzystać do modelowania rozprzestrzeniania się COVID-19. Czy potrafisz stworzyć model, który odzwierciedla rzeczywiste rozprzestrzenianie się wirusa?
diff --git a/translations/pl/lessons/7-Ethics/README.md b/translations/pl/lessons/7-Ethics/README.md
index b0af5e94..1ba168c2 100644
--- a/translations/pl/lessons/7-Ethics/README.md
+++ b/translations/pl/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Etyka i Odpowiedzialna Sztuczna Inteligencja
Jesteś już prawie na końcu tego kursu i mam nadzieję, że teraz wyraźnie widzisz, że sztuczna inteligencja opiera się na szeregu formalnych metod matematycznych, które pozwalają nam znajdować zależności w danych i trenować modele, aby odtwarzały pewne aspekty ludzkiego zachowania. W obecnym momencie historii uważamy AI za bardzo potężne narzędzie do wydobywania wzorców z danych i stosowania tych wzorców do rozwiązywania nowych problemów.
diff --git a/translations/pl/lessons/README.md b/translations/pl/lessons/README.md
index 1c2b27d4..5e27ae66 100644
--- a/translations/pl/lessons/README.md
+++ b/translations/pl/lessons/README.md
@@ -1,12 +1,3 @@
-
# Przegląd
diff --git a/translations/pl/lessons/X-Extras/X1-MultiModal/README.md b/translations/pl/lessons/X-Extras/X1-MultiModal/README.md
index 0809cd58..52188851 100644
--- a/translations/pl/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/pl/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Sieci Multi-Modalne
Po sukcesie modeli transformerowych w rozwiązywaniu zadań NLP, podobne architektury zaczęto stosować w zadaniach związanych z wizją komputerową. Coraz większe zainteresowanie budzą modele, które *łączą* możliwości analizy obrazu i języka naturalnego. Jednym z takich podejść jest CLIP i DALL.E, opracowane przez OpenAI.
diff --git a/translations/pl/lessons/sketchnotes/LICENSE.md b/translations/pl/lessons/sketchnotes/LICENSE.md
index 4054387e..cb667131 100644
--- a/translations/pl/lessons/sketchnotes/LICENSE.md
+++ b/translations/pl/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Prawa, prawa te nie są licencjonowane na mocy tej Licencji Publicznej; oraz
c. nie możesz oferować ani nakładać żadnych dodatkowych lub odmiennych warunków, ani stosować Skutecznych Środków Technologicznych do Materiału Licencjonowanego, które ograniczałyby korzystanie z praw przyznanych na mocy tej Licencji Publicznej przez jakiegokolwiek odbiorcę Materiału Licencjonowanego.
diff --git a/translations/pl/lessons/sketchnotes/README.md b/translations/pl/lessons/sketchnotes/README.md
index 08bb53ee..5c9bf4ac 100644
--- a/translations/pl/lessons/sketchnotes/README.md
+++ b/translations/pl/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Wszystkie sketchnotki z programu nauczania można pobrać tutaj.
🎨 Stworzone przez: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/pl/troubleshoot.md b/translations/pl/troubleshoot.md
index 3560d2d8..adfa659a 100644
--- a/translations/pl/troubleshoot.md
+++ b/translations/pl/troubleshoot.md
@@ -1,12 +1,3 @@
-
# Przewodnik rozwiązywania problemów AI-For-Beginners
Ten przewodnik pomoże Ci rozwiązać typowe problemy napotykane podczas korzystania lub współtworzenia repozytorium [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners). Każdy problem zawiera tło, objawy, wyjaśnienia oraz krok po kroku rozwiązania.
diff --git a/translations/tr/.co-op-translator.json b/translations/tr/.co-op-translator.json
new file mode 100644
index 00000000..8650a355
--- /dev/null
+++ b/translations/tr/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:21:01+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "tr"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T01:51:30+00:00",
+ "source_file": "README.md",
+ "language_code": "tr"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-26T07:18:31+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "tr"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-26T07:40:40+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "tr"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-26T07:40:57+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "tr"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-26T07:41:10+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "tr"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-26T07:40:34+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "tr"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-26T07:40:47+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "tr"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-26T07:41:37+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "tr"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:30:39+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "tr"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-26T07:40:06+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "tr"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-15T14:33:23+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "tr"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:44:50+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "tr"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:25:41+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "tr"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:27:04+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-15T14:33:42+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "tr"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-26T07:39:40+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T08:43:57+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-29T08:23:35+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T08:43:26+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-26T07:34:52+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T08:44:15+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-26T07:35:34+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:48:22+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T08:39:22+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-26T07:29:48+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T08:38:45+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T08:38:27+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:54:50+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T08:39:01+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-26T07:30:50+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-26T07:31:24+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T08:40:20+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T08:41:09+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T08:39:45+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-26T07:28:01+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T08:40:53+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-26T07:26:11+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-26T07:25:04+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T08:47:28+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-26T07:22:19+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T08:47:10+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-26T07:21:03+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T08:45:09+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-26T07:22:41+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T08:46:25+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-26T07:20:30+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T08:44:46+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-26T07:21:43+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T08:45:19+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-26T07:22:50+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T08:46:07+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-26T07:23:20+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T08:45:46+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "tr"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-26T07:19:03+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "tr"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T08:37:02+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "tr"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T08:38:00+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "tr"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-26T07:33:24+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "tr"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T08:37:18+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "tr"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-26T07:32:42+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "tr"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-26T07:18:48+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "tr"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-26T07:18:43+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "tr"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-26T07:33:31+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "tr"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-26T07:37:11+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "tr"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-26T07:36:11+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "tr"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:43:37+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "tr"
+ }
+}
\ No newline at end of file
diff --git a/translations/tr/AGENTS.md b/translations/tr/AGENTS.md
index fb958347..b80b916b 100644
--- a/translations/tr/AGENTS.md
+++ b/translations/tr/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Proje Genel Bakış
diff --git a/translations/tr/README.md b/translations/tr/README.md
index 1901c9b4..2e986ba4 100644
--- a/translations/tr/README.md
+++ b/translations/tr/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -21,159 +12,160 @@ CO_OP_TRANSLATOR_METADATA:
[](https://discord.gg/nTYy5BXMWG)
-# Yapay Zekaya Yeni Başlayanlar İçin - Bir Müfredat
+# Yeni Başlayanlar İçin Yapay Zeka - Bir Müfredat
-||
+||
|:---:|
-| Yapay Zekaya Yeni Başlayanlar - _[@girlie_mac](https://twitter.com/girlie_mac) tarafından Sketchnote_ |
+| Yeni Başlayanlar İçin Yapay Zeka - _Sketchnote [@girlie_mac](https://twitter.com/girlie_mac) tarafından_ |
-12 haftalık, 24 derslik müfredatımızla **Yapay Zeka** (AI) dünyasını keşfedin! Pratik dersler, quizler ve laboratuvarlar içerir. Müfredat, yeni başlayanlar için uygundur ve TensorFlow ile PyTorch gibi araçların yanı sıra yapay zekada etik konularını kapsar.
+**Yapay Zeka** (YZ) dünyasını 12 haftalık, 24 derslik müfredatımızla keşfedin! Pratik dersler, quizler ve laboratuvarlar içerir. Müfredat başlangıç seviyesi için uygundur ve TensorFlow, PyTorch gibi araçların yanı sıra YZ'deki etik konularını da kapsar.
-### 🌐 Çok Dilde Destek
+### 🌐 Çoklu Dil Desteği
-#### GitHub Action ile desteklenir (Otomatik ve Her Zaman Güncel)
+#### GitHub Action ile Desteklenmektedir (Otomatik ve Her Zaman Güncel)
-[Arapça](../ar/README.md) | [Bengalce](../bn/README.md) | [Bulgarca](../bg/README.md) | [Burma (Myanmar)](../my/README.md) | [Çince (Basitleştirilmiş)](../zh/README.md) | [Çince (Geleneksel, Hong Kong)](../hk/README.md) | [Çince (Geleneksel, Makao)](../mo/README.md) | [Çince (Geleneksel, Tayvan)](../tw/README.md) | [Hırvatça](../hr/README.md) | [Çekçe](../cs/README.md) | [Danca](../da/README.md) | [Flemenkçe](../nl/README.md) | [Estonyaca](../et/README.md) | [Fince](../fi/README.md) | [Fransızca](../fr/README.md) | [Almanca](../de/README.md) | [Yunanca](../el/README.md) | [İbranice](../he/README.md) | [Hintçe](../hi/README.md) | [Macarca](../hu/README.md) | [Endonezce](../id/README.md) | [İtalyanca](../it/README.md) | [Japonca](../ja/README.md) | [Kannada](../kn/README.md) | [Korece](../ko/README.md) | [Litvanca](../lt/README.md) | [Malayca](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalce](../ne/README.md) | [Nijerya Pidgin](../pcm/README.md) | [Norveççe](../no/README.md) | [Farsça (Persian)](../fa/README.md) | [Lehçe](../pl/README.md) | [Portekizce (Brezilya)](../br/README.md) | [Portekizce (Portekiz)](../pt/README.md) | [Pencapça (Gurmukhi)](../pa/README.md) | [Rumence](../ro/README.md) | [Rusça](../ru/README.md) | [Sırpça (Kiril)](../sr/README.md) | [Slovakça](../sk/README.md) | [Slovence](../sl/README.md) | [İspanyolca](../es/README.md) | [Svahili](../sw/README.md) | [İsveççe](../sv/README.md) | [Tagalog (Filipinler)](../tl/README.md) | [Tamilce](../ta/README.md) | [Telugu](../te/README.md) | [Tayca](../th/README.md) | [Türkçe](./README.md) | [Ukraynaca](../uk/README.md) | [Urduca](../ur/README.md) | [Vietnamca](../vi/README.md)
+[Arapça](../ar/README.md) | [Bengalce](../bn/README.md) | [Bulgarca](../bg/README.md) | [Burma Dili (Myanmar)](../my/README.md) | [Çince (Basitleştirilmiş)](../zh-CN/README.md) | [Çince (Geleneksel, Hong Kong)](../zh-HK/README.md) | [Çince (Geleneksel, Makao)](../zh-MO/README.md) | [Çince (Geleneksel, Tayvan)](../zh-TW/README.md) | [Hırvatça](../hr/README.md) | [Çekçe](../cs/README.md) | [Danca](../da/README.md) | [Felemenkçe](../nl/README.md) | [Estonca](../et/README.md) | [Fince](../fi/README.md) | [Fransızca](../fr/README.md) | [Almanca](../de/README.md) | [Yunanca](../el/README.md) | [İbranice](../he/README.md) | [Hintçe](../hi/README.md) | [Macarca](../hu/README.md) | [Endonezce](../id/README.md) | [İtalyanca](../it/README.md) | [Japonca](../ja/README.md) | [Kannada Dili](../kn/README.md) | [Korece](../ko/README.md) | [Litvanca](../lt/README.md) | [Malayca](../ms/README.md) | [Malayalam Dili](../ml/README.md) | [Marathi Dili](../mr/README.md) | [Nepalce](../ne/README.md) | [Nijerya Pidgin](../pcm/README.md) | [Norveççe](../no/README.md) | [Farsça (Persçe)](../fa/README.md) | [Lehçe](../pl/README.md) | [Portekizce (Brezilya)](../pt-BR/README.md) | [Portekizce (Portekiz)](../pt-PT/README.md) | [Pencapça (Gurmukhi)](../pa/README.md) | [Rumence](../ro/README.md) | [Rusça](../ru/README.md) | [Sırpça (Kiril Alfabesi)](../sr/README.md) | [Slovakça](../sk/README.md) | [Slovence](../sl/README.md) | [İspanyolca](../es/README.md) | [Svahili Dili](../sw/README.md) | [İsveççe](../sv/README.md) | [Tagalogca (Filipince)](../tl/README.md) | [Tamilce](../ta/README.md) | [Telugu Dili](../te/README.md) | [Tayca](../th/README.md) | [Türkçe](./README.md) | [Ukraynaca](../uk/README.md) | [Urduca](../ur/README.md) | [Vietnamca](../vi/README.md)
-> **Yerelde Klonlamayı Tercih Ediyor musunuz?**
+> **Yerel Klonlamayı Tercih Eder misiniz?**
-> Bu depo, indirme boyutunu önemli ölçüde artıran 50+ dil çevirisi içerir. Çeviriler olmadan klonlamak için spars checkout kullanın:
+> Bu depo 50'den fazla dil çevirisini içerir, bu da indirme boyutunu önemli ölçüde artırır. Çeviriler olmadan klonlamak için seyrek checkout kullanın:
> ```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'
> ```
-> Bu size kursu tamamlamak için ihtiyacınız olan her şeyi daha hızlı indirmenizi sağlar.
+> Bu size kursu tamamlamak için ihtiyacınız olan her şeyi çok daha hızlı bir indirme ile sağlar.
-**Ek dil çeviri desteği için isteklerinizi [buradan](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) iletebilirsiniz**
+**Ek çeviri dillerinin desteklenmesini isterseniz, desteklenenler [burada](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) listelenmiştir**
## Topluluğa Katılın
[](https://discord.gg/nTYy5BXMWG)
-## Neler Öğreneceksiniz
+## Öğrenecekleriniz
**[Kursun Zihin Haritası](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
Bu müfredatta öğrenecekleriniz:
-* Yapay Zekanın farklı yaklaşımları, "iyi eski" sembolik yaklaşım olan **Bilgi Temsili** ve çıkarım ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)) dahil.
-* Modern yapay zekanın temelinde olan **Sinir Ağları** ve **Derin Öğrenme**. Bu önemli konuların arkasındaki kavramları, en popüler iki framework olan [TensorFlow](http://Tensorflow.org) ve [PyTorch](http://pytorch.org) içinde kod örnekleriyle göstereceğiz.
-* Görüntü ve metinle çalışmak için **Sinir Ağı Mimarileri**. Güncel modelleri kapsayacağız ancak en son durumu tam yansıtmayabilir.
-* Daha az popüler AI yaklaşımları, örneğin **Genetik Algoritmalar** ve **Çok Ajanlı Sistemler**.
+* **Bilgi Temsili** ve akıl yürütme içeren "eski iyi" sembolik yaklaşım dahil olmak üzere Yapay Zekaya farklı yaklaşımlar ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* Modern YZ'nin temelinde yer alan **Sinir Ağları** ve **Derin Öğrenme**. Bu önemli konuları, en popüler iki framework olan [TensorFlow](http://Tensorflow.org) ve [PyTorch](http://pytorch.org) ile kod örnekleri üzerinden açıklayacağız.
+* Görüntü ve metinle çalışmak için **Sinirsel Mimariler**. Güncel modelleri kapsayacağız ancak en son teknolojide biraz eksik olabilir.
+* Daha az yaygın olan yapay zeka yaklaşımları, örneğin **Genetik Algoritmalar** ve **Çok Ajanlı Sistemler**.
-Bu müfredatta kapsamayacağımız konular:
+Bu müfredatta kapsam dışında bırakılanlar:
-> [Bu kurs için tüm ek kaynakları Microsoft Learn koleksiyonumuzda bulun](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Kurs için tüm ek kaynakları Microsoft Learn koleksiyonumuzda bulun](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* **İş dünyasında AI kullanımı**na dair iş vaka örnekleri. Microsoft Learn’da yer alan [İş kullanıcıları için Yapay Zekaya Giriş](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolunu veya [AI İş Okulu](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum) programını, [INSEAD](https://www.insead.edu/) iş birliğiyle inceleyebilirsiniz.
-* Klasik **Makine Öğrenimi**, [Makine Öğrenimi Yeni Başlayanlar Müfredatımızda](http://github.com/Microsoft/ML-for-Beginners) detaylıca açıklanmıştır.
-* **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** kullanılarak oluşturulan pratik AI uygulamaları. Bunun için Microsoft Learn üzerindeki [görme](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [doğal dil işleme](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Azure OpenAI Hizmeti ile Üretken AI](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ve diğer modüllerle başlamanızı öneririz.
-* Belirli ML **Bulut Çerçeveleri**, örneğin [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) veya [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). [Azure Machine Learning ile makine öğrenimi çözümleri oluşturma ve işletme](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ve [Azure Databricks ile makine öğrenimi çözümleri oluşturma ve işletme](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) öğrenme yollarını değerlendirin.
-* **Konuşarak Yapay Zeka** ve **Sohbet Botları**. Ayrı bir [Konuşan yapay zeka çözümleri oluşturma](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolu bulunmaktadır, ayrıca detaylar için [bu blog yazısını](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) inceleyebilirsiniz.
-* Derin öğrenmenin arkasındaki **Derin Matematik**. Bunun için Ian Goodfellow, Yoshua Bengio ve Aaron Courville’nin yazdığı [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) kitabını, ayrıca [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) üzerinden çevrimiçi olarak öneririz.
+* **İş dünyasında YZ** kullanımına ilişkin iş vaka analizleri. Microsoft Learn'den [İş Kullanıcıları için YZ'ye Giriş](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolunu ya da [YZ İş Okulu](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), [INSEAD](https://www.insead.edu/) işbirliği ile geliştirilmiş, inceleyebilirsiniz.
+* Klasik makine öğrenmesi, [Makine Öğrenimi Yeni Başlayanlar Müfredatımızda](http://github.com/Microsoft/ML-for-Beginners) iyi anlatılmıştır.
+* **[Bilişsel Hizmetler](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** kullanılarak inşa edilmiş pratik YZ uygulamaları. Bunun için Microsoft Learn modülleri arasında [görüntü işleme](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [doğal dil işleme](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Azure OpenAI Hizmeti ile Üretken YZ](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ve diğerlerini öneriyoruz.
+* [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) veya [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum) gibi belirli Bulut ML Framework’leri. [Azure Machine Learning ile Makine Öğrenimi Çözümleri Kur ve İşlet](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ve [Azure Databricks ile Makine Öğrenimi Çözümleri Kur ve İşlet](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) öğrenme yollarını kullanmayı düşünebilirsiniz.
+* **Konuşma YZ'si** ve **Sohbet Botları**. Ayrı bir [Konuşma YZ Çözümleri Oluşturma](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolu vardır ve daha fazla detay için [bu blog yazısına](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) da bakabilirsiniz.
+* Derin öğrenmenin ardındaki **Derin Matematik**. Bunun için Ian Goodfellow, Yoshua Bengio ve Aaron Courville'nin yazdığı [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) kitabını öneririz, ayrıca çevrimiçi olarak [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) üzerinden ulaşabilirsiniz.
-_Bulut’da AI_ konularına yumuşak bir giriş için [Azure üzerinde yapay zekaya başlama](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolunu değerlendirebilirsiniz.
+_Bulut üzerinde Yapay Zeka_ konularına nazik bir giriş için [Azure’da yapay zekaya başlangıç](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) öğrenme yolunu düşünebilirsiniz.
# İçerik
-| | Ders Bağlantısı | PyTorch/Keras/TensorFlow | Laboratuvar |
+| | Ders Bağlantısı | PyTorch/Keras/TensorFlow | Lab |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
| 0 | [Kurs Kurulumu](./lessons/0-course-setup/setup.md) | [Geliştirme Ortamınızı Kurun](./lessons/0-course-setup/how-to-run.md) | |
-| I | [**Yapay Zekaya Giriş**](./lessons/1-Intro/README.md) | | |
-| 01 | [Yapay Zekaya Giriş ve Tarihçe](./lessons/1-Intro/README.md) | - | - |
-| II | **Sembolik Yapay Zeka** |
+| I | [**YZ'ye Giriş**](./lessons/1-Intro/README.md) | | |
+| 01 | [YZ'nin Girişi ve Tarihi](./lessons/1-Intro/README.md) | - | - |
+| II | **Sembolik YZ** |
| 02 | [Bilgi Temsili ve Uzman Sistemler](./lessons/2-Symbolic/README.md) | [Uzman Sistemler](./lessons/2-Symbolic/Animals.ipynb) / [Ontoloji](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Kavram Grafiği](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Sinir Ağlarına Giriş**](./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 | [Çok Katmanlı Perceptron ve Kendi Çerçevemizi Oluşturma](./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 | [Çerçevelere Giriş (PyTorch/TensorFlow) ve Aşırı Öğrenme](./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 | [**Bilgisayarlı Görüntü İşleme**](./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'da Bilgisayarlı Görüntüyü Keşfedin](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
-| 06 | [Bilgisayarlı Görüntü İşlemeye Giriş. 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 | [Konvolüsyonel Sinir Ağları](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN Mimarileri](./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 | [Önceden Eğitilmiş Ağlar ve Transfer Öğrenme](./lessons/4-ComputerVision/08-TransferLearning/README.md) ve [Eğitim Püf Noktaları](./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 | [Otoenkoderler ve VAE'ler](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
-| 10 | [Üretken Rekabetçi Ağlar & Sanatsal Stil Transferi](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
-| 11 | [Nesne Algılama](./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 | [Anlamsal Bölütleme. 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) | |
+| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Defter](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Laboratuvar](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
+| 04 | [Çok Katmanlı Perceptron ve Kendi Çerçevemizi Oluşturma](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Defter](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Laboratuvar](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 05 | [Çerçeveye Giriş (PyTorch/TensorFlow) ve Aşırı Uydurma](./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) | [Laboratuvar](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
+| IV | [**Bilgisayarla Görü**](./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'da Bilgisayarla Görüyü Keşfedin](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
+| 06 | [Bilgisayarla Görmeye Giriş. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Defter](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Laboratuvar](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
+| 07 | [Konvolüsyonel Sinir Ağları](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN Mimarileri](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Laboratuvar](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
+| 08 | [Önceden Eğitilmiş Ağlar ve Transfer Öğrenimi](./lessons/4-ComputerVision/08-TransferLearning/README.md) ve [Eğitim Püf Noktaları](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Laboratuvar](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
+| 09 | [Otoenkoderler ve VAE'lar](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
+| 10 | [Üretici Çekişmeli Ağlar ve Sanatsal Stil Transferi](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
+| 11 | [Nesne Algılama](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Laboratuvar](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
+| 12 | [Semantik Segmentasyon. 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 | [**Doğal Dil İşleme**](./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 Azure'da Doğal Dil İşlemeyi Keşfedin](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Metin Temsili. 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 | [Anlamsal kelime gömme. Word2Vec ve 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 | [Dil Modelleme. Kendi gömmelerinizi eğitme](./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) |
+| 14 | [Anlamlı kelime gömme. Word2Vec ve 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 | [Dil Modelleme. Kendi gömmelerinizi eğitme](./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) | [Laboratuvar](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 16 | [Tekrarlayan Sinir Ağları](./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 | [Üretken Tekrarlayan Ağlar](./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 | [Adlandırılmış Varlık Tanıma](./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 | [Büyük Dil Modelleri, İpucu Programlama ve Az Örnekli Görevler](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| 17 | [Üretici Tekrarlayan Ağlar](./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) | [Laboratuvar](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
+| 18 | [Transformerlar. 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 | [Adlandırılmış Varlık Tanıma](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Laboratuvar](./lessons/5-NLP/19-NER/lab/README.md) |
+| 20 | [Büyük Dil Modelleri, İpucu Programlama ve Az Sayıda Örnek Görevler](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Diğer AI Teknikleri** || |
-| 21 | [Genetik Algoritmalar](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
-| 22 | [Derin Takviyeli Öğrenme](./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) |
+| 21 | [Genetik Algoritmalar](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Defter](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
+| 22 | [Derin Takviyeli Öğrenme](./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) | [Laboratuvar](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Çoklu Ajan Sistemleri](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
-| VII | **AI Etiği** | | |
-| 24 | [AI Etiği ve Sorumlu AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Sorumlu AI İlkeleri](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
+| VII | **AI Etikleri** | | |
+| 24 | [AI Etikleri ve Sorumlu AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Sorumlu AI İlkeleri](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
| IX | **Ekstralar** | | |
-| 25 | [Çok Modlu Ağlar, CLIP ve VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
+| 25 | [Çok Modlu Ağlar, CLIP ve VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Defter](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
-## Her ders şunları içerir
+## Her ders içerir
* Ön okuma materyali
-* Çoğunlukla çerçeveye özgü (**PyTorch** veya **TensorFlow**) çalıştırılabilir Jupyter Notebook’lar. Çalıştırılabilir notebook ayrıca çok fazla teorik materyal içerir; bu nedenle konuyu anlamak için en az bir versiyondan (PyTorch veya TensorFlow) geçmeniz gerekir.
-* Bazı konular için, öğrendiğiniz materyali belirli bir probleme uygulama fırsatı veren **laboratuvarlar**.
+* Çoğunlukla belirli bir çerçeveye özgü (**PyTorch** veya **TensorFlow**) yürütülebilir Jupyter Defterleri. Yürütülebilir defter aynı zamanda bol miktarda teorik materyal içerir, bu yüzden konuyu anlamak için defterin en az bir versiyonunu (PyTorch veya TensorFlow) incelemeniz gerekir.
+* Öğrendiğiniz materyali belirli bir probleme uygulama fırsatı veren bazı konular için mevcut **Laboratuvarlar**.
* Bazı bölümler, ilgili konuları kapsayan [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) modüllerine bağlantılar içerir.
## Başlarken
-### 🎯 AI’ya yeni misiniz? Buradan başlayın!
+### 🎯 Yapay Zekaya Yeni misiniz? Buradan Başlayın!
-Eğer yapay zekaya tamamen yeniseniz ve hızlı, uygulamalı örnekler arıyorsanız, [**Yeni Başlayanlar için Dostça Örnekler**](./examples/README.md) sayfamıza göz atın! Bunlar şunları içerir:
+Yapay Zeka konusunda tamamen yeniyse ve hızlı, uygulamalı örnekler istiyorsanız, [**Yeni Başlayanlar için Dostane Örnekler**](./examples/README.md) sayfamıza göz atın! Bunlar şunları içerir:
- 🌟 **Merhaba AI Dünyası** - İlk AI programınız (desen tanıma)
-- 🧠 **Basit Sinir Ağı** - Kendi sinir ağınızı baştan inşa edin
-- 🖼️ **Görüntü Sınıflandırıcı** - Detaylı yorumlarla görüntüleri sınıflandırın
-- 💬 **Metin Duygu Analizi** - Pozitif/negatif metni analiz etme
+- 🧠 **Basit Sinir Ağı** - Baştan bir sinir ağı inşa edin
-Bu örnekler, tam müfredata geçmeden önce AI kavramlarını anlamanıza yardımcı olmak için tasarlanmıştır.
+- 🖼️ **Görüntü Sınıflandırıcı** - Detaylı yorumlarla görüntüleri sınıflandırın
+- 💬 **Metin Duygu Analizi** - Pozitif/negatif metni analiz edin
+
+Bu örnekler, tam müfredata başlamadan önce yapay zeka kavramlarını anlamanıza yardımcı olacak şekilde tasarlanmıştır.
### 📚 Tam Müfredat Kurulumu
-- Geliştirme ortamınızı kurmanıza yardımcı olmak için bir [kurulum dersi](./lessons/0-course-setup/setup.md) oluşturduk. - Eğitmenler için de bir [müfredat kurulum dersi](./lessons/0-course-setup/for-teachers.md) hazırladık!
-- Kodu [VSCode veya Codespace'de nasıl çalıştıracağınızı](./lessons/0-course-setup/how-to-run.md) öğrenin
+- Geliştirme ortamınızı kurmanıza yardımcı olmak için bir [kurulum dersi](./lessons/0-course-setup/setup.md) oluşturduk. - Eğitimciler için de bir [müfredat kurulum dersi](./lessons/0-course-setup/for-teachers.md) hazırladık!
+- Kodun [VSCode veya Codespace'te nasıl çalıştırılacağı](./lessons/0-course-setup/how-to-run.md)
-Aşağıdaki adımları takip edin:
+Bu adımları izleyin:
-Depoyu çatallayın: Bu sayfanın sağ üst köşesindeki "Fork" düğmesine tıklayın.
+Depoyu Forklayın: Bu sayfanın sağ üst köşesindeki "Fork" düğmesine tıklayın.
-Depoyu klonlayın: `git clone https://github.com/microsoft/AI-For-Beginners.git`
+Depoyu Klonlayın: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-Daha sonra daha kolay bulabilmek için bu depoya yıldız (🌟) vermeyi unutmayın.
+Projeyi daha sonra kolayca bulmak için bu repoya yıldız (🌟) vermeyi unutmayın.
## Diğer Öğrenenlerle Tanışın
-Bu kursu alan diğer öğrenenlerle tanışmak ve iletişim kurmak, destek almak için [resmi AI Discord sunucumuza](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) katılın.
+Bu kursu alan diğer öğrenenlerle tanışmak ve destek almak için [resmi AI Discord sunucumuza](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) katılın.
-Ürün geri bildiriminiz veya sorularınız varsa, inşa ederken [Azure AI Foundry Geliştirici Forumu](https://aka.ms/foundry/forum)'nu ziyaret edin.
+Ürün geri bildiriminiz veya sorularınız varsa, inşa ederken [Azure AI Foundry Geliştirici Forumu](https://aka.ms/foundry/forum) ziyaret edin.
-## Quizler
+## Sınavlar
-> **Quizlerle ilgili bir not**: Tüm quizler Quiz-app klasörü içinde etc\quiz-app dizininde ya da [Çevrimiçi Burada](https://ff-quizzes.netlify.app/) bulunur. Quizler dersler içinde bağlantılıdır, quiz uygulaması yerel olarak çalıştırılabilir veya Azure’a dağıtılabilir; `quiz-app` klasöründeki talimatları takip edin. Quizler kademeli olarak yerelleştirilmektedir.
+> **Sınavlarla ilgili bir not**: Tüm sınavlar etc\quiz-app içindeki Quiz-app klasöründe veya [Çevrimiçi Burada](https://ff-quizzes.netlify.app/) bulunmaktadır. Derslerden bağlantı verilmiştir, quiz uygulaması yerel olarak çalıştırılabilir veya Azure’a dağıtılabilir; talimatlar `quiz-app` klasöründedir. Kademeli olarak yerelleştirilmektedir.
## Yardım İsteniyor
-Önerileriniz veya yazım ya da kod hataları bulduysanız, bir issue açın veya bir pull request oluşturun.
+Önerileriniz veya yazım ya da kod hataları buldunuz mu? Bir issue açın veya pull request oluşturun.
-## Özel Teşekkür
+## Özel Teşekkürler
-* **✍️ Birincil Yazar:** [Dmitry Soshnikov](http://soshnikov.com), PhD
+* **✍️ Ana Yazar:** [Dmitry Soshnikov](http://soshnikov.com), PhD
* **🔥 Editör:** [Jen Looper](https://twitter.com/jenlooper), PhD
-* **🎨 Sketchnote illüstratörü:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **🎨 Sketchnote çizeri:** [Tomomi Imura](https://twitter.com/girlie_mac)
* **✅ Quiz Oluşturucu:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
* **🙏 Ana Katkıda Bulunanlar:** [Evgenii Pishchik](https://github.com/Pe4enIks)
## Diğer Müfredatlar
-Ekibimiz diğer müfredatlar da hazırlıyor! Göz atın:
+Ekibimiz başka müfredatlar da üretiyor! Göz atın:
### LangChain
@@ -198,36 +190,36 @@ Ekibimiz diğer müfredatlar da hazırlıyor! Göz atın:
---
-### Temel Öğrenim
+### Temel Öğrenme
[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
---
### Copilot Serisi
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
## Yardım Alma
-Takıldığınızda ya da AI uygulamaları geliştirme ile ilgili sorularınız olduğunda, MCP hakkında diğer öğrenenler ve deneyimli geliştiricilerle tartışmalara katılın. Soruların memnuniyetle karşılandığı ve bilginin özgürce paylaşıldığı destekleyici bir topluluktur.
+Yapay zeka uygulamaları geliştirirken takılırsanız veya sorularınız olursa. MCP hakkında deneyimli geliştiriciler ve diğer öğrenenlerle tartışmalara katılın. Burası soruların hoş karşılandığı ve bilginin özgürce paylaşıldığı destekleyici bir topluluktur.
[](https://discord.gg/nTYy5BXMWG)
-Ürün geri bildiriminiz veya inşaat sırasında hatalar varsa şurayı ziyaret edin:
+Ürün geri bildiriminiz veya oluşan hatalarda:
-[](https://aka.ms/foundry/forum)
+[](https://aka.ms/foundry/forum) ziyaret edin.
---
**Feragatname**:
-Bu belge, AI çeviri hizmeti [Co-op Translator](https://github.com/Azure/co-op-translator) kullanılarak çevrilmiştir. Doğruluk için çaba göstermemize rağmen, otomatik çevirilerin hatalar veya yanlışlıklar içerebileceğini lütfen unutmayınız. Orijinal belge, asıl dilinde yetkili kaynak olarak kabul edilmelidir. Kritik bilgiler için profesyonel insan çevirisi önerilir. Bu çevirinin kullanımı sonucunda oluşabilecek herhangi bir yanlış anlama veya yorum hatasından sorumlu değiliz.
+Bu belge, AI çeviri hizmeti [Co-op Translator](https://github.com/Azure/co-op-translator) kullanılarak çevrilmiştir. Doğruluk için çaba göstersek de, otomatik çevirilerin hata veya yanlışlık içerebileceğini lütfen unutmayınız. Orijinal belge, kendi dilinde yetkili kaynak olarak kabul edilmelidir. Kritik bilgiler için profesyonel insan çevirisi önerilir. Bu çevirinin kullanımından kaynaklanan yanlış anlamalar veya yanlış yorumlamalardan dolayı sorumluluk kabul edilmemektedir.
\ No newline at end of file
diff --git a/translations/tr/SECURITY.md b/translations/tr/SECURITY.md
index f5135bac..cb4939e7 100644
--- a/translations/tr/SECURITY.md
+++ b/translations/tr/SECURITY.md
@@ -1,12 +1,3 @@
-
## Güvenlik
Microsoft, yazılım ürünlerimizin ve hizmetlerimizin güvenliğini ciddiye alır. Bu, [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) ve [diğer GitHub organizasyonlarımız](https://opensource.microsoft.com/) gibi GitHub organizasyonlarımız aracılığıyla yönetilen tüm kaynak kodu depolarını da kapsar.
diff --git a/translations/tr/etc/CODE_OF_CONDUCT.md b/translations/tr/etc/CODE_OF_CONDUCT.md
index 2535f912..f9c09fef 100644
--- a/translations/tr/etc/CODE_OF_CONDUCT.md
+++ b/translations/tr/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Microsoft Açık Kaynak Davranış Kuralları
Bu proje, [Microsoft Açık Kaynak Davranış Kuralları](https://opensource.microsoft.com/codeofconduct/) benimsemiştir.
diff --git a/translations/tr/etc/CONTRIBUTING.md b/translations/tr/etc/CONTRIBUTING.md
index 0879d585..84abdace 100644
--- a/translations/tr/etc/CONTRIBUTING.md
+++ b/translations/tr/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Katkıda Bulunma
Bu proje katkılara ve önerilere açıktır. Çoğu katkı, bir Katkıda Bulunma Lisans Sözleşmesi'ni (CLA) kabul etmenizi gerektirir. Bu sözleşme, katkınızı kullanma hakkını bize verdiğinizi ve bu hakkı gerçekten sağladığınızı beyan eder. Ayrıntılar için https://cla.microsoft.com adresini ziyaret edebilirsiniz.
diff --git a/translations/tr/etc/Mindmap.md b/translations/tr/etc/Mindmap.md
index 77b2c57e..d60f5532 100644
--- a/translations/tr/etc/Mindmap.md
+++ b/translations/tr/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# Yapay Zeka
## [Yapay Zekaya Giriş](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/tr/etc/SUPPORT.md b/translations/tr/etc/SUPPORT.md
index 66f1caa6..1633b572 100644
--- a/translations/tr/etc/SUPPORT.md
+++ b/translations/tr/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Destek
## Sorunları bildirme ve yardım alma
diff --git a/translations/tr/etc/TRANSLATIONS.md b/translations/tr/etc/TRANSLATIONS.md
index 8f1eb627..efc53f74 100644
--- a/translations/tr/etc/TRANSLATIONS.md
+++ b/translations/tr/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Dersleri Çevirerek Katkıda Bulunun
Bu müfredattaki derslerin çevirilerini memnuniyetle karşılıyoruz!
diff --git a/translations/tr/etc/quiz-app/README.md b/translations/tr/etc/quiz-app/README.md
index 06bfab42..d5a7fb24 100644
--- a/translations/tr/etc/quiz-app/README.md
+++ b/translations/tr/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Quizler
Bu quizler, https://aka.ms/ai-beginners adresindeki AI müfredatının ders öncesi ve sonrası quizleridir.
diff --git a/translations/tr/examples/README.md b/translations/tr/examples/README.md
index 1c3ad5bf..32a52f53 100644
--- a/translations/tr/examples/README.md
+++ b/translations/tr/examples/README.md
@@ -1,12 +1,3 @@
-
# Yeni Başlayanlar İçin AI Örnekleri
Hoş geldiniz! Bu dizin, yapay zeka ve makine öğrenimine başlamak için basit, bağımsız örnekler içerir. Her örnek, ayrıntılı yorumlar ve adım adım açıklamalarla yeni başlayanlar için uygun şekilde tasarlanmıştır.
diff --git a/translations/tr/lessons/0-course-setup/for-teachers.md b/translations/tr/lessons/0-course-setup/for-teachers.md
index 154cd5d6..95834176 100644
--- a/translations/tr/lessons/0-course-setup/for-teachers.md
+++ b/translations/tr/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# Eğitimciler İçin
Bu müfredatı sınıfınızda kullanmak ister misiniz? Lütfen çekinmeden kullanın!
diff --git a/translations/tr/lessons/0-course-setup/how-to-run.md b/translations/tr/lessons/0-course-setup/how-to-run.md
index 8855ffa3..c0e33cd5 100644
--- a/translations/tr/lessons/0-course-setup/how-to-run.md
+++ b/translations/tr/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Kodu Çalıştırma
Bu müfredat, çalıştırmak isteyebileceğiniz birçok yürütülebilir örnek ve laboratuvar içerir. Bunu yapmak için, bu müfredatın parçası olarak sağlanan Jupyter Not defterlerinde Python kodu çalıştırma yeteneğine ihtiyacınız vardır. Kodu çalıştırmak için birkaç seçeneğiniz vardır:
diff --git a/translations/tr/lessons/0-course-setup/setup.md b/translations/tr/lessons/0-course-setup/setup.md
index de5b13b3..2d2bca84 100644
--- a/translations/tr/lessons/0-course-setup/setup.md
+++ b/translations/tr/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Bu Müfredatla Başlarken
## Öğrenci misiniz?
diff --git a/translations/tr/lessons/1-Intro/README.md b/translations/tr/lessons/1-Intro/README.md
index c4e28118..f74eb2d5 100644
--- a/translations/tr/lessons/1-Intro/README.md
+++ b/translations/tr/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Yapay Zekaya Giriş
diff --git a/translations/tr/lessons/1-Intro/assignment.md b/translations/tr/lessons/1-Intro/assignment.md
index 07518307..16cde994 100644
--- a/translations/tr/lessons/1-Intro/assignment.md
+++ b/translations/tr/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Oyun Maratonu
Oyunlar, yapay zeka (AI) ve makine öğrenimi (ML) gelişmelerinden büyük ölçüde etkilenmiş bir alandır. Bu ödevde, yapay zekanın evrimiyle şekillenmiş bir oyun hakkında kısa bir makale yazın. Seçtiğiniz oyun, birden fazla bilgisayar işlem sistemi türünden etkilenmiş kadar eski bir oyun olmalıdır. İyi bir örnek Satranç veya Go olabilir, ancak Pong ya da Pac-Man gibi video oyunlarına da göz atabilirsiniz. Oyunun geçmişini, bugününü ve yapay zeka ile geleceğini tartışan bir makale yazın.
diff --git a/translations/tr/lessons/2-Symbolic/README.md b/translations/tr/lessons/2-Symbolic/README.md
index 3db3a3a8..531e6d61 100644
--- a/translations/tr/lessons/2-Symbolic/README.md
+++ b/translations/tr/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Bilgi Temsili ve Uzman Sistemler
-
+
> Sketchnote [Tomomi Imura](https://twitter.com/girlie_mac) tarafından
@@ -41,7 +32,7 @@ Sembolik AI'deki önemli kavramlardan biri **bilgidir**. Bilgiyi *bilgi* veya *v
Böylece, **bilgi temsili** problemi, bilgiyi otomatik olarak kullanılabilir hale getirmek için bilgisayar içinde etkili bir şekilde veri formunda temsil etme yollarını bulmaktır. Bu bir spektrum olarak görülebilir:
-
+
> Görsel [Dmitry Soshnikov](http://soshnikov.com) tarafından
@@ -94,7 +85,7 @@ Block Syntax | Indent | | |
Sembolik AI'nin erken başarılarından biri olan **uzman sistemler**, sınırlı problem alanında bir uzman gibi davranmak üzere tasarlanmış bilgisayar sistemleridir. Bir veya daha fazla insan uzmandan çıkartılmış bir **bilgi tabanına** dayanır ve bunun üzerinde bazı akıl yürütme yapan bir **çıkarım motoruna** sahiptir.
- | 
+ | 
---------------------------------------------|------------------------------------------------
İnsan sinir sisteminin sadeleştirilmiş yapısı | Bilgi tabanlı sistem mimarisi
@@ -106,7 +97,7 @@ Uzman sistemler, kısa dönem ve uzun dönem bellek içeren insan akıl yürütm
Örnek olarak, bir hayvanın fiziksel özelliklerine dayanarak tanımlandığı aşağıdaki uzman sistemi düşünelim:
-
+
> Görsel [Dmitry Soshnikov](http://soshnikov.com) tarafından
diff --git a/translations/tr/lessons/2-Symbolic/assignment.md b/translations/tr/lessons/2-Symbolic/assignment.md
index b5b8307b..129d544c 100644
--- a/translations/tr/lessons/2-Symbolic/assignment.md
+++ b/translations/tr/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Bir Ontoloji Oluşturun
Bir bilgi tabanı oluşturmak, bir konuyla ilgili gerçekleri temsil eden bir modeli kategorize etmekle ilgilidir. Bir konu seçin - bir kişi, bir yer veya bir şey gibi - ve ardından o konunun bir modelini oluşturun. Bu derste açıklanan bazı teknikleri ve model oluşturma stratejilerini kullanın. Örneğin, mobilyalar, ışıklar ve benzeri şeylerle bir oturma odasının ontolojisini oluşturmak olabilir. Oturma odası, mutfaktan nasıl farklıdır? Banyodan? Bunun bir oturma odası olduğunu ve bir yemek odası olmadığını nasıl anlarsınız? Ontolojinizi oluşturmak için [Protégé](https://protege.stanford.edu/) kullanın.
diff --git a/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/README.md
index 58e9d1a7..b826928c 100644
--- a/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Sinir Ağlarına Giriş: Perceptron
## [Ders Öncesi Testi](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ Modern sinir ağına benzer bir şeyin ilk uygulama girişimlerinden biri, 1957
| | |
|--------------|-----------|
-| | |
+|
| 
|
> Görseller [Wikipedia'dan](https://en.wikipedia.org/wiki/Perceptron)
@@ -34,7 +25,7 @@ y(x) = f(wTx)
burada f bir adım aktivasyon fonksiyonudur.
-
+
## Perceptron Eğitimi
diff --git a/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index e2a55dff..4aa59738 100644
--- a/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Perceptron ile Çok Sınıflı Sınıflandırma
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) ders planından Laboratuvar Çalışması.
diff --git a/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index 55c56f7e..cf3decd0 100644
--- a/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Sinir Ağlarına Giriş. Çok Katmanlı Perceptron
Önceki bölümde, en basit sinir ağı modeli olan tek katmanlı perceptron, yani doğrusal iki sınıflı sınıflandırma modelini öğrendiniz.
@@ -65,7 +56,7 @@ Gradyan inişi algoritması aynı kalır, ancak gradyanları hesaplamak daha zor
Dikkat edin, bu ifadelerin en sol kısmı aynıdır ve bu nedenle türevleri etkili bir şekilde kayıp fonksiyonundan başlayarak "geri" doğru hesaplayabiliriz. Bu nedenle, çok katmanlı perceptron eğitme yöntemi **geri yayılım** veya 'backprop' olarak adlandırılır.
-
+
> TODO: görsel kaynağı
diff --git a/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 995eb167..f57c82bb 100644
--- a/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# MNIST Sınıflandırması Kendi Çerçevemizle
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) içindeki Lab Görevi.
diff --git a/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/README.md
index 5a55f7e8..0ebaae77 100644
--- a/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Sinir Ağı Çerçeveleri
Daha önce öğrendiğimiz gibi, sinir ağlarını verimli bir şekilde eğitebilmek için iki şeyi yapmamız gerekiyor:
diff --git a/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index 9dd3443e..a3e42f02 100644
--- a/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# PyTorch/TensorFlow ile Sınıflandırma
[AI for Beginners Müfredatı](https://github.com/microsoft/ai-for-beginners) tarafından hazırlanan Lab Görevi.
diff --git a/translations/tr/lessons/3-NeuralNetworks/README.md b/translations/tr/lessons/3-NeuralNetworks/README.md
index af243e60..ca6f805f 100644
--- a/translations/tr/lessons/3-NeuralNetworks/README.md
+++ b/translations/tr/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Sinir Ağlarına Giriş
diff --git a/translations/tr/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/tr/lessons/4-ComputerVision/06-IntroCV/README.md
index cb0982b4..fdfe27c8 100644
--- a/translations/tr/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/tr/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Bilgisayarlı Görüye Giriş
[Bilgisayarlı Görü](https://wikipedia.org/wiki/Computer_vision), bilgisayarların dijital görüntüleri yüksek seviyede anlamasını sağlamayı amaçlayan bir disiplindir. Bu oldukça geniş bir tanımdır çünkü *anlama* birçok farklı şeyi ifade edebilir; bir resimdeki nesneyi bulmak (**nesne tespiti**), ne olduğunu anlamak (**olay tespiti**), bir resmi metinle açıklamak veya bir sahneyi 3D olarak yeniden oluşturmak gibi. İnsan görüntüleriyle ilgili özel görevler de vardır: yaş ve duygu tahmini, yüz tespiti ve tanımlama, 3D duruş tahmini gibi.
@@ -115,7 +106,7 @@ Optik akış hakkında daha fazla bilgi edinmek için [bu harika eğitimi](https
Bu laboratuvarda, basit jestlerle bir video çekeceksiniz ve amacınız optik akış kullanarak yukarı/aşağı/sol/sağ hareketlerini çıkarmaktır.
-
+
---
diff --git a/translations/tr/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/tr/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 0f77ea02..809772e7 100644
--- a/translations/tr/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/tr/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Optik Akış Kullanarak Hareketleri Tespit Etme
[AI for Beginners Curriculum](https://aka.ms/ai-beginners) müfredatından bir laboratuvar ödevi.
diff --git a/translations/tr/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/tr/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 5c58b41d..8fd47b59 100644
--- a/translations/tr/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/tr/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Bilinen CNN Mimarileri
### VGG-16
@@ -25,7 +16,7 @@ Gördüğünüz gibi, VGG geleneksel bir piramit mimarisini takip eder; bu, bir
ResNet, 2015 yılında Microsoft Research tarafından önerilen bir model ailesidir. ResNet'in ana fikri **artık blokları** kullanmaktır:
-
+
> Görsel [bu makaleden](https://arxiv.org/pdf/1512.03385.pdf) alınmıştır.
@@ -37,7 +28,7 @@ Bu ağı, veri setine göre karmaşıklığını ayarlayabilen bir yapı olarak
Google Inception mimarisi bu fikri bir adım ileri taşır ve her ağ katmanını birkaç farklı yolun birleşimi olarak oluşturur:
-
+
> Görsel [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) kaynağından alınmıştır.
diff --git a/translations/tr/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/tr/lessons/4-ComputerVision/07-ConvNets/README.md
index 11c7fbbf..c4f4f1f3 100644
--- a/translations/tr/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/tr/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Evrişimsel Sinir Ağları
Daha önce sinir ağlarının görüntülerle oldukça iyi başa çıktığını görmüştük; hatta tek katmanlı bir algılayıcı bile MNIST veri setindeki el yazısı rakamları makul bir doğrulukla tanıyabiliyor. Ancak, MNIST veri seti oldukça özeldir ve tüm rakamlar görüntünün ortasına hizalanmıştır, bu da görevi daha basit hale getirir.
@@ -24,7 +15,7 @@ Desenleri çıkarmak için **evrişimsel filtreler** kavramını kullanacağız.
Örneğin, MNIST rakamlarına 3x3 boyutunda dikey kenar ve yatay kenar filtreleri uygularsak, orijinal görüntümüzde dikey ve yatay kenarların olduğu yerlerde vurgular (örneğin, yüksek değerler) elde edebiliriz. Bu nedenle, bu iki filtre "kenarları aramak" için kullanılabilir. Benzer şekilde, diğer düşük seviyeli desenleri aramak için farklı filtreler tasarlayabiliriz:
-
+
> Görsel: [Leung-Malik Filtre Bankası](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/tr/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/tr/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index 10d0ace8..37f4a04c 100644
--- a/translations/tr/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/tr/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Evcil Hayvan Yüzlerinin Sınıflandırılması
[AI for Beginners Müfredatı](https://github.com/microsoft/ai-for-beginners) kapsamında bir laboratuvar görevi.
diff --git a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/README.md
index 6ed0428a..91af3263 100644
--- a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Önceden Eğitilmiş Ağlar ve Transfer Öğrenimi
CNN'leri eğitmek oldukça zaman alabilir ve bu görev için çok fazla veri gereklidir. Ancak, bu sürenin büyük bir kısmı, bir ağın görüntülerden desenler çıkarmak için kullanabileceği en iyi düşük seviyeli filtreleri öğrenmekle geçer. Doğal olarak şu soru ortaya çıkar: Bir veri kümesinde eğitilmiş bir sinir ağını alıp, tamamen yeni bir eğitim sürecine gerek kalmadan farklı görüntüleri sınıflandırmak için uyarlayabilir miyiz?
diff --git a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 9a670c83..500efaf4 100644
--- a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Derin Öğrenme Eğitim İpuçları
Sinir ağları derinleştikçe, bu ağların eğitimi daha da zorlaşır. Ana sorunlardan biri, [kaybolan gradyanlar](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) veya [patlayan gradyanlar](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.) olarak adlandırılan problemdir. [Bu yazı](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11), bu sorunlara iyi bir giriş sağlar.
diff --git a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index b2708121..2e35a50e 100644
--- a/translations/tr/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/tr/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Oxford Evcil Hayvanlarının Transfer Öğrenimi ile Sınıflandırılması
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) kapsamında bir laboratuvar görevi.
diff --git a/translations/tr/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/tr/lessons/4-ComputerVision/09-Autoencoders/README.md
index 6bab3cc1..228e0c50 100644
--- a/translations/tr/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/tr/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Otomatik Kodlayıcılar
CNN'leri eğitirken karşılaşılan sorunlardan biri, çok fazla etiketlenmiş veriye ihtiyaç duymamızdır. Görüntü sınıflandırma durumunda, görüntüleri farklı sınıflara ayırmamız gerekir ve bu manuel bir çabadır.
@@ -46,7 +37,7 @@ VAE, gizli parametrelerin *istatistiksel dağılımını* tahmin etmeyi öğrene
* N(zmean,exp(zlog\_sigma)) dağılımından `sample` adlı bir vektör örneklenir
* Kod çözücü, `sample` vektörünü giriş olarak kullanarak orijinal görüntüyü çözmeye çalışır
-
+ 
> Görsel [bu blog yazısından](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) Isaak Dykeman tarafından
@@ -57,13 +48,13 @@ Varyasyonel otomatik kodlayıcılar, iki bölümden oluşan karmaşık bir kayı
VAE'lerin önemli bir avantajı, yeni görüntüleri nispeten kolay bir şekilde oluşturabilmemize olanak tanımasıdır, çünkü gizli vektörlerin örnekleneceği dağılımı biliriz. Örneğin, MNIST üzerinde 2D gizli vektörle VAE eğitirsek, gizli vektörün bileşenlerini değiştirerek farklı rakamlar elde edebiliriz:
-
+
> Görsel [Dmitry Soshnikov](http://soshnikov.com) tarafından
Gizli parametre uzayının farklı bölümlerinden gizli vektörler almaya başladıkça, görüntülerin birbirine nasıl karıştığını gözlemleyin. Bu uzayı ayrıca 2D olarak görselleştirebiliriz:
-
+
> Görsel [Dmitry Soshnikov](http://soshnikov.com) tarafından
diff --git a/translations/tr/lessons/4-ComputerVision/10-GANs/README.md b/translations/tr/lessons/4-ComputerVision/10-GANs/README.md
index c3253048..34c96d90 100644
--- a/translations/tr/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/tr/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Üretici Çekişmeli Ağlar
Önceki bölümde **üretici modelleri** öğrendik: eğitim veri setindeki görüntülere benzer yeni görüntüler üretebilen modeller. VAE, üretici model için iyi bir örnekti.
@@ -17,7 +8,7 @@ Ancak, VAE ile makul bir çözünürlükte anlamlı bir şey, örneğin bir tabl
GAN'ın temel fikri, birbirine karşı eğitilecek iki sinir ağına sahip olmaktır:
-
+
> Görsel: [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ Bir CNN ayırt edici şu katmanlardan oluşur: birkaç konvolüsyon+havuzlama (a
> ✅ Konvolüsyon katmanı bir görüntü üzerinde doğrusal bir filtre olarak uygulandığından, dekonvolüsyon temelde konvolüsyona benzer ve aynı katman mantığı kullanılarak uygulanabilir.
-
+
> Görsel: [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/README.md
index d7f4a0ef..6fc617c4 100644
--- a/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Nesne Tespiti
Bugüne kadar ele aldığımız görüntü sınıflandırma modelleri, bir görüntüyü alıp MNIST problemindeki 'sayı' sınıfı gibi kategorik bir sonuç üretiyordu. Ancak, birçok durumda bir resmin nesneleri tasvir ettiğini bilmek yeterli değildir - nesnelerin tam konumlarını belirlemek isteriz. İşte **nesne tespiti** tam olarak bu noktada devreye girer.
diff --git a/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index a9da85e7..a1dc3abf 100644
--- a/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/tr/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Hollywood Heads Veri Seti Kullanarak Kafa Tespiti
[AI for Beginners Müfredatı](https://github.com/microsoft/ai-for-beginners) kapsamında bir laboratuvar çalışması.
diff --git a/translations/tr/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/tr/lessons/4-ComputerVision/12-Segmentation/README.md
index 7b44ed48..38622f60 100644
--- a/translations/tr/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/tr/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Segmentasyon
Daha önce, nesneleri *sınır kutuları* tahmin ederek görüntüde bulmamıza olanak tanıyan Nesne Tespiti hakkında bilgi edinmiştik. Ancak, bazı görevlerde yalnızca sınır kutularına değil, daha hassas nesne konumlandırmasına da ihtiyacımız olabilir. Bu görev **segmentasyon** olarak adlandırılır.
@@ -20,7 +11,7 @@ Segmentasyon, **piksel sınıflandırması** olarak görülebilir; burada görü
Örneğin örnek segmentasyonunda bu koyunlar farklı nesneler olarak kabul edilir, ancak semantik segmentasyonda tüm koyunlar tek bir sınıf olarak temsil edilir.
-
+
> Görsel [bu blog yazısından](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) alınmıştır.
@@ -29,7 +20,7 @@ Segmentasyon için farklı sinir ağları mimarileri vardır, ancak hepsi aynı
* **Kodlayıcı**, giriş görüntüsünden özellikler çıkarır.
* **Kod Çözücü**, bu özellikleri sınıfların sayısına karşılık gelen aynı boyutta ve kanallara sahip bir **maske görüntüsüne** dönüştürür.
-
+
> Görsel [bu yayından](https://arxiv.org/pdf/2001.05566.pdf) alınmıştır.
@@ -43,7 +34,7 @@ Bu derste, tıbbi görüntülerde insan nevilerini (ben olarak da bilinir) tanı
> ✅ Bu teknik özellikle bu tür tıbbi görüntüleme için uygundur, ancak başka hangi gerçek dünya uygulamalarını hayal edebilirsiniz?
-
+
> Görsel PH2 Veritabanından alınmıştır.
diff --git a/translations/tr/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/tr/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index 037fec5e..e35a2ab1 100644
--- a/translations/tr/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/tr/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# İnsan Vücudu Segmentasyonu
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) kapsamında bir laboratuvar ödevi.
diff --git a/translations/tr/lessons/4-ComputerVision/README.md b/translations/tr/lessons/4-ComputerVision/README.md
index c783514e..ff291f40 100644
--- a/translations/tr/lessons/4-ComputerVision/README.md
+++ b/translations/tr/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Bilgisayarlı Görü
diff --git a/translations/tr/lessons/5-NLP/13-TextRep/README.md b/translations/tr/lessons/5-NLP/13-TextRep/README.md
index bdf5ca28..0f8b8807 100644
--- a/translations/tr/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/tr/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Metni Tensörler Olarak Temsil Etmek
## [Ders Öncesi Testi](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ Amacımız, metne dayanarak haber öğesini kategorilerden birine sınıflandır
Doğal Dil İşleme (NLP) görevlerini sinir ağlarıyla çözmek istiyorsak, metni tensörler olarak temsil etmenin bir yoluna ihtiyacımız var. Bilgisayarlar zaten metinsel karakterleri, ekranınızdaki yazı tiplerine eşleyen ASCII veya UTF-8 gibi kodlamalar kullanarak sayılarla temsil eder.
-
+
> [Görsel kaynağı](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ Bazı durumlarda, üç kelimeden oluşan tri-gramlar kullanmayı düşünebiliri
Metin sınıflandırma gibi görevleri çözerken, metni sabit boyutlu bir vektörle temsil edebilmemiz gerekir. Bu vektörü, son yoğun sınıflandırıcıya giriş olarak kullanacağız. Bunu yapmanın en basit yollarından biri, tüm bireysel kelime temsillerini birleştirmek, örneğin onları toplayarak. Her kelimenin tek sıcak kodlamalarını toplarsak, metin içinde her kelimenin kaç kez göründüğünü gösteren bir frekans vektörü elde ederiz. Bu tür bir metin temsili **kelime torbası** (BoW) olarak adlandırılır.
-
+
> Görsel yazar tarafından oluşturulmuştur
diff --git a/translations/tr/lessons/5-NLP/13-TextRep/assignment.md b/translations/tr/lessons/5-NLP/13-TextRep/assignment.md
index 45937d58..42eb9ef2 100644
--- a/translations/tr/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/tr/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Ödev: Not Defterleri
Bu derse ait not defterlerini (PyTorch veya TensorFlow versiyonlarından birini) kullanarak, kendi veri setinizle yeniden çalıştırın. Örneğin, Kaggle'dan bir veri seti alabilir ve uygun şekilde kaynak belirterek kullanabilirsiniz. Kendi bulgularınızı vurgulamak için not defterini yeniden yazın. Sürpriz olabilecek yenilikçi veri setlerini denemeyi düşünün, örneğin NUFORC'un [UFO gözlemleri hakkında olan bu veri seti](https://www.kaggle.com/datasets/NUFORC/ufo-sightings).
diff --git a/translations/tr/lessons/5-NLP/14-Embeddings/README.md b/translations/tr/lessons/5-NLP/14-Embeddings/README.md
index 108c9469..50230ac5 100644
--- a/translations/tr/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/tr/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Gömülü Temsiller
## [Ders Öncesi Test](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/tr/lessons/5-NLP/14-Embeddings/assignment.md b/translations/tr/lessons/5-NLP/14-Embeddings/assignment.md
index 474fc196..f7b30ceb 100644
--- a/translations/tr/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/tr/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Ödev: Not Defterleri
Bu derse ait not defterlerini (PyTorch veya TensorFlow versiyonlarından birini) kullanarak, kendi veri setinizle yeniden çalıştırın. Örneğin, Kaggle'dan bir veri seti alabilir ve uygun şekilde kaynak belirterek kullanabilirsiniz. Not defterini kendi bulgularınızı vurgulayacak şekilde yeniden yazın. Farklı bir tür veri seti deneyin ve bulgularınızı belgeleyin, [bu Beatles şarkı sözleri](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics) gibi metinler kullanarak.
diff --git a/translations/tr/lessons/5-NLP/15-LanguageModeling/README.md b/translations/tr/lessons/5-NLP/15-LanguageModeling/README.md
index 9ebbd624..37bd39da 100644
--- a/translations/tr/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/tr/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Dil Modellemesi
Word2Vec ve GloVe gibi anlamsal gömmeler aslında **dil modellemesi**ne doğru atılmış ilk adımlardır - dilin doğasını bir şekilde *anlayan* (veya *temsil eden*) modeller oluşturmak.
diff --git a/translations/tr/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/tr/lessons/5-NLP/15-LanguageModeling/lab/README.md
index 773b7f0d..ceae1259 100644
--- a/translations/tr/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/tr/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Skip-Gram Modelini Eğitme
[AI for Beginners Müfredatı](https://github.com/microsoft/ai-for-beginners) tarafından hazırlanan laboratuvar ödevi.
diff --git a/translations/tr/lessons/5-NLP/16-RNN/README.md b/translations/tr/lessons/5-NLP/16-RNN/README.md
index 519b19f9..436ff641 100644
--- a/translations/tr/lessons/5-NLP/16-RNN/README.md
+++ b/translations/tr/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Tekrarlayan Sinir Ağları
## [Ders Öncesi Quiz](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ Basit bir RNN hücresinin nasıl organize edildiğini görelim. Önceki durum S<
Basit bir RNN hücresinin içinde iki ağırlık matrisi vardır: biri bir giriş sembolünü dönüştürür (buna W diyelim), diğeri ise bir giriş durumunu dönüştürür (H). Bu durumda ağın çıktısı σ(W×Xi+H×Si-1+b) olarak hesaplanır, burada σ aktivasyon fonksiyonu ve b ek bir bias'tır.
-
+
> Görsel yazar tarafından oluşturulmuştur
diff --git a/translations/tr/lessons/5-NLP/16-RNN/assignment.md b/translations/tr/lessons/5-NLP/16-RNN/assignment.md
index 3abb8f35..20357738 100644
--- a/translations/tr/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/tr/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Ödev: Not Defterleri
Bu derse ait not defterlerini (PyTorch veya TensorFlow versiyonlarından birini) kullanarak, kendi veri setinizle yeniden çalıştırın. Örneğin, Kaggle'dan bir veri seti alabilir ve uygun şekilde kaynak belirterek kullanabilirsiniz. Not defterini kendi bulgularınızı vurgulayacak şekilde yeniden yazın. Farklı bir tür veri seti deneyin ve bulgularınızı belgeleyin, örneğin [bu hava durumu tweetleriyle ilgili Kaggle yarışması veri seti](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv) gibi.
diff --git a/translations/tr/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/tr/lessons/5-NLP/17-GenerativeNetworks/README.md
index d3a0f143..9913e3c0 100644
--- a/translations/tr/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/tr/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Üretici Ağlar
## [Ders Öncesi Test](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ Bu RNN'yi adım adım metin üretmek için eğiteceğiz. Her adımda, `nchars` u
Metin üretirken (çıkarsama sırasında), bazı **başlangıç** verileriyle başlarız. Bu veri RNN hücrelerinden geçirilerek ara durumu oluşturur ve ardından üretim başlar. Her seferinde bir karakter üretiriz ve durumu ve üretilen karakteri bir sonraki karakteri üretmek için başka bir RNN hücresine geçiririz. Bu işlem yeterli sayıda karakter üretilene kadar devam eder.
-
+
> Resim, yazar tarafından oluşturulmuştur.
diff --git a/translations/tr/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/tr/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index aaae6b63..9800ccba 100644
--- a/translations/tr/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/tr/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Kelime Düzeyinde Metin Üretimi RNN'ler Kullanılarak
[AI for Beginners Müfredatı](https://github.com/microsoft/ai-for-beginners) kapsamında bir laboratuvar çalışması.
diff --git a/translations/tr/lessons/5-NLP/18-Transformers/README.md b/translations/tr/lessons/5-NLP/18-Transformers/README.md
index 9ba0e555..49804045 100644
--- a/translations/tr/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/tr/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Dikkat Mekanizmaları ve Transformerlar
## [Ders Öncesi Test](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ Pozisyonel kodlama fikri şu şekildedir:
* Token gömmeye benzer şekilde eğitilebilir gömme. Burada bu yaklaşımı ele alıyoruz. Hem tokenlar hem de pozisyonları üzerinde gömme katmanları uygularız, aynı boyutlarda gömme vektörleri elde ederiz ve bunları toplarız.
* Orijinal makalede önerildiği gibi sabit pozisyon kodlama fonksiyonu.
-
+
> Görsel yazar tarafından oluşturulmuştur.
diff --git a/translations/tr/lessons/5-NLP/18-Transformers/READMEtransformers.md b/translations/tr/lessons/5-NLP/18-Transformers/READMEtransformers.md
deleted file mode 100644
index ac204c85..00000000
--- a/translations/tr/lessons/5-NLP/18-Transformers/READMEtransformers.md
+++ /dev/null
@@ -1,112 +0,0 @@
-# Dikkat Mekanizmaları ve Transformerlar
-
-## [Ders öncesi quiz](https://ff-quizzes.netlify.app/en/ai/quiz/35)
-
-NLP alanındaki en önemli problemlerden biri **makine çevirisi**dir; bu, Google Translate gibi araçların temelini oluşturan önemli bir görevdir. Bu bölümde, makine çevirisine, daha genel olarak ise herhangi bir *dizi-dizi* görevine (bu göreve **cümle dönüştürme** de denir) odaklanacağız.
-
-RNN'lerle, dizi-dizi işlemi, bir giriş dizisini gizli bir duruma dönüştüren **kodlayıcı** adındaki bir ağ ile bu gizli durumu çevrilmiş bir sonuca açan **çözücü** adındaki başka bir ağdan oluşan iki tekrarlayan ağ ile gerçekleştirilir. Bu yaklaşımda birkaç problem bulunmaktadır:
-
-* Kodlayıcı ağın son durumu, bir cümlenin başını hatırlamakta zorlanır, bu da uzun cümleler için modelin kalitesini düşürür.
-* Bir dizideki tüm kelimelerin sonuca olan etkisi aynıdır. Ancak gerçekte, giriş dizisindeki belirli kelimeler, sıralı çıktılar üzerinde diğerlerinden daha fazla etkiye sahiptir.
-
-**Dikkat Mekanizmaları**, RNN'nin her bir çıktı tahmini üzerindeki her giriş vektörünün bağlamsal etkisini ağırlıklandırmanın bir yolunu sunar. Bu, giriş RNN'sinin ara durumları ile çıktı RNN'si arasında kısayollar oluşturarak uygulanır. Bu şekilde, çıktı sembolü yt üretilirken, farklı ağırlık katsayıları αt,i ile tüm giriş gizli durumları hi dikkate alınacaktır.
-
-
-
-> Eklemeli dikkat mekanizmasına sahip kodlayıcı-çözücü modeli [Bahdanau ve diğerleri, 2015](https://arxiv.org/pdf/1409.0473.pdf) tarafından, [bu blog yazısından](https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html) alıntıdır.
-
-Dikkat matris {αi,j} belirli giriş kelimelerinin bir çıktı dizisindeki belirli bir kelimenin üretilmesindeki rolünü temsil eder. Aşağıda böyle bir matrisin örneği verilmiştir:
-
-
-
-> [Bahdanau ve diğerleri, 2015](https://arxiv.org/pdf/1409.0473.pdf) (Şekil 3)
-
-Dikkat mekanizmaları, günümüz veya yakın dönemdeki NLP'deki en son teknolojinin büyük bir kısmından sorumludur. Ancak dikkatin eklenmesi, model parametrelerinin sayısını büyük ölçüde artırır ve bu da RNN'lerde ölçeklenebilirlik sorunlarına yol açar. RNN'lerin ölçeklenebilirliğinde temel bir kısıtlama, modellerin tekrarlayan doğasının, eğitimi toplu ve paralel hale getirmeyi zorlaştırmasıdır. Bir RNN'de bir dizinin her bir öğesi, ardışık sırayla işlenmelidir; bu da kolayca paralel hale getirilemeyeceği anlamına gelir.
-
-
-
-> [Google Blogu](https://research.googleblog.com/2016/09/a-neural-network-for-machine.html) kaynaklı şekil
-
-Dikkat mekanizmalarının benimsenmesi ve bu kısıtlamanın birleşimi, günümüzde bildiğimiz ve kullandığımız, BERT'ten Open-GPT3'e kadar uzanan en son teknoloji Transformer Modellerinin yaratılmasına yol açtı.
-
-## Transformer Modelleri
-
-Transformerların arkasındaki ana fikirlerden biri, RNN'lerin ardışık doğasından kaçınmak ve eğitimi sırasında paralel hale getirilebilen bir model oluşturmaktır. Bu, iki fikrin uygulanmasıyla gerçekleştirilir:
-
-* konumsal kodlama
-* RNN'ler (veya CNN'ler) yerine desenleri yakalamak için kendine dikkat mekanizmasını kullanmak (bu nedenle transformerları tanıtan makalenin adı *[Dikkat, ihtiyacınız olan her şey](https://arxiv.org/abs/1706.03762)*dir)
-
-### Konumsal Kodlama/Gömme
-
-Konumsal kodlamanın temel fikri şudur:
-1. RNN'ler kullanırken, tokenların göreceli konumu adım sayısı ile temsil edilir ve bu nedenle açıkça temsil edilmesine gerek yoktur.
-2. Ancak, dikkate geçtiğimizde, bir dizideki tokenların göreceli konumlarını bilmemiz gerekir.
-3. Konumsal kodlama almak için, token dizimizi dizideki token konumları dizisi ile artırırız (yani, 0,1, ... sayılar dizisi).
-4. Daha sonra token konumunu bir token gömme vektörü ile karıştırırız. Konumu (tam sayı) bir vektöre dönüştürmek için farklı yaklaşımlar kullanabiliriz:
-
-* Token gömme ile benzer şekilde eğitilebilir gömme. Burada dikkate aldığımız yaklaşım budur. Hem tokenlar hem de konumları üzerinde gömme katmanları uygularız ve sonuçta aynı boyutlarda gömme vektörleri elde ederiz, bunları toplarız.
-* Orijinal makalede önerilen sabit konum kodlama fonksiyonu.
-
-
-
-> Yazarın resmi
-
-Konumsal gömme ile elde ettiğimiz sonuç, hem orijinal tokenı hem de dizideki konumunu gömer.
-
-### Çoklu Başlık Kendine Dikkat
-
-Sonraki adım, dizimizdeki bazı desenleri yakalamaktır. Bunu yapmak için, transformerlar **kendine dikkat** mekanizmasını kullanır; bu, esasen aynı diziyi girdi ve çıktı olarak uygulanan dikkattir. Kendine dikkati uygulamak, cümle içindeki **bağlamı** dikkate almamızı sağlar ve hangi kelimelerin birbiriyle ilişkili olduğunu görmemize olanak tanır. Örneğin, hangi kelimelerin *o* gibi referanslarla ifade edildiğini görmemizi sağlar ve ayrıca bağlamı dikkate alır:
-
-
-
-> Resim [Google Blogu](https://research.googleblog.com/2017/08/transformer-novel-neural-network.html) kaynaklı
-
-Transformerlarda, ağın farklı bağımlılık türlerini yakalama gücünü artırmak için **Çoklu Başlık Dikkati** kullanılır; örneğin, uzun vadeli ve kısa vadeli kelime ilişkileri, karşılıklı referanslar vs.
-
-[TensorFlow Not Defteri](../../../../../lessons/5-NLP/18-Transformers/TransformersTF.ipynb) transformer katmanlarının uygulanması hakkında daha fazla detay içerir.
-
-### Kodlayıcı-Çözücü Dikkati
-
-Transformerlarda, dikkat iki yerde kullanılır:
-
-* Kendine dikkat kullanarak giriş metnindeki desenleri yakalamak için
-* Dizi çevirisi gerçekleştirmek için - bu, kodlayıcı ve çözücü arasındaki dikkat katmanıdır.
-
-Kodlayıcı-çözücü dikkati, bu bölümün başında açıklandığı gibi RNN'lerde kullanılan dikkat mekanizmasına çok benzer. Bu animasyonlu diyagram, kodlayıcı-çözücü dikkatin rolünü açıklar.
-
-
-
-Her bir giriş konumu bağımsız olarak her bir çıkış konumuna eşlendiğinden, transformerlar RNN'lerden daha iyi paralelleşebilir; bu da çok daha büyük ve daha etkili dil modellerinin oluşmasını sağlar. Her bir dikkat başlığı, kelimeler arasındaki farklı ilişkileri öğrenmek için kullanılabilir ve bu da doğal dil işleme görevlerini geliştirir.
-
-## BERT
-
-**BERT** (Transformerlardan İkili Kodlayıcı Temsilleri), *BERT-base* için 12 katman ve *BERT-large* için 24 katman içeren çok büyük bir çok katmanlı transformer ağıdır. Model, öncelikle geniş bir metin veri kümesi (WikiPedia + kitaplar) üzerinde denetimsiz eğitim (bir cümlede maskelenmiş kelimeleri tahmin etme) kullanılarak önceden eğitilir. Ön eğitim sırasında model, daha sonra ince ayar ile diğer veri kümeleri ile kullanılabilecek önemli düzeyde dil anlayışı kazanır. Bu süreç **aktarım öğrenimi** olarak adlandırılır.
-
-
-
-> Resim [kaynak](http://jalammar.github.io/illustrated-bert/)
-
-## ✍️ Alıştırmalar: Transformerlar
-
-Aşağıdaki not defterlerinde öğreniminize devam edin:
-
-* [PyTorch'da Transformerlar](../../../../../lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb)
-* [TensorFlow'da Transformerlar](../../../../../lessons/5-NLP/18-Transformers/TransformersTF.ipynb)
-
-## Sonuç
-
-Bu derste, NLP araç kutusundaki tüm temel araçlar olan Transformerlar ve Dikkat Mekanizmaları hakkında bilgi edindiniz. BERT, DistilBERT, BigBird, OpenGPT3 ve daha fazlası dahil olmak üzere birçok Transformer mimarisi varyasyonu bulunmaktadır ve bunlar ince ayar yapılabilir. [HuggingFace paketi](https://github.com/huggingface/) bu mimarilerin çoğunu hem PyTorch hem de TensorFlow ile eğitmek için bir depo sağlar.
-
-## 🚀 Zorluk
-
-## [Ders sonrası quiz](https://ff-quizzes.netlify.app/en/ai/quiz/36)
-
-## Gözden Geçirme & Kendi Kendine Çalışma
-
-* [Blog yazısı](https://mchromiak.github.io/articles/2017/Sep/12/Transformer-Attention-is-all-you-need/), klasik [Dikkat, ihtiyacınız olan her şey](https://arxiv.org/abs/1706.03762) makalesini açıklamaktadır.
-* Transformerlar hakkında detaylı mimariyi açıklayan [bir dizi blog yazısı](https://towardsdatascience.com/transformers-explained-visually-part-1-overview-of-functionality-95a6dd460452).
-
-## [Görev](assignment.md)
-
-**Açıklama**:
-Bu belge, makine tabanlı AI çeviri hizmetleri kullanılarak çevrilmiştir. Doğruluk için çaba göstersek de, otomatik çevirilerin hatalar veya yanlış anlamalar içerebileceğini lütfen unutmayın. Orijinal belge, kendi dilinde yetkili kaynak olarak kabul edilmelidir. Kritik bilgiler için profesyonel insan çevirisi önerilmektedir. Bu çevirinin kullanımından kaynaklanan yanlış anlamalar veya yanlış yorumlamalardan dolayı sorumluluk kabul etmiyoruz.
\ No newline at end of file
diff --git a/translations/tr/lessons/5-NLP/18-Transformers/assignment.md b/translations/tr/lessons/5-NLP/18-Transformers/assignment.md
index 64e2f6e1..68858148 100644
--- a/translations/tr/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/tr/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Ödev: Transformers
HuggingFace üzerinde Transformers ile deney yapın! Sitede mevcut olan çeşitli modellerle çalışmak için sağladıkları scriptlerden bazılarını deneyin: https://huggingface.co/docs/transformers/run_scripts. Onların sunduğu bir veri kümesini deneyin, ardından bu müfredattan veya Kaggle'dan kendi veri kümenizi içe aktarın ve ilginç metinler üretebilir misiniz bir bakın. Bulgularınızı içeren bir defter hazırlayın.
diff --git a/translations/tr/lessons/5-NLP/19-NER/README.md b/translations/tr/lessons/5-NLP/19-NER/README.md
index fc0b7cf3..b08d5e51 100644
--- a/translations/tr/lessons/5-NLP/19-NER/README.md
+++ b/translations/tr/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Adlandırılmış Varlık Tanıma
Şimdiye kadar, çoğunlukla bir NLP görevi olan sınıflandırmaya odaklandık. Ancak, sinir ağlarıyla gerçekleştirilebilecek başka NLP görevleri de vardır. Bu görevlerden biri, metin içinde yer alan belirli varlıkları tanımayı içeren **[Adlandırılmış Varlık Tanıma](https://wikipedia.org/wiki/Named-entity_recognition)** (NER) işlemidir. Bu varlıklar arasında yerler, kişi isimleri, tarih-zaman aralıkları, kimyasal formüller ve daha fazlası bulunabilir.
@@ -17,7 +8,7 @@ CO_OP_TRANSLATOR_METADATA:
Diyelim ki Amazon Alexa veya Google Asistan gibi bir doğal dil sohbet botu geliştirmek istiyorsunuz. Akıllı sohbet botlarının çalışma şekli, kullanıcının ne istediğini anlamak için girilen cümle üzerinde metin sınıflandırması yapmaktır. Bu sınıflandırmanın sonucu, sohbet botunun ne yapması gerektiğini belirleyen **niyet** olarak adlandırılır.
-
+
> Görsel yazar tarafından oluşturulmuştur
diff --git a/translations/tr/lessons/5-NLP/19-NER/lab/README.md b/translations/tr/lessons/5-NLP/19-NER/lab/README.md
index 64ed62c0..1b53a94d 100644
--- a/translations/tr/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/tr/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) içindeki Laboratuvar Görevi.
diff --git a/translations/tr/lessons/5-NLP/20-LangModels/README.md b/translations/tr/lessons/5-NLP/20-LangModels/README.md
index ee3cf75c..b94ac26e 100644
--- a/translations/tr/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/tr/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Önceden Eğitilmiş Büyük Dil Modelleri
Önceki tüm görevlerimizde, etiketlenmiş bir veri seti kullanarak belirli bir görevi yerine getirmek için bir sinir ağı eğitiyorduk. BERT gibi büyük transformer modelleriyle, dil modelleme işlemini kendi kendine denetimli bir şekilde kullanarak bir dil modeli oluşturuyoruz ve ardından bu modeli belirli bir alt görev için alanına özel eğitimle özelleştiriyoruz. Ancak, büyük dil modellerinin herhangi bir alanına özel eğitim olmadan birçok görevi çözebileceği gösterilmiştir. Bu tür görevleri gerçekleştirebilen model ailesine **GPT**: Generative Pre-Trained Transformer denir.
diff --git a/translations/tr/lessons/5-NLP/20-LangModels/READMELargeLang.md b/translations/tr/lessons/5-NLP/20-LangModels/READMELargeLang.md
deleted file mode 100644
index 37bec0fa..00000000
--- a/translations/tr/lessons/5-NLP/20-LangModels/READMELargeLang.md
+++ /dev/null
@@ -1,55 +0,0 @@
-# Önceden Eğitilmiş Büyük Dil Modelleri
-
-Önceki görevlerimizde, etiketlenmiş veri seti kullanarak belirli bir görevi yerine getirmek için bir sinir ağı eğitiyorduk. BERT gibi büyük dönüştürücü modellerle, dil modellemesini kendi kendine denetimli bir şekilde kullanarak bir dil modeli oluşturuyoruz; bu model daha sonra belirli bir alt görev için daha fazla alan spesifik eğitimi ile özelleştiriliyor. Ancak, büyük dil modellerinin herhangi bir alan spesifik eğitimi olmadan birçok görevi de çözebileceği gösterilmiştir. Bunu yapabilen modeller ailesine **GPT** denir: Üretken Önceden Eğitilmiş Dönüştürücü.
-
-## [Öncesi ders sınavı](https://ff-quizzes.netlify.app/en/ai/quiz/39)
-
-## Metin Üretimi ve Perpleksite
-
-Bir sinir ağının alt görev eğitimi olmadan genel görevleri yerine getirebilmesi fikri, [Dil Modelleri Denetimsiz Çoklu Görev Öğrenicileridir](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) makalesinde sunulmuştur. Ana fikir, birçok diğer görevin **metin üretimi** kullanılarak modellenebileceğidir; çünkü metni anlamak, esasen onu üretebilme yeteneği anlamına gelir. Model, insan bilgisini kapsayan devasa bir metin miktarı üzerinde eğitildiğinden, çeşitli konularda da bilgi sahibi olur.
-
-> Metni anlamak ve üretebilmek, çevremizdeki dünya hakkında bir şeyler bilmekle de ilgilidir. İnsanlar da büyük ölçüde okuyarak öğrenirler ve GPT ağı bu açıdan benzerlik gösterir.
-
-Metin üretim ağları, bir sonraki kelimenin olasılığını $$P(w_N)$$ tahmin ederek çalışır. Ancak, bir sonraki kelimenin koşulsuz olasılığı, bu kelimenin metin koleksiyonundaki sıklığına eşittir. GPT, önceki kelimeleri göz önünde bulundurarak bir sonraki kelimenin **koşullu olasılığını** bize verebilir: $$P(w_N | w_{n-1}, ..., w_0)$$
-
-> Olasılıklar hakkında daha fazla bilgi için [Veri Bilimi Başlangıç Curriculum'umuza](https://github.com/microsoft/Data-Science-For-Beginners/tree/main/1-Introduction/04-stats-and-probability) göz atabilirsiniz.
-
-Dil üreten modelin kalitesi **perpleksite** ile tanımlanabilir. Bu, görev spesifik veri setine ihtiyaç duymadan model kalitesini ölçmemizi sağlayan içsel bir metriktir. Bir cümlenin *olasılığı* kavramına dayanmaktadır - model, gerçek olma olasılığı yüksek olan bir cümleye yüksek olasılık atar (yani model bu cümleye **perpleks** değildir) ve daha az anlam ifade eden cümlelere düşük olasılık atar (örneğin, *Bunu yapabilir mi?*). Modelimize gerçek metin koleksiyonundan cümleler verdiğimizde, bu cümlelerin yüksek olasılığa ve düşük **perpleksiteye** sahip olmasını bekleriz. Matematiksel olarak, test setinin normalize edilmiş ters olasılığı olarak tanımlanır:
-$$
-\mathrm{Perplexity}(W) = \sqrt[N]{1\over P(W_1,...,W_N)}
-$$
-
-**Metin üretimi ile deney yapabilirsiniz [Hugging Face'den GPT destekli metin editörü](https://transformer.huggingface.co/doc/gpt2-large)**. Bu editörde, metninizi yazmaya başlarsınız ve **[TAB]** tuşuna basmak size birkaç tamamlama seçeneği sunar. Eğer bunlar çok kısa ise veya memnun kalmazsanız - tekrar [TAB] tuşuna basın, daha fazla seçenek elde edersiniz; bunlar arasında daha uzun metin parçaları da bulunur.
-
-## GPT Bir Ailedir
-
-GPT, tek bir model değil, [OpenAI](https://openai.com) tarafından geliştirilen ve eğitilen modellerin bir koleksiyonudur.
-
-GPT modelleri altında, şunlar bulunmaktadır:
-
-| [GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2#openai-gpt2) | [GPT 3](https://openai.com/research/language-models-are-few-shot-learners) | [GPT-4](https://openai.com/gpt-4) |
-| -- | -- | -- |
-| 1.5 milyar parametreye kadar dil modeli. | 175 milyar parametreye kadar dil modeli | 100T parametre ve hem görsel hem de metin girdilerini kabul edip metin çıktısı verir. |
-
-GPT-3 ve GPT-4 modelleri [Microsoft Azure'dan bilişsel bir hizmet olarak](https://azure.microsoft.com/en-us/services/cognitive-services/openai-service/#overview?WT.mc_id=academic-77998-cacaste) ve [OpenAI API'si](https://openai.com/api/) olarak mevcuttur.
-
-## İstek Mühendisliği
-
-GPT, dil ve kodu anlamak için geniş veri hacimlerinde eğitildiğinden, girdilere (isteklere) yanıt olarak çıktılar sağlar. İstekler, bir modelin tamamlayacağı görevler hakkında talimatlar veren GPT girdileri veya sorgularıdır. İstenilen bir sonucu elde etmek için, doğru kelimeleri, formatları, ifadeleri veya hatta sembolleri seçmek gibi en etkili isteğe ihtiyacınız vardır. Bu yaklaşım [İstek Mühendisliği](https://learn.microsoft.com/en-us/shows/ai-show/the-basics-of-prompt-engineering-with-azure-openai-service?WT.mc_id=academic-77998-bethanycheum) olarak adlandırılır.
-
-[Bu belgede](https://learn.microsoft.com/en-us/semantic-kernel/prompt-engineering/?WT.mc_id=academic-77998-bethanycheum) istek mühendisliği hakkında daha fazla bilgi bulabilirsiniz.
-
-## ✍️ Örnek Not Defteri: [OpenAI-GPT ile Oynama](../../../../../lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb)
-
-Aşağıdaki not defterlerinde öğrenmeye devam edin:
-
-* [OpenAI-GPT ve Hugging Face Dönüştürücüleri ile metin üretimi](../../../../../lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb)
-
-## Sonuç
-
-Yeni genel önceden eğitilmiş dil modelleri sadece dil yapısını modellemekle kalmaz, aynı zamanda büyük miktarda doğal dil içerir. Bu nedenle, bazı NLP görevlerini sıfırdan veya az sayıda örnekle çözmek için etkili bir şekilde kullanılabilirler.
-
-## [Ders sonrası sınav](https://ff-quizzes.netlify.app/en/ai/quiz/40)
-
-**Açıklama**:
-Bu belge, makine tabanlı AI çeviri hizmetleri kullanılarak çevrilmiştir. Doğruluğa önem vermemize rağmen, otomatik çevirilerin hatalar veya yanlış anlamalar içerebileceğini lütfen unutmayın. Belgenin orijinal metni, yetkili kaynak olarak kabul edilmelidir. Kritik bilgiler için profesyonel insan çevirisi önerilmektedir. Bu çevirinin kullanımı sonucunda ortaya çıkan yanlış anlamalar veya yanlış yorumlamalardan sorumlu değiliz.
\ No newline at end of file
diff --git a/translations/tr/lessons/5-NLP/README.md b/translations/tr/lessons/5-NLP/README.md
index 5f632551..e57ff4c9 100644
--- a/translations/tr/lessons/5-NLP/README.md
+++ b/translations/tr/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Doğal Dil İşleme
diff --git a/translations/tr/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/tr/lessons/6-Other/21-GeneticAlgorithms/README.md
index fb5cde60..556192f8 100644
--- a/translations/tr/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/tr/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Genetik Algoritmalar
## [Ders Öncesi Testi](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/tr/lessons/6-Other/22-DeepRL/README.md b/translations/tr/lessons/6-Other/22-DeepRL/README.md
index 0b0463ff..fc57ada3 100644
--- a/translations/tr/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/tr/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Derin Pekiştirmeli Öğrenme
Pekiştirmeli öğrenme (RL), denetimli öğrenme ve denetimsiz öğrenme ile birlikte temel makine öğrenimi paradigmalarından biri olarak görülür. Denetimli öğrenmede bilinen sonuçlara sahip bir veri setine dayanırken, RL **yaparak öğrenme** prensibine dayanır. Örneğin, bir bilgisayar oyununu ilk kez gördüğümüzde, kuralları bilmeden oynamaya başlarız ve sadece oynayarak ve davranışlarımızı ayarlayarak becerilerimizi geliştirebiliriz.
@@ -34,7 +25,7 @@ Muhtemelen hepiniz modern dengeleme cihazlarını, örneğin *Segway* veya *Gyro
Dengelemenin basitleştirilmiş bir versiyonu **CartPole** problemi olarak bilinir. CartPole dünyasında, sola veya sağa hareket edebilen yatay bir kaydırıcıya sahibiz ve hedef, kaydırıcının üzerinde dikey bir direği dengede tutmaktır.
-
+
Bu ortamı oluşturmak ve kullanmak için birkaç satır Python koduna ihtiyacımız var:
diff --git a/translations/tr/lessons/6-Other/22-DeepRL/lab/README.md b/translations/tr/lessons/6-Other/22-DeepRL/lab/README.md
index 22c8b2f6..4002ca55 100644
--- a/translations/tr/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/tr/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## Ortam
Mountain Car ortamı, bir vadide sıkışmış bir arabadan oluşur. Amacınız vadiden çıkıp bayrağa ulaşmaktır. Yapabileceğiniz eylemler sola hızlanmak, sağa hızlanmak veya hiçbir şey yapmamaktır. Arabanın x ekseni boyunca konumunu ve hızını gözlemleyebilirsiniz.
diff --git a/translations/tr/lessons/6-Other/23-MultiagentSystems/README.md b/translations/tr/lessons/6-Other/23-MultiagentSystems/README.md
index e7910216..5b72b009 100644
--- a/translations/tr/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/tr/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Çoklu-Ajan Sistemleri
Zekayı elde etmenin olası yollarından biri, **ortaya çıkan** (veya **sinerjik**) yaklaşımdır. Bu yaklaşım, birçok nispeten basit ajanın birleşik davranışının, sistemin bir bütün olarak daha karmaşık (veya zeki) bir davranış sergilemesine yol açabileceği gerçeğine dayanır. Teorik olarak, bu yaklaşım [Kolektif Zeka](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentizm](https://en.wikipedia.org/wiki/Global_brain) ve [Evrimsel Sibernetik](https://en.wikipedia.org/wiki/Global_brain) ilkelerine dayanır. Bu ilkeler, üst düzey sistemlerin, alt düzey sistemlerin uygun şekilde birleştirilmesiyle bir tür ek değer kazandığını ifade eder (*metasistem geçişi ilkesi* olarak adlandırılır).
@@ -60,7 +51,7 @@ NetLogo'yu [indirip](https://ccl.northwestern.edu/netlogo/download.shtml) kurara
NetLogo'nun harika bir özelliği, deneyebileceğiniz çalışan modellerin bulunduğu bir kütüphaneye sahip olmasıdır. **File → Models Library** seçeneğine gidin ve birçok model kategorisi arasından seçim yapabilirsiniz.
-
+
> Dmitry Soshnikov tarafından modeller kütüphanesi ekran görüntüsü
diff --git a/translations/tr/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/tr/lessons/6-Other/23-MultiagentSystems/assignment.md
index 18bcfb96..18f3d1e1 100644
--- a/translations/tr/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/tr/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# NetLogo Ödevi
NetLogo'nun kütüphanesindeki modellerden birini alın ve bunu gerçek bir durumu olabildiğince yakından simüle etmek için kullanın. İyi bir örnek, Alternatif Görselleştirmeler klasöründeki Virüs modelini, COVID-19'un yayılmasını modellemek için nasıl kullanılabileceğini gösterecek şekilde uyarlamak olabilir. Gerçek hayattaki bir viral yayılımı taklit eden bir model oluşturabilir misiniz?
diff --git a/translations/tr/lessons/7-Ethics/README.md b/translations/tr/lessons/7-Ethics/README.md
index 6f1046ce..779e3a0f 100644
--- a/translations/tr/lessons/7-Ethics/README.md
+++ b/translations/tr/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Etik ve Sorumlu Yapay Zeka
Bu kursu neredeyse tamamladınız ve umarım şu ana kadar yapay zekanın, verilerdeki ilişkileri bulmamıza ve insan davranışının bazı yönlerini taklit eden modelleri eğitmemize olanak tanıyan bir dizi resmi matematiksel yönteme dayandığını açıkça görüyorsunuzdur. Tarihin bu noktasında, yapay zekayı verilerden desenler çıkarmak ve bu desenleri yeni problemleri çözmek için uygulamak adına çok güçlü bir araç olarak görüyoruz.
diff --git a/translations/tr/lessons/README.md b/translations/tr/lessons/README.md
index fede0813..61e65c54 100644
--- a/translations/tr/lessons/README.md
+++ b/translations/tr/lessons/README.md
@@ -1,12 +1,3 @@
-
# Genel Bakış
diff --git a/translations/tr/lessons/X-Extras/X1-MultiModal/README.md b/translations/tr/lessons/X-Extras/X1-MultiModal/README.md
index f963df76..3438041b 100644
--- a/translations/tr/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/tr/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Çok Modlu Ağlar
Transformer modellerinin NLP görevlerini çözmedeki başarısından sonra, aynı veya benzer mimariler bilgisayar görme görevlerine uygulanmaya başlandı. Görme ve doğal dil yeteneklerini *birleştiren* modeller oluşturma konusunda artan bir ilgi var. Bu girişimlerden biri OpenAI tarafından gerçekleştirildi ve CLIP ile DALL.E olarak adlandırıldı.
diff --git a/translations/tr/lessons/sketchnotes/LICENSE.md b/translations/tr/lessons/sketchnotes/LICENSE.md
index 3d1579d7..00cc2cb7 100644
--- a/translations/tr/lessons/sketchnotes/LICENSE.md
+++ b/translations/tr/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Attribution-ShareAlike 4.0 Uluslararası
=======================================================================
diff --git a/translations/tr/lessons/sketchnotes/README.md b/translations/tr/lessons/sketchnotes/README.md
index 7a5d0b89..ac49ed4c 100644
--- a/translations/tr/lessons/sketchnotes/README.md
+++ b/translations/tr/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Tüm müfredatın sketchnote'larını buradan indirebilirsiniz.
🎨 Oluşturan: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/tr/troubleshoot.md b/translations/tr/troubleshoot.md
index 75972df6..523e10bb 100644
--- a/translations/tr/troubleshoot.md
+++ b/translations/tr/troubleshoot.md
@@ -1,12 +1,3 @@
-
# AI-For-Beginners Sorun Giderme Kılavuzu
Bu kılavuz, [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners) deposunu kullanırken veya katkıda bulunurken karşılaşılan yaygın sorunları çözmenize yardımcı olur. Her sorun için arka plan bilgisi, belirtiler, açıklamalar ve adım adım çözümler sunulmaktadır.