diff --git a/translations/he/.co-op-translator.json b/translations/he/.co-op-translator.json new file mode 100644 index 00000000..00992d3a --- /dev/null +++ b/translations/he/.co-op-translator.json @@ -0,0 +1,398 @@ +{ + "AGENTS.md": { + "original_hash": "6b11a37115944252ab3ed04e358d830d", + "translation_date": "2025-10-03T09:24:51+00:00", + "source_file": "AGENTS.md", + "language_code": "he" + }, + "README.md": { + "original_hash": "1984fc89dd304a8a33ab5584691a99aa", + "translation_date": "2026-01-30T02:10:40+00:00", + "source_file": "README.md", + "language_code": "he" + }, + "SECURITY.md": { + "original_hash": "a583f49d359c7ebba61433e4dfcd05a9", + "translation_date": "2025-08-28T19:13:42+00:00", + "source_file": "SECURITY.md", + "language_code": "he" + }, + "etc/CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-08-28T20:13:31+00:00", + "source_file": "etc/CODE_OF_CONDUCT.md", + "language_code": "he" + }, + "etc/CONTRIBUTING.md": { + "original_hash": "847a587aa1b83f4d00858183ff3ed18a", + "translation_date": "2025-08-28T20:13:10+00:00", + "source_file": "etc/CONTRIBUTING.md", + "language_code": "he" + }, + "etc/Mindmap.md": { + "original_hash": "f2f88dbd2debd38e26149b27b1fd272d", + "translation_date": "2025-08-28T20:11:54+00:00", + "source_file": "etc/Mindmap.md", + "language_code": "he" + }, + "etc/SUPPORT.md": { + "original_hash": "fdfc08baee91e402938a2b1f94fe0949", + "translation_date": "2025-08-28T20:10:13+00:00", + "source_file": "etc/SUPPORT.md", + "language_code": "he" + }, + "etc/TRANSLATIONS.md": { + "original_hash": "62b3e3ad5182edb905eec649a87eeeb4", + "translation_date": "2025-08-28T20:12:43+00:00", + "source_file": "etc/TRANSLATIONS.md", + "language_code": "he" + }, + "etc/quiz-app/README.md": { + "original_hash": "d699cf8509f74baa5b0b838de5cf0662", + "translation_date": "2025-08-28T20:14:09+00:00", + "source_file": "etc/quiz-app/README.md", + "language_code": "he" + }, + "examples/README.md": { + "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7", + "translation_date": "2025-10-03T11:32:11+00:00", + "source_file": "examples/README.md", + "language_code": "he" + }, + "lessons/0-course-setup/for-teachers.md": { + "original_hash": "a094ef9927883de1cfcee51dbd143381", + "translation_date": "2025-08-28T19:19:11+00:00", + "source_file": "lessons/0-course-setup/for-teachers.md", + "language_code": "he" + }, + "lessons/0-course-setup/how-to-run.md": { + "original_hash": "a4717bd9103b9f6cd84d534b83534689", + "translation_date": "2026-01-16T03:33:24+00:00", + "source_file": "lessons/0-course-setup/how-to-run.md", + "language_code": "he" + }, + "lessons/0-course-setup/setup.md": { + "original_hash": "7b4e5b8956915870d0a0ed3cc5890042", + "translation_date": "2025-12-12T19:58:30+00:00", + "source_file": "lessons/0-course-setup/setup.md", + "language_code": "he" + }, + "lessons/1-Intro/README.md": { + "original_hash": "f57e8aa46141fd220b16ffed8f11aec7", + "translation_date": "2025-11-18T21:43:29+00:00", + "source_file": "lessons/1-Intro/README.md", + "language_code": "he" + }, + "lessons/1-Intro/assignment.md": { + "original_hash": "a334df77a82aaaf2a29c77065d3e481e", + "translation_date": "2025-11-18T21:44:31+00:00", + "source_file": "lessons/1-Intro/assignment.md", + "language_code": "he" + }, + "lessons/2-Symbolic/README.md": { + "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4", + "translation_date": "2026-01-16T03:35:15+00:00", + "source_file": "lessons/2-Symbolic/README.md", + "language_code": "he" + }, + "lessons/2-Symbolic/assignment.md": { + "original_hash": "a057a8604f3976c3e309884453f1fad0", + "translation_date": "2025-08-28T19:41:21+00:00", + "source_file": "lessons/2-Symbolic/assignment.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/03-Perceptron/README.md": { + "original_hash": "c34cbba802058b6fa267e1a294d4e510", + "translation_date": "2025-09-23T10:22:12+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": { + "original_hash": "ba5d1eb353d20d3e7181066b3c424b99", + "translation_date": "2025-08-29T11:42:49+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/README.md": { + "original_hash": "789d6c3fb6fc7948a470b33078a5983a", + "translation_date": "2025-09-23T10:21:43+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": { + "original_hash": "48fdd704d483e19bc3d7464074c9fcbe", + "translation_date": "2025-08-28T19:47:50+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/05-Frameworks/README.md": { + "original_hash": "ddd216f558a255260a9374008002c971", + "translation_date": "2025-09-23T10:22:33+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": { + "original_hash": "e452d897efb9a89700f41021834cf6e5", + "translation_date": "2025-08-28T19:51:04+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md", + "language_code": "he" + }, + "lessons/3-NeuralNetworks/README.md": { + "original_hash": "f862a99d88088163df12270e2f2ad6c3", + "translation_date": "2025-10-03T12:50:35+00:00", + "source_file": "lessons/3-NeuralNetworks/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/06-IntroCV/README.md": { + "original_hash": "feeca98225cb420afc89415f24f63d92", + "translation_date": "2025-09-23T10:17:33+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/06-IntroCV/lab/README.md": { + "original_hash": "3d53d6409f80970f7281a45dee35328a", + "translation_date": "2025-08-28T19:31:31+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": { + "original_hash": "53faab85adfcebd8c10bcd71dc2fa557", + "translation_date": "2025-09-23T10:16:55+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/07-ConvNets/README.md": { + "original_hash": "a560d5b845962cf33dc102266e409568", + "translation_date": "2025-09-23T10:16:34+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/07-ConvNets/lab/README.md": { + "original_hash": "b70fcf7fcee862990f848c679090943f", + "translation_date": "2025-10-03T14:56:02+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/08-TransferLearning/README.md": { + "original_hash": "178c0b5ee5395733eb18aec51e71a0a9", + "translation_date": "2025-09-23T10:17:12+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": { + "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99", + "translation_date": "2025-08-28T19:28:44+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": { + "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2", + "translation_date": "2025-08-28T19:29:33+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/09-Autoencoders/README.md": { + "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d", + "translation_date": "2025-09-23T10:18:34+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/10-GANs/README.md": { + "original_hash": "0ff65b4da07b23697235de2beb2a3c25", + "translation_date": "2025-09-23T10:19:21+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/11-ObjectDetection/README.md": { + "original_hash": "d76a7eda28de5210c8b1ba50a6216c69", + "translation_date": "2025-09-23T10:17:59+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": { + "original_hash": "ad568d55ae65c856fe929fc2b278510a", + "translation_date": "2025-08-28T19:33:44+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/12-Segmentation/README.md": { + "original_hash": "6568aaae7e0e4afed4b5d74b5b223700", + "translation_date": "2025-09-23T10:19:03+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/12-Segmentation/lab/README.md": { + "original_hash": "365f0decfe0f47b460bbde8227c5009d", + "translation_date": "2025-08-28T19:36:41+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md", + "language_code": "he" + }, + "lessons/4-ComputerVision/README.md": { + "original_hash": "58a52f000089c1d8906a4daa4ab1169b", + "translation_date": "2025-08-28T19:23:32+00:00", + "source_file": "lessons/4-ComputerVision/README.md", + "language_code": "he" + }, + "lessons/5-NLP/13-TextRep/README.md": { + "original_hash": "dbd3f73e4139f030ecb2e20387d70fee", + "translation_date": "2025-09-23T10:25:24+00:00", + "source_file": "lessons/5-NLP/13-TextRep/README.md", + "language_code": "he" + }, + "lessons/5-NLP/13-TextRep/assignment.md": { + "original_hash": "cdc1f2e631f055f3473b36d18e4760b3", + "translation_date": "2025-08-28T20:09:57+00:00", + "source_file": "lessons/5-NLP/13-TextRep/assignment.md", + "language_code": "he" + }, + "lessons/5-NLP/14-Embeddings/README.md": { + "original_hash": "b708c9b85b833864c73c6281f1e6b96e", + "translation_date": "2025-09-23T10:25:01+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/README.md", + "language_code": "he" + }, + "lessons/5-NLP/14-Embeddings/assignment.md": { + "original_hash": "bc690ecf68b38d311cc9e12f3144a28c", + "translation_date": "2025-08-28T20:08:32+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/assignment.md", + "language_code": "he" + }, + "lessons/5-NLP/15-LanguageModeling/README.md": { + "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57", + "translation_date": "2025-09-23T10:23:22+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/README.md", + "language_code": "he" + }, + "lessons/5-NLP/15-LanguageModeling/lab/README.md": { + "original_hash": "5130f01fdc5ebb83032b23d489027aac", + "translation_date": "2025-08-28T20:00:49+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md", + "language_code": "he" + }, + "lessons/5-NLP/16-RNN/README.md": { + "original_hash": "e2273cc150380a5e191903cea858f021", + "translation_date": "2025-09-23T10:24:33+00:00", + "source_file": "lessons/5-NLP/16-RNN/README.md", + "language_code": "he" + }, + "lessons/5-NLP/16-RNN/assignment.md": { + "original_hash": "47f7d3c6a5373543e051e4d1140ce898", + "translation_date": "2025-08-28T20:07:16+00:00", + "source_file": "lessons/5-NLP/16-RNN/assignment.md", + "language_code": "he" + }, + "lessons/5-NLP/17-GenerativeNetworks/README.md": { + "original_hash": "51be6057374d01d70e07dd5ec88ebc0d", + "translation_date": "2025-09-23T10:23:00+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md", + "language_code": "he" + }, + "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": { + "original_hash": "439e12796197a90e7623d4c9c057b9c2", + "translation_date": "2025-08-28T19:59:49+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md", + "language_code": "he" + }, + "lessons/5-NLP/18-Transformers/README.md": { + "original_hash": "f335dfcb4a993920504c387973a36957", + "translation_date": "2025-09-23T10:23:31+00:00", + "source_file": "lessons/5-NLP/18-Transformers/README.md", + "language_code": "he" + }, + "lessons/5-NLP/18-Transformers/assignment.md": { + "original_hash": "177f3ea3995d725e6f9f5c66af16edcd", + "translation_date": "2025-08-28T20:02:46+00:00", + "source_file": "lessons/5-NLP/18-Transformers/assignment.md", + "language_code": "he" + }, + "lessons/5-NLP/19-NER/README.md": { + "original_hash": "6522312ff835796ca34136a9462fafb2", + "translation_date": "2025-09-23T10:24:17+00:00", + "source_file": "lessons/5-NLP/19-NER/README.md", + "language_code": "he" + }, + "lessons/5-NLP/19-NER/lab/README.md": { + "original_hash": "032bda5068f543d6c1fcb30c34231461", + "translation_date": "2025-08-28T20:05:23+00:00", + "source_file": "lessons/5-NLP/19-NER/lab/README.md", + "language_code": "he" + }, + "lessons/5-NLP/20-LangModels/README.md": { + "original_hash": "97836d30a6bec736f8e3b4411c572bc2", + "translation_date": "2025-09-23T10:23:55+00:00", + "source_file": "lessons/5-NLP/20-LangModels/README.md", + "language_code": "he" + }, + "lessons/5-NLP/README.md": { + "original_hash": "8ef02a9318257ea140ed3ed74442096d", + "translation_date": "2025-08-28T19:58:00+00:00", + "source_file": "lessons/5-NLP/README.md", + "language_code": "he" + }, + "lessons/6-Other/21-GeneticAlgorithms/README.md": { + "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a", + "translation_date": "2025-09-23T10:15:12+00:00", + "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md", + "language_code": "he" + }, + "lessons/6-Other/22-DeepRL/README.md": { + "original_hash": "04395657fc01648f8f70484d0e55ab67", + "translation_date": "2025-09-23T10:16:08+00:00", + "source_file": "lessons/6-Other/22-DeepRL/README.md", + "language_code": "he" + }, + "lessons/6-Other/22-DeepRL/lab/README.md": { + "original_hash": "7bd8dc72040e98e35e7225e34058cd4e", + "translation_date": "2025-08-28T19:18:50+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/README.md", + "language_code": "he" + }, + "lessons/6-Other/23-MultiagentSystems/README.md": { + "original_hash": "38a1185ae3d54b180378bbd71ae3ef16", + "translation_date": "2025-09-23T10:15:28+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/README.md", + "language_code": "he" + }, + "lessons/6-Other/23-MultiagentSystems/assignment.md": { + "original_hash": "cf654ca60c7f86c8dad28596fb42994b", + "translation_date": "2025-08-28T19:17:08+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md", + "language_code": "he" + }, + "lessons/7-Ethics/README.md": { + "original_hash": "437c988596e751072e41a5aad3fcc5d9", + "translation_date": "2025-08-28T19:42:03+00:00", + "source_file": "lessons/7-Ethics/README.md", + "language_code": "he" + }, + "lessons/README.md": { + "original_hash": "5fef1a0b22498d7188959e2a2cb08af7", + "translation_date": "2025-08-28T19:14:06+00:00", + "source_file": "lessons/README.md", + "language_code": "he" + }, + "lessons/X-Extras/X1-MultiModal/README.md": { + "original_hash": "9c592c26aca16ca085d268c732284187", + "translation_date": "2025-08-28T19:22:51+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/README.md", + "language_code": "he" + }, + "lessons/sketchnotes/LICENSE.md": { + "original_hash": "45ab63a2cd8f5faef6c9b150618837a4", + "translation_date": "2025-08-28T19:56:06+00:00", + "source_file": "lessons/sketchnotes/LICENSE.md", + "language_code": "he" + }, + "lessons/sketchnotes/README.md": { + "original_hash": "050b8bddebafba55b129414e6ab096ab", + "translation_date": "2025-08-28T19:51:23+00:00", + "source_file": "lessons/sketchnotes/README.md", + "language_code": "he" + }, + "troubleshoot.md": { + "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86", + "translation_date": "2025-10-03T09:46:53+00:00", + "source_file": "troubleshoot.md", + "language_code": "he" + } +} \ No newline at end of file diff --git a/translations/he/AGENTS.md b/translations/he/AGENTS.md index 29f91a50..8d1fe3cd 100644 --- a/translations/he/AGENTS.md +++ b/translations/he/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## סקירת הפרויקט diff --git a/translations/he/README.md b/translations/he/README.md index bfa945a2..bcc60007 100644 --- a/translations/he/README.md +++ b/translations/he/README.md @@ -1,232 +1,225 @@ - -[![רישיון GitHub](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE) -[![תורמי GitHub](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/) -[![בעיות GitHub](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/) -[![בקשות משיכה GitHub](https://img.shields.io/github/issues-pr/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/pulls/) -[![ברוכים הבאים ל-PR](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![GitHub license](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE) +[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/) +[![GitHub issues](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/) +[![GitHub pull-requests](https://img.shields.io/github/issues-pr/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/pulls/) +[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![עוקבים ב-GitHub](https://img.shields.io/github/watchers/microsoft/AI-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/AI-For-Beginners/watchers/) -[![Forkים ב-GitHub](https://img.shields.io/github/forks/microsoft/AI-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/AI-For-Beginners/network/) -[![כוכבים ב-GitHub](https://img.shields.io/github/stars/microsoft/AI-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/AI-For-Beginners/stargazers/) -[![באינדר](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD) -[![גיטר](https://badges.gitter.im/Microsoft/ai-for-beginners.svg)](https://gitter.im/Microsoft/ai-for-beginners?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge) +[![GitHub watchers](https://img.shields.io/github/watchers/microsoft/AI-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/AI-For-Beginners/watchers/) +[![GitHub forks](https://img.shields.io/github/forks/microsoft/AI-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/AI-For-Beginners/network/) +[![GitHub stars](https://img.shields.io/github/stars/microsoft/AI-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/AI-For-Beginners/stargazers/) +[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD) +[![Gitter](https://badges.gitter.im/Microsoft/ai-for-beginners.svg)](https://gitter.im/Microsoft/ai-for-beginners?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge) -[![Discord של Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -# אינטליגנציה מלאכותית למתחילים - תוכנית לימודים +# אינטיליגנציה מלאכותית למתחילים - תוכנית לימודים -|![סכמוט השירטוט על ידי @girlie_mac https://twitter.com/girlie_mac](../../../../translated_images/he/ai-overview.0857791951d19500.webp)| +|![Sketchnote by @girlie_mac https://twitter.com/girlie_mac](../../translated_images/he/ai-overview.0857791951d19500.webp)| |:---:| -| אינטליגנציה מלאכותית למתחילים - _סכמוט שירטוט על ידי [@girlie_mac](https://twitter.com/girlie_mac)_ | +| AI למתחילים - _סכמטה מאת [@girlie_mac](https://twitter.com/girlie_mac)_ | + +חקור את עולם **האינטיליגנציה המלאכותית** (AI) עם תוכנית הלימודים שלנו ל-12 שבועות ו-24 שיעורים! היא כוללת שיעורים מעשיים, חידונים ומעבדות. התוכנית מותאמת למתחילים וכוללת כלים כמו TensorFlow ו-PyTorch, וכן אתיקה ב-AI -חקור את העולם של **אינטליגנציה מלאכותית** (AI) עם תוכנית הלימודים שלנו בת 12 שבועות, 24 שיעורים! התוכנית כוללת שיעורים מעשיים, מבחנים ומעבדות. התוכנית ידידותית למתחילים ומכסה כלים כמו TensorFlow ו-PyTorch, לצד אתיקה באינטליגנציה מלאכותית ### 🌐 תמיכה בריבוי שפות -#### נתמכת באמצעות GitHub Action (אוטומטי ותמיד מעודכן) +#### נתמך באמצעות GitHub Action (אוטומטי ותמיד מעודכן) -[ערבית](../ar/README.md) | [בנגלית](../bn/README.md) | [בולגרית](../bg/README.md) | [בורמזית (מיאנמר)](../my/README.md) | [סינית (מפושטת)](../zh/README.md) | [סינית (מסורתית, הונג קונג)](../hk/README.md) | [סינית (מסורתית, מקאו)](../mo/README.md) | [סינית (מסורתית, טייוואן)](../tw/README.md) | [קרואטית](../hr/README.md) | [צ׳כית](../cs/README.md) | [דנית](../da/README.md) | [הולנדית](../nl/README.md) | [אסטונית](../et/README.md) | [פינית](../fi/README.md) | [צרפתית](../fr/README.md) | [גרמנית](../de/README.md) | [יוונית](../el/README.md) | [עברית](./README.md) | [הינדי](../hi/README.md) | [הונגרית](../hu/README.md) | [אינדונזית](../id/README.md) | [איטלקית](../it/README.md) | [יפנית](../ja/README.md) | [קנדה](../kn/README.md) | [קוריאנית](../ko/README.md) | [ליטאית](../lt/README.md) | [מלאית](../ms/README.md) | [מאליאלאם](../ml/README.md) | [מרהטית](../mr/README.md) | [נפאלית](../ne/README.md) | [פידג'ין ניגרית](../pcm/README.md) | [נורווגית](../no/README.md) | [פרסית (פארסי)](../fa/README.md) | [פולנית](../pl/README.md) | [פורטוגזית (ברזיל)](../br/README.md) | [פורטוגזית (פורטוגל)](../pt/README.md) | [פונג׳אבית (גורמוכ׳י)](../pa/README.md) | [רומנית](../ro/README.md) | [רוסית](../ru/README.md) | [סרבית (קירילית)](../sr/README.md) | [סלובקית](../sk/README.md) | [סלובנית](../sl/README.md) | [ספרדית](../es/README.md) | [סווהילי](../sw/README.md) | [שבדית](../sv/README.md) | [טגלוג (פיליפינית)](../tl/README.md) | [טמילית](../ta/README.md) | [טלאגו](../te/README.md) | [תאית](../th/README.md) | [טורקית](../tr/README.md) | [אוקראינית](../uk/README.md) | [אורדו](../ur/README.md) | [וייטנאמית](../vi/README.md) +[ערבית](../ar/README.md) | [בנגלית](../bn/README.md) | [בולגרית](../bg/README.md) | [בורמזית (מיאנמר)](../my/README.md) | [סינית (מפושטת)](../zh-CN/README.md) | [סינית (מסורתית, הונג קונג)](../zh-HK/README.md) | [סינית (מסורתית, מקאו)](../zh-MO/README.md) | [סינית (מסורתית, טאיוואן)](../zh-TW/README.md) | [קרואטית](../hr/README.md) | [צ'כית](../cs/README.md) | [דנית](../da/README.md) | [הולנדית](../nl/README.md) | [אסטונית](../et/README.md) | [פינית](../fi/README.md) | [צרפתית](../fr/README.md) | [גרמנית](../de/README.md) | [יוונית](../el/README.md) | [עברית](./README.md) | [הינדי](../hi/README.md) | [הונגרית](../hu/README.md) | [אינדונזית](../id/README.md) | [איטלקית](../it/README.md) | [יפנית](../ja/README.md) | [קנדה](../kn/README.md) | [קוריאנית](../ko/README.md) | [ליטאית](../lt/README.md) | [מלאית](../ms/README.md) | [מאליאלאם](../ml/README.md) | [מרטהית](../mr/README.md) | [נפאלית](../ne/README.md) | [פידג'ין ניגרי](../pcm/README.md) | [נורווגית](../no/README.md) | [פרסית (פרסי)](../fa/README.md) | [פולנית](../pl/README.md) | [פורטוגזית (ברזיל)](../pt-BR/README.md) | [פורטוגזית (פורטוגל)](../pt-PT/README.md) | [פונג'אבי (גורמוקי)](../pa/README.md) | [רומנית](../ro/README.md) | [רוסית](../ru/README.md) | [סרבית (קירילית)](../sr/README.md) | [סלובקית](../sk/README.md) | [סלובנית](../sl/README.md) | [ספרדית](../es/README.md) | [סוואהילי](../sw/README.md) | [שוודית](../sv/README.md) | [טגלוג (פיליפינית)](../tl/README.md) | [טמילית](../ta/README.md) | [טלווגו](../te/README.md) | [תאית](../th/README.md) | [טורקית](../tr/README.md) | [אוקראינית](../uk/README.md) | [אורדו](../ur/README.md) | [וייטנאמית](../vi/README.md) > **מעדיפים לשכפל מקומית?** -> מאגר זה כולל יותר מ-50 תרגומים לשפות שונות, מה שמגדיל משמעותית את גודל ההורדה. כדי לשכפל ללא תרגומים, השתמשו ב-sparse checkout: +> מאגר זה כולל יותר מ-50 שפות תרגום שמגדילות משמעותית את גודל ההורדה. כדי לשכפל בלי תרגומים, השתמשו ב-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' > ``` -> זה נותן לך את כל מה שאתה צריך כדי להשלים את הקורס עם הורדה הרבה יותר מהירה. +> זה נותן לכם את כל מה שאתם צריכים כדי להשלים את הקורס במהירות הורדה הרבה יותר גבוהה. -**אם ברצונך שהתמיכה בשפות תרגום נוספות, רשימות אלו מופיעות [כאן](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** +**אם ברצונכם לתמוך בשפות תרגום נוספות, הרשימה מופיעה [כאן](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** -## הצטרף לקהילה -[![Discord של Microsoft Foundry](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +## הצטרפו לקהילה +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -## מה תלמד +## מה תלמדו -**[מפת רעיונות של הקורס](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** +**[מפת חשיבה של הקורס](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** -בתכנית זו תלמד: +בתוכנית זו, תלמדו: -* גישות שונות לאינטליגנציה מלאכותית, כולל הגישה הסימבולית "הטובה הישנה" עם **ייצוג ידע** והסקת מסקנות ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* **רשתות עצביות** ו**למידה עמוקה**, שעומדות במרכז האינטליגנציה המודרנית. נמחיש את המושגים המרכזיים הללו באמצעות קוד בשתי המסגרות הפופולריות ביותר - [TensorFlow](http://Tensorflow.org) ו-[PyTorch](http://pytorch.org). -* **ארכיטקטורות עצביות** לעבודה עם תמונות וטקסט. נכסה מודלים עדכניים אך ייתכן ונחסרה מעט תמיכה בטכנולוגיה העדכנית ביותר. -* גישות פחות נפוצות ב-AI, כמו **אלגוריתמים גנטיים** ו**מערכות מרובי-סוכנים**. +* גישות שונות לאינטיליגנציה מלאכותית, כולל הגישה הסימבולית ה"טובה הישנה" עם **ייצוג ידע** והסקת מסקנות ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* **רשתות נוירונים** ו**למידה עמוקה**, שהן בליבת ה-AI המודרני. נדגים את המושגים מאחורי הנושאים החשובים הללו באמצעות קוד בשני הפלטפורמות הפופולריות ביותר - [TensorFlow](http://Tensorflow.org) ו-[PyTorch](http://pytorch.org). +* **ארכיטקטורות עצביות** לעבודה עם תמונות וטקסט. נכסה מודלים אחרונים אך ייתכן שיהיה חוסר קל בסטייט-אוף-דה-ארט. +* גישות AI פחות פופולריות, כמו **אלגוריתמים גנטיים** ו**מערכות רב-סוכניים**. -מה שלא נכסה בתכנית זו: +מה לא נכסה בתוכנית זו: -> [מצא את כל המשאבים הנוספים לקורס זה באוסף Microsoft Learn שלנו](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) +> [מצאו את כל המשאבים הנוספים לקורס זה באוסף שלנו ב-Microsoft Learn](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* מקרי עסקים לשימוש ב**AI בעסקים**. מומלץ לקחת את מסלול הלמידה [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) ב-Microsoft Learn, או את [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), שפותח בשיתוף עם [INSEAD](https://www.insead.edu/). -* **למידת מכונה קלאסית**, המתוארת היטב בתכנית הלימודים שלנו [למידת מכונה למתחילים](http://github.com/Microsoft/ML-for-Beginners). -* יישומי AI מעשיים שנבנו באמצעות **[שירותי קוגניציה](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. לשם כך, אנו ממליצים להתחיל במודולים ב-Microsoft Learn בנושא [ראייה ממוחשבת](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [עיבוד שפה טבעית](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[AI גנרטיבי עם Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ואחרים. -* מסגרות ענן ספציפיות ל-ML, כמו [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), או [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). מומלץ להשתמש במסלולי הלמידה [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) ו-[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). -* **AI שיחתי** ו**צ׳אט בוטים**. יש מסלול למידה נפרד [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), וניתן גם לעיין ב-[פוסט בבלוג](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) לפרטים נוספים. -* **מתמטיקה עמוקה** שמאחורי למידה עמוקה. לשם כך, נמליץ על הספר [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) מאת Ian Goodfellow, Yoshua Bengio ו-Aaron Courville, הזמין גם באינטרנט ב[https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). +* מקרים עסקיים של שימוש ב-**AI בעסקים**. מומלץ לקחת את מסלול הלמידה [מבוא ל-AI למשתמשים עסקיים](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) ב-Microsoft Learn, או את [בית הספר העסקי של AI](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), שפותח בשיתוף עם [INSEAD](https://www.insead.edu/). +* **למידת מכונה קלאסית**, שמתוארת היטב בתוכנית הלימודים שלנו [למידת מכונה למתחילים](http://github.com/Microsoft/ML-for-Beginners). +* יישומי AI מעשיים שנבנו באמצעות **[שירותי קוגניציה](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. עבור זה, אנו ממליצים להתחיל במודולים של Microsoft Learn עבור [ראייה](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [עיבוד שפה טבעית](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[AI יוצר עם Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ואחרים. +* **מסגרות ענן ייחודיות ללמידת מכונה**, כגון [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), או [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). שקלו להשתמש במסלולי למידה כמו [בניית פתרונות למידת מכונה והפעלתם עם Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ו-[בניית פתרונות למידת מכונה והפעלתם עם Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum). +* **AI שיחתי** ו**בוטים לצ'אט**. יש מסלול למידה נפרד ל-[יצירת פתרונות AI שיחתי](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), וגם ניתן לעיין ב-[פוסט בלוג זה](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) לפרטים נוספים. +* **מתמטיקה עמוקה** שמאחורי הלמידה העמוקה. עבור זה, מומלץ לקרוא את [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) מאת Ian Goodfellow, Yoshua Bengio ו-Aaron Courville, הזמין גם באינטרנט ב-[https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -למבוא עדין לנושאי _AI בענן_ ניתן לשקול לקחת את מסלול הלמידה [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). +למבוא עדין לנושאי _AI בענן_ תוכלו לשקול לקחת את מסלול הלמידה [התחילו עם אינטיליגנציה מלאכותית ב-Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum). # תוכן -| | קישור לשיעור | PyTorch/Keras/TensorFlow | מעבדה | +| | קישור לשיעור | PyTorch/Keras/TensorFlow | מעבדה | | :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | | 0 | [הגדרת הקורס](./lessons/0-course-setup/setup.md) | [הגדר את סביבת הפיתוח שלך](./lessons/0-course-setup/how-to-run.md) | | -| I | [**מבוא לאינטליגנציה מלאכותית**](./lessons/1-Intro/README.md) | | | +| I | [**מבוא ל-AI**](./lessons/1-Intro/README.md) | | | | 01 | [מבוא והיסטוריה של AI](./lessons/1-Intro/README.md) | - | - | -| II | **אינטליגנציה מלאכותית סימבולית** | -| 02 | [ייצוג ידע ומערכות מומחים](./lessons/2-Symbolic/README.md) | [מערכות מומחים](./lessons/2-Symbolic/Animals.ipynb) / [אונטולוגיה](./lessons/2-Symbolic/FamilyOntology.ipynb) /[גרף קונספט](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | +| II | **AI סימבולי** | +| 02 | [ייצוג ידע ומערכות מומחים](./lessons/2-Symbolic/README.md) | [מערכות מומחים](./lessons/2-Symbolic/Animals.ipynb) / [אונטולוגיה](./lessons/2-Symbolic/FamilyOntology.ipynb) /[גרף מושגים](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | | III | [**מבוא לרשתות עצביות**](./lessons/3-NeuralNetworks/README.md) ||| -| 03 | [פרספטרון](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [دفتر הערות](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [מעבדה](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | -| 04 | [פרספטרון רב-שכבתי ויצירת המסגרת שלנו](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [دفتر הערות](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [מעבדה](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | -| 05 | [מבוא למסגרות עבודה (PyTorch/TensorFlow) והתאמת יתר](./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) | [מעבדה](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | -| IV | [**ראייה ממוחשבת**](./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)| [חקור ראייה ממוחשבת במיקרוסופט אזור](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | -| 06 | [מבוא לראייה ממוחשבת. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [دفتر הערות](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [מעבדה](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | +| 03 | [פרסטרון](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [מחברת](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [מעבדה](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | +| 04 | [פרסטרון רב-שכבתי ויצירת המסגרת שלנו](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [מחברת](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [מעבדה](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | +| 05 | [מבוא למסגרות (PyTorch/TensorFlow) והתחמקות מעודף התאמה](./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) | [מעבדה](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | +| IV | [**ראייה ממוחשבת**](./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)| [חקור ראייה ממוחשבת ב-Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | +| 06 | [מבוא לראייה ממוחשבת. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [מחברת](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [מעבדה](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | | 07 | [רשתות עצביות קונבולוציוניות](./lessons/4-ComputerVision/07-ConvNets/README.md) & [ארכיטקטורות 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) | [מעבדה](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) | | 08 | [רשתות מאומנות מראש ולמידת העברה](./lessons/4-ComputerVision/08-TransferLearning/README.md) ו[טריקים לאימון](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [מעבדה](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | | 09 | [אוטואנקודרים ו-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 | [רשתות מתנגדות יצירתיות והעברת סגנון אמנותי](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | -| 11 | [זיהוי אובייקטים](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [מעבדה](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | +| 10 | [רשתות אדברסיאליות גנרטיביות והעברת סגנון אמנותי](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | +| 11 | [זיהוי עצמים](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [מעבדה](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | | 12 | [סגמנטציה סמנטית. 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 | [**עיבוד שפה טבעית**](./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) | [חקור עיבוד שפה טבעית במיקרוסופט אזור](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| +| V | [**עיבוד שפה טבעית**](./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) | [חקור עיבוד שפה טבעית ב-Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| | 13 | [ייצוג טקסט. 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 | [הטמעות מילים סמנטיות. Word2Vec ו-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 | [מודל שפה. אימון הטמעות משלך](./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) | [מעבדה](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | +| 15 | [דוגמנות שפה. אימון הטמעות משלך](./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) | [מעבדה](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | | 16 | [רשתות עצביות חוזרות](./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 | [רשתות חוזרות יצירתיות](./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) | [מעבדה](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) | +| 17 | [רשתות גנרטיביות חוזרות](./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) | [מעבדה](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) | | 18 | [טרנספורמרים. 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 | [זיהוי ישויות ממוספרות](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [מעבדה](./lessons/5-NLP/19-NER/lab/README.md) | -| 20 | [מודלים גדולים של שפה, תכנות הפרומפט ומשימות בדוגמאות מועטות](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | -| VI | **טכניקות נוספות בבינה מלאכותית** || | -| 21 | [אלגוריתמים גנטיים](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [دفتر הערות](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | -| 22 | [למידה מחזקת עמוקה](./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) | [מעבדה](./lessons/6-Other/22-DeepRL/lab/README.md) | +| 19 | [זיהוי ישויות שמיות](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [מעבדה](./lessons/5-NLP/19-NER/lab/README.md) | +| 20 | [מודלים גדולים של שפה, תכנות הנחיות ומשימות עם מעט דוגמאות](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | | +| VI | **טכניקות אחרות ב-AI** || | +| 21 | [אלגוריתמים גנטיים](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [מחברת](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | +| 22 | [למידת חיזוק עמוקה](./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) | [מעבדה](./lessons/6-Other/22-DeepRL/lab/README.md) | | 23 | [מערכות מולטי-סוכן](./lessons/6-Other/23-MultiagentSystems/README.md) | | | -| VII | **אתיקה בבינה מלאכותית** | | | -| 24 | [אתיקה בבינה מלאכותית ובינה מלאכותית אחראית](./lessons/7-Ethics/README.md) | [Microsoft Learn: עקרונות בינה מלאכותית אחראית](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | +| VII | **אתיקה ב-AI** | | | +| 24 | [אתיקה ב-AI ו-AI אחראי](./lessons/7-Ethics/README.md) | [Microsoft Learn: עקרונות AI אחראי](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | | IX | **תוספות** | | | -| 25 | [רשתות מולטי-מודל, CLIP ו-VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [دفتر הערות](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | +| 25 | [רשתות מולטימודליות, CLIP ו-VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [מחברת](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | -## כל שיעור מכיל +## כל שיעור כולל * חומר לקריאה מוקדמת -* מחברות Jupyter ניתנות להרצה, שלרוב מותאמות למערכת מסוימת (**PyTorch** או **TensorFlow**). מחברת ההרצה כוללת גם חומר תיאורטי רב, לכן כדי להבין את הנושא יש לעבור לפחות על אחד הגירסאות של המחברת (או PyTorch או TensorFlow). -* **מעבדות** זמינות לחלק מהנושאים, המספקות לך הזדמנות לנסות ליישם את החומר שלמדת על בעיה מסוימת. -* חלק מהפרקים מכילים קישורים ל[**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) מודולים המכסים נושאים קשורים. +* מחברות Jupyter הניתנות להרצה, שלעיתים קרובות ייחודיות למסגרת (**PyTorch** או **TensorFlow**). המחברת הניתנת להרצה כוללת גם הרבה חומר תיאורטי, ולכן להבנת הנושא יש צורך לעבור לפחות על גרסה אחת של המחברת (או PyTorch או TensorFlow). +* **מעבדות** זמינות לכמה נושאים, המאפשרות לך לנסות ליישם את החומר שלמדת על בעיה ספציפית. +* חלק מהסעיפים מכילים קישורים ל[**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) מודולים המכסים נושאים קשורים. -## התחלה +## מתחילים -### 🎯 חדש בבינה מלאכותית? התחל כאן! +### 🎯 חדש ב-AI? התחילו כאן! -אם אתה חדש לחלוטין בבינה מלאכותית ורוצה דוגמאות מהירות עם התנסות מעשית, בדוק את [**דוגמאות ידידותיות למתחילים**](./examples/README.md)! הן כוללות: +אם אתה חדש לחלוטין ב-AI ורוצה דוגמאות מהירות ומעשיות, בדוק את [**דוגמאות למתחילים**](./examples/README.md)! הן כוללות: -- 🌟 **שלום עולם של בינה מלאכותית** - התכנית הראשונה שלך בבינה מלאכותית (זיהוי תבניות) +- 🌟 **שלום עולם AI** - תוכנית AI ראשונה שלך (זיהוי תבניות) - 🧠 **רשת עצבית פשוטה** - בניית רשת עצבית מאפס -- 🖼️ **מךין תמונות** - סיווג תמונות עם הערות מפורטות -- 💬 **רגש בטקסט** - ניתוח טקסט חיובי/שלילי -דוגמאות אלו מיועדות לעזור לך להבין מושגי בינה מלאכותית לפני הכניסה לתכנית הלימודים המלאה. +- 🖼️ **ממיין תמונות** - מיון תמונות עם הערות מפורטות +- 💬 **סנטימנט טקסט** - ניתוח טקסט חיובי/שלילי -### 📚 הגדרת תכנית לימודים מלאה +דוגמאות אלו נועדו לעזור לך להבין מושגי בינה מלאכותית לפני שמצטרפים לתוכנית הלימודים המלאה. -- יצרנו [שיעור הגדרה](./lessons/0-course-setup/setup.md) שיעזור לך בהגדרת סביבת הפיתוח שלך. - למורים, יצרנו גם [שיעור הגדרת תוכניות לימודים](./lessons/0-course-setup/for-teachers.md)! -- איך [להריץ את הקוד ב-VSCode או Codespace](./lessons/0-course-setup/how-to-run.md) +### 📚 הגדרת תוכנית לימודים מלאה -עקוב אחר השלבים האלה: +- יצרנו [שיעור הגדרה](./lessons/0-course-setup/setup.md) שיעזור לך בהגדרת סביבת הפיתוח שלך. - עבור מחנכים, יצרנו עבורך גם [שיעור הגדרת תוכנית לימודים](./lessons/0-course-setup/for-teachers.md)! +- כיצד [להריץ את הקוד ב-VSCode או ב-Codespace](./lessons/0-course-setup/how-to-run.md) -פרוש את המאגר: לחץ על כפתור ה-"Fork" בפינה הימנית העליונה של הדף. +עקוב אחר השלבים הבאים: -שכפל את המאגר: `git clone https://github.com/microsoft/AI-For-Beginners.git` +התפצל מהמאגר: לחץ על כפתור "Fork" בפינה הימנית-עליונה של עמוד זה. -אל תשכח להוסיף כוכב (🌟) למאגר הזה כדי למצוא אותו בקלות מאוחר יותר. +שכפל את המאגר: `git clone https://github.com/microsoft/AI-For-Beginners.git` -## פגוש לומדים נוספים +אל תשכח להעניק כוכב (🌟) לרפוזיטורי זה כדי למצוא אותו בקלות אחר כך. -הצטרף ל[שרת הדיסקורד הרשמי של בינה מלאכותית](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) לפגוש ולרשת עם לומדים נוספים הקורס ולקבל תמיכה. +## פגוש לומדים אחרים -אם יש לך משוב או שאלות בזמן בנייה בקר באתר [פורום מפתחי Azure AI Foundry](https://aka.ms/foundry/forum) +הצטרף לשרת ה-Discord הרשמי של AI שלנו בכתובת [official AI Discord server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) כדי להכיר וליצור קשר עם לומדים אחרים שלקחו את הקורס ולקבל תמיכה. -## חידונים +אם יש לך משוב על המוצר או שאלות בזמן הבנייה, בקר בפורום מפתחי Azure AI Foundry שלנו ב-[Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) -> **הערה לגבי חידונים**: כל החידונים נמצאים בתיקיית Quiz-app ב-etc\quiz-app, או [מקוון כאן](https://ff-quizzes.netlify.app/) הם מקושרים מתוך השיעורים, ניתן להריץ את אפליקציית החידון מקומית או לפרוס ל-Azure; עקוב אחרי ההוראות בתיקיית `quiz-app`. הם מתורגמים בהדרגה. +## בחנים -## דרושים עזרה +> **הערה בנוגע לבחנים**: כל הבחנים נמצאים בתיקיית Quiz-app בתיקייה etc\quiz-app, או ב-[Online Here](https://ff-quizzes.netlify.app/). הם מקושרים מתוך השיעורים, אפשר להריץ את אפליקציית הבחנים מקומית או לפרוס ב-Azure; עקוב אחר ההוראות בתיקיית `quiz-app`. הם מתורגמים בהדרגה. -יש לך הצעות או מצאת שגיאות כתיב או קוד? פתח נושא או צור בקשת משיכה. +## רוצים עזרה -## תודות מיוחדות +יש לך הצעות או מצאת טעויות איות או קוד? פתח בעיה או צור בקשת משיכה. -* **✍️ מחבר ראשי:** [דמיטרי סושניקוב](http://soshnikov.com), PhD -* **🔥 עורך:** [ג'ן לופר](https://twitter.com/jenlooper), PhD -* **🎨 מאייר סקצ'נוט:** [תומומי אימורה](https://twitter.com/girlie_mac) -* **✅ יוצר חידונים:** [לטיפה בללו](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) -* **🙏 תורמים מרכזיים:** [אבגניי פישצ'יק](https://github.com/Pe4enIks) +## תודה מיוחדת -## תכניות לימודים נוספות +* **✍️ מחבר ראשי:** [Dmitry Soshnikov](http://soshnikov.com), PhD +* **🔥 עורך:** [Jen Looper](https://twitter.com/jenlooper), PhD +* **🎨 מאייר סקצ'נוט:** [Tomomi Imura](https://twitter.com/girlie_mac) +* **✅ יוצר הבחנים:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) +* **🙏 תורמים מרכזיים:** [Evgenii Pishchik](https://github.com/Pe4enIks) -הצוות שלנו מייצר תוכניות לימודים נוספות! עיין ב: +## תוכניות לימודים נוספות - +הצוות שלנו מפיק תוכניות לימודים נוספות! בדוק: + + ### LangChain [![LangChain4j for Beginners](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js for Beginners](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain.js for Beginners](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) ---- +--- -### Azure / Edge / MCP / סוכנים +### Azure / Edge / MCP / Agents [![AZD for Beginners](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) [![Edge AI for Beginners](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) [![MCP for Beginners](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents for Beginners](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) - ---- +[![AI Agents for Beginners](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +--- + ### סדרת בינה מלאכותית גנרטיבית [![Generative AI for Beginners](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) [![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) [![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) ---- - -### ליבת הלמידה +--- + +### ליבת הלימודים [![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) [![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) [![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) [![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) [![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) [![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) +[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) ---- - -### סדרת Copilot +--- + +### סדרת קופיילוט [![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) [![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) - + -## לקבלת עזרה +## לקבלת עזרה -אם נתקעת או יש לך שאלות לגבי בניית אפליקציות בינה מלאכותית, הצטרף ללומדים אחרים ולמפתחים מנוסים בדיונים לגבי MCP. זו קהילה תומכת שבה שאלות מתקבלות בברכה וידע נעשה זמין בחופשיות. +אם נתקעת או יש לך שאלות לגבי בניית אפליקציות AI, הצטרף ללומדים ולמפתחים מנוסים בדיונים על MCP. זו קהילה תומכת שבה שאלות מתקבלות בברכה והידע משותף בחופשיות. -[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) +[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -אם יש לך משוב על מוצר או שגיאות בזמן הבנייה בקר: +אם יש לך משוב על המוצר או שגיאות בזמן הבנייה, בקר: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**כתב ויתור**: -מסמך זה תורגם באמצעות שירות תרגום מבוסס בינה מלאכותית [Co-op Translator](https://github.com/Azure/co-op-translator). למרות שאנו שואפים לדיוק, נא לשים לב כי תרגומים אוטומטיים עשויים להכיל שגיאות או אי-דיוקים. המסמך המקורי בשפת המקור שלו מהווה את המקור הסמכותי. למידע קריטי מומלץ להשתמש בתרגום מקצועי על ידי אדם. אנו לא אחראים לכל אי הבנה או פרשנות שגויה הנובעות משימוש בתרגום זה. +**כתב ויתור**: +מסמך זה תורגם באמצעות שירות תרגום מבוסס בינה מלאכותית [Co-op Translator](https://github.com/Azure/co-op-translator). למרות שאנו שואפים לדייק, יש לקחת בחשבון כי תרגומים אוטומטיים עלולים להכיל שגיאות או אי-דיוקים. יש להתייחס למסמך המקורי בשפת המקור כמקור הסמכות. למידע קריטי מומלץ להשתמש בתרגום מקצועי אנושי. אנו אינם אחראים לכל אי הבנה או פרשנות שגויה הנובעת מהשימוש בתרגום זה. \ No newline at end of file diff --git a/translations/he/SECURITY.md b/translations/he/SECURITY.md index 02dfc8c9..639bfdfa 100644 --- a/translations/he/SECURITY.md +++ b/translations/he/SECURITY.md @@ -1,12 +1,3 @@ - ## אבטחה מיקרוסופט מתייחסת ברצינות לאבטחת מוצרי התוכנה והשירותים שלה, כולל כל מאגרי הקוד הפתוח המנוהלים דרך הארגונים שלנו ב-GitHub, הכוללים את [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), ו-[הארגונים שלנו ב-GitHub](https://opensource.microsoft.com/). diff --git a/translations/he/etc/CODE_OF_CONDUCT.md b/translations/he/etc/CODE_OF_CONDUCT.md index 0205dd4c..db28f66d 100644 --- a/translations/he/etc/CODE_OF_CONDUCT.md +++ b/translations/he/etc/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # קוד ההתנהגות של קוד פתוח של מיקרוסופט הפרויקט הזה אימץ את [קוד ההתנהגות של קוד פתוח של מיקרוסופט](https://opensource.microsoft.com/codeofconduct/). diff --git a/translations/he/etc/CONTRIBUTING.md b/translations/he/etc/CONTRIBUTING.md index 59851e13..77140c82 100644 --- a/translations/he/etc/CONTRIBUTING.md +++ b/translations/he/etc/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # תרומה פרויקט זה מקבל בברכה תרומות והצעות. רוב התרומות דורשות ממך להסכים להסכם רישיון תורם (CLA) שמצהיר שיש לך את הזכות, ואתה אכן מעניק לנו את הזכויות להשתמש בתרומתך. לפרטים נוספים, בקר בכתובת https://cla.microsoft.com. diff --git a/translations/he/etc/Mindmap.md b/translations/he/etc/Mindmap.md index a7069040..e2304296 100644 --- a/translations/he/etc/Mindmap.md +++ b/translations/he/etc/Mindmap.md @@ -1,12 +1,3 @@ - # בינה מלאכותית ## [מבוא לבינה מלאכותית](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md) diff --git a/translations/he/etc/SUPPORT.md b/translations/he/etc/SUPPORT.md index 0d24027b..080c723a 100644 --- a/translations/he/etc/SUPPORT.md +++ b/translations/he/etc/SUPPORT.md @@ -1,12 +1,3 @@ - # תמיכה ## כיצד לדווח על בעיות ולקבל עזרה diff --git a/translations/he/etc/TRANSLATIONS.md b/translations/he/etc/TRANSLATIONS.md index 0564f9d7..b1453e5c 100644 --- a/translations/he/etc/TRANSLATIONS.md +++ b/translations/he/etc/TRANSLATIONS.md @@ -1,12 +1,3 @@ - # תרמו על ידי תרגום שיעורים אנחנו מזמינים אתכם לתרגם את השיעורים בתוכנית הלימודים הזו! diff --git a/translations/he/etc/quiz-app/README.md b/translations/he/etc/quiz-app/README.md index dfcd73a7..6536092f 100644 --- a/translations/he/etc/quiz-app/README.md +++ b/translations/he/etc/quiz-app/README.md @@ -1,12 +1,3 @@ - # חידונים החידונים האלו הם החידונים שלפני ואחרי ההרצאות בתוכנית הלימודים של AI בכתובת https://aka.ms/ai-beginners diff --git a/translations/he/examples/README.md b/translations/he/examples/README.md index 5e619b31..8d166431 100644 --- a/translations/he/examples/README.md +++ b/translations/he/examples/README.md @@ -1,12 +1,3 @@ - # דוגמאות AI ידידותיות למתחילים ברוכים הבאים! ספרייה זו מכילה דוגמאות פשוטות ועצמאיות שיעזרו לכם להתחיל עם AI ולמידת מכונה. כל דוגמה תוכננה להיות ידידותית למתחילים עם הערות מפורטות והסברים שלב אחר שלב. diff --git a/translations/he/lessons/0-course-setup/for-teachers.md b/translations/he/lessons/0-course-setup/for-teachers.md index 9cb84d08..25902094 100644 --- a/translations/he/lessons/0-course-setup/for-teachers.md +++ b/translations/he/lessons/0-course-setup/for-teachers.md @@ -1,12 +1,3 @@ - # למורים האם תרצו להשתמש בתוכנית הלימודים הזו בכיתה שלכם? אתם מוזמנים לעשות זאת! diff --git a/translations/he/lessons/0-course-setup/how-to-run.md b/translations/he/lessons/0-course-setup/how-to-run.md index 7e2ab95f..d64b0e43 100644 --- a/translations/he/lessons/0-course-setup/how-to-run.md +++ b/translations/he/lessons/0-course-setup/how-to-run.md @@ -1,12 +1,3 @@ - # כיצד להריץ את הקוד תכנית הלימודים הזו מכילה הרבה דוגמאות מעשיות ומעבדות שתרצו להריץ. כדי לעשות זאת, עליכם להיות מסוגלים להריץ קוד פייתון ב-Jupyter Notebooks המסופקים כחלק מתכנית הלימודים הזו. יש לכם כמה אפשרויות להרצת הקוד: diff --git a/translations/he/lessons/0-course-setup/setup.md b/translations/he/lessons/0-course-setup/setup.md index 825ed3d4..b6108acb 100644 --- a/translations/he/lessons/0-course-setup/setup.md +++ b/translations/he/lessons/0-course-setup/setup.md @@ -1,12 +1,3 @@ - # התחלת עבודה עם תכנית הלימודים הזו ## האם אתה סטודנט? diff --git a/translations/he/lessons/1-Intro/README.md b/translations/he/lessons/1-Intro/README.md index 77360771..5cc026d6 100644 --- a/translations/he/lessons/1-Intro/README.md +++ b/translations/he/lessons/1-Intro/README.md @@ -1,12 +1,3 @@ - # מבוא לבינה מלאכותית ![סיכום תוכן מבוא לבינה מלאכותית בציור](../../../../translated_images/he/ai-intro.bf28d1ac4235881c.webp) diff --git a/translations/he/lessons/1-Intro/assignment.md b/translations/he/lessons/1-Intro/assignment.md index 84d58fa9..d23bf674 100644 --- a/translations/he/lessons/1-Intro/assignment.md +++ b/translations/he/lessons/1-Intro/assignment.md @@ -1,12 +1,3 @@ - # ג'אם משחקים משחקים הם תחום שהושפע רבות מההתפתחויות בבינה מלאכותית ולמידת מכונה. במשימה זו, כתבו מאמר קצר על משחק שאתם אוהבים שהושפע מההתפתחות של הבינה המלאכותית. זה צריך להיות משחק מספיק ותיק כדי שהושפע ממספר סוגים של מערכות עיבוד מחשב. דוגמה טובה היא שחמט או גו, אך גם כדאי להסתכל על משחקי וידאו כמו פונג או פאק-מן. כתבו מאמר שמדבר על העבר, ההווה והעתיד של המשחק בהקשר של בינה מלאכותית. diff --git a/translations/he/lessons/2-Symbolic/README.md b/translations/he/lessons/2-Symbolic/README.md index 0b35fc21..5cf0d1ce 100644 --- a/translations/he/lessons/2-Symbolic/README.md +++ b/translations/he/lessons/2-Symbolic/README.md @@ -1,15 +1,6 @@ - # ייצוג ידע ומערכות מומחים -![תקציר של תוכן בינה מלאכותית סמנטית](../../../../../../translated_images/he/ai-symbolic.715a30cb610411a6.webp) +![תקציר של תוכן בינה מלאכותית סמנטית](../../../../translated_images/he/ai-symbolic.715a30cb610411a6.webp) > סקצ'נוט מאת [Tomomi Imura](https://twitter.com/girlie_mac) @@ -41,7 +32,7 @@ CO_OP_TRANSLATOR_METADATA: לכן, בעיית ה**ייצוג ידע** היא למצוא דרך יעילה לייצג ידע בתוך מחשב בצורת נתונים, כדי שניתן יהיה להשתמש בו באופן אוטומטי. זה ניתן לראות כספקטרום: -![ספקטרום ייצוג ידע](../../../../../../translated_images/he/knowledge-spectrum.b60df631852c0217.webp) +![ספקטרום ייצוג ידע](../../../../translated_images/he/knowledge-spectrum.b60df631852c0217.webp) > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) @@ -94,7 +85,7 @@ Python | תחביר בלוקים | הזחה אחד ההצלחות המוקדמות של הבינה המלאכותית הסמלית היו מה שנקרא **מערכות מומחים** - מערכות מחשב שמטרתן לפעול כמומחים בתחום בעיה מוגבל. הן התבססו על **בסיס ידע** שחולץ מאחד או יותר מומחים אנושיים, והכילו **מנוע היסק** שביצע היסק על בסיס זה. -![ארכיטקטורה אנושית](../../../../../../translated_images/he/arch-human.5d4d35f1bba3ab1c.webp) | ![מערכת מבוססת ידע](../../../../../../translated_images/he/arch-kbs.3ec5c150b09fa8da.webp) +![ארכיטקטורה אנושית](../../../../translated_images/he/arch-human.5d4d35f1bba3ab1c.webp) | ![מערכת מבוססת ידע](../../../../translated_images/he/arch-kbs.3ec5c150b09fa8da.webp) ---------------------------------------------|------------------------------------------------ מבנה מפושט של מערכת עצבית אנושית | ארכיטקטורה של מערכת מבוססת ידע @@ -106,7 +97,7 @@ Python | תחביר בלוקים | הזחה לדוגמה, נשקול את מערכת המומחה הבאה לקביעת חיה בהתבסס על התכונות הפיזיות שלה: -![עץ AND-OR](../../../../../../translated_images/he/AND-OR-Tree.5592d2c70187f283.webp) +![עץ AND-OR](../../../../translated_images/he/AND-OR-Tree.5592d2c70187f283.webp) > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/he/lessons/2-Symbolic/assignment.md b/translations/he/lessons/2-Symbolic/assignment.md index 4e7fc278..83503ce2 100644 --- a/translations/he/lessons/2-Symbolic/assignment.md +++ b/translations/he/lessons/2-Symbolic/assignment.md @@ -1,12 +1,3 @@ - # בניית אונטולוגיה בניית בסיס ידע עוסקת בקטלוג מודל שמייצג עובדות על נושא מסוים. בחרו נושא - כמו אדם, מקום או דבר - ואז בנו מודל של אותו נושא. השתמשו בכמה מהטכניקות ואסטרטגיות בניית המודל שתוארו בשיעור הזה. דוגמה יכולה להיות יצירת אונטולוגיה של סלון עם רהיטים, תאורה וכדומה. איך הסלון שונה מהמטבח? מהאמבטיה? איך אתם יודעים שזה סלון ולא חדר אוכל? השתמשו ב-[Protégé](https://protege.stanford.edu/) כדי לבנות את האונטולוגיה שלכם. diff --git a/translations/he/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/he/lessons/3-NeuralNetworks/03-Perceptron/README.md index 3044e913..550d2eec 100644 --- a/translations/he/lessons/3-NeuralNetworks/03-Perceptron/README.md +++ b/translations/he/lessons/3-NeuralNetworks/03-Perceptron/README.md @@ -1,12 +1,3 @@ - # מבוא לרשתות עצביות: פרספטרון ## [שאלון לפני השיעור](https://ff-quizzes.netlify.app/en/ai/quiz/5) @@ -15,7 +6,7 @@ CO_OP_TRANSLATOR_METADATA: | | | |--------------|-----------| -|Frank Rosenblatt | The Mark 1 Perceptron| +|Frank Rosenblatt | The Mark 1 Perceptron| > תמונות [מוויקיפדיה](https://en.wikipedia.org/wiki/Perceptron) @@ -34,7 +25,7 @@ y(x) = f(wTx) כאשר f היא פונקציית הפעלה מדרגה. - + ## אימון הפרספטרון diff --git a/translations/he/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/he/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md index fddc054b..55c57ba6 100644 --- a/translations/he/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md +++ b/translations/he/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md @@ -1,12 +1,3 @@ - # סיווג רב-קטגורי עם פרספטרון תרגיל מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/README.md index 5cd51b6d..bc8ec70b 100644 --- a/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/README.md +++ b/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/README.md @@ -1,12 +1,3 @@ - # מבוא לרשתות נוירונים. פרספטרון רב-שכבתי בפרק הקודם למדתם על מודל הרשת הנוירונית הפשוט ביותר - פרספטרון חד-שכבתי, מודל סיווג ליניארי לשתי קטגוריות. @@ -65,7 +56,7 @@ CO_OP_TRANSLATOR_METADATA: שימו לב שהחלק השמאלי ביותר של כל הביטויים הללו זהה, ולכן ניתן לחשב נגזרות בצורה יעילה על ידי התחלה מפונקציית הפסד והתקדמות "אחורה" דרך גרף החישוב. לכן שיטת האימון של פרספטרון רב-שכבתי נקראת **בקפרופגציה**, או 'backprop'. -compute graph +compute graph > TODO: ציון מקור התמונה diff --git a/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md index 9a8cb5c7..56c6dd59 100644 --- a/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md +++ b/translations/he/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md @@ -1,12 +1,3 @@ - # סיווג MNIST עם המסגרת שלנו מטלת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/he/lessons/3-NeuralNetworks/05-Frameworks/README.md index c7924ad3..1b04f687 100644 --- a/translations/he/lessons/3-NeuralNetworks/05-Frameworks/README.md +++ b/translations/he/lessons/3-NeuralNetworks/05-Frameworks/README.md @@ -1,12 +1,3 @@ - # מסגרות רשתות עצביות כפי שלמדנו כבר, כדי לאמן רשתות עצביות בצורה יעילה, יש לבצע שני דברים: diff --git a/translations/he/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/he/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md index eb6c09d3..977d315a 100644 --- a/translations/he/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md +++ b/translations/he/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md @@ -1,12 +1,3 @@ - # סיווג עם PyTorch/TensorFlow מטלת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/3-NeuralNetworks/README.md b/translations/he/lessons/3-NeuralNetworks/README.md index 95411e5b..e4d28dc5 100644 --- a/translations/he/lessons/3-NeuralNetworks/README.md +++ b/translations/he/lessons/3-NeuralNetworks/README.md @@ -1,12 +1,3 @@ - # מבוא לרשתות עצביות ![סיכום תוכן מבוא לרשתות עצביות בציור](../../../../translated_images/he/ai-neuralnetworks.1c687ae40bc86e83.webp) diff --git a/translations/he/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/he/lessons/4-ComputerVision/06-IntroCV/README.md index 8050a666..7eca2bac 100644 --- a/translations/he/lessons/4-ComputerVision/06-IntroCV/README.md +++ b/translations/he/lessons/4-ComputerVision/06-IntroCV/README.md @@ -1,12 +1,3 @@ - # מבוא לראייה ממוחשבת [ראייה ממוחשבת](https://wikipedia.org/wiki/Computer_vision) היא תחום שמטרתו לאפשר למחשבים להבין ברמה גבוהה תמונות דיגיטליות. זו הגדרה רחבה למדי, כי *הבנה* יכולה להתייחס לדברים רבים, כולל זיהוי אובייקט בתמונה (**זיהוי אובייקטים**), הבנת מה מתרחש (**זיהוי אירועים**), תיאור תמונה בטקסט, או שחזור סצנה בתלת-ממד. יש גם משימות מיוחדות הקשורות לתמונות של בני אדם: הערכת גיל ורגשות, זיהוי פנים וזיהוי זהות, והערכת תנוחה בתלת-ממד, בין היתר. @@ -115,7 +106,7 @@ im = cv2.cvtColor(im,cv2.COLOR_BGR2RGB) במעבדה זו, תצלמו וידאו עם מחוות פשוטות, והמטרה שלכם היא לחלץ תנועות למעלה/למטה/שמאלה/ימינה באמצעות זרימה אופטית. -פריים תנועת כף יד +פריים תנועת כף יד --- diff --git a/translations/he/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/he/lessons/4-ComputerVision/06-IntroCV/lab/README.md index a7d54c87..4df51739 100644 --- a/translations/he/lessons/4-ComputerVision/06-IntroCV/lab/README.md +++ b/translations/he/lessons/4-ComputerVision/06-IntroCV/lab/README.md @@ -1,12 +1,3 @@ - # זיהוי תנועות באמצעות זרימה אופטית מטלת מעבדה מתוך [תוכנית הלימודים למתחילים ב-AI](https://aka.ms/ai-beginners). diff --git a/translations/he/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/he/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md index bc3ad896..3c8042da 100644 --- a/translations/he/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md +++ b/translations/he/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md @@ -1,12 +1,3 @@ - # ארכיטקטורות CNN ידועות ### VGG-16 @@ -25,7 +16,7 @@ VGG-16 היא רשת שהשיגה דיוק של 92.7% בסיווג ImageNet top- ResNet היא משפחת מודלים שהוצעה על ידי Microsoft Research בשנת 2015. הרעיון המרכזי של ResNet הוא שימוש ב**בלוקים שאריתיים**: - + > תמונה מ-[המאמר הזה](https://arxiv.org/pdf/1512.03385.pdf) @@ -37,7 +28,7 @@ ResNet היא משפחת מודלים שהוצעה על ידי Microsoft Researc ארכיטקטורת Google Inception לוקחת את הרעיון הזה צעד אחד קדימה, ובונה כל שכבת רשת כקומבינציה של מספר מסלולים שונים: - + > תמונה מ-[Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) diff --git a/translations/he/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/he/lessons/4-ComputerVision/07-ConvNets/README.md index ef264fd1..5a558811 100644 --- a/translations/he/lessons/4-ComputerVision/07-ConvNets/README.md +++ b/translations/he/lessons/4-ComputerVision/07-ConvNets/README.md @@ -1,12 +1,3 @@ - # רשתות נוירונים קונבולוציוניות כבר ראינו בעבר שרשתות נוירונים טובות מאוד בעבודה עם תמונות, ואפילו פרספטרון בעל שכבה אחת מסוגל לזהות ספרות כתובות ביד מתוך מאגר הנתונים MNIST בדיוק סביר. עם זאת, מאגר הנתונים MNIST הוא מיוחד מאוד, וכל הספרות ממורכזות בתוך התמונה, מה שהופך את המשימה לפשוטה יותר. @@ -24,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA: לדוגמה, אם ניישם פילטרים של קצה אנכי וקצה אופקי בגודל 3x3 על הספרות של MNIST, נוכל לקבל הדגשות (למשל, ערכים גבוהים) היכן שיש קצוות אנכיים ואופקיים בתמונה המקורית שלנו. כך ניתן להשתמש בשני הפילטרים הללו כדי "לחפש" קצוות. באופן דומה, ניתן לעצב פילטרים שונים כדי לחפש תבניות בסיסיות אחרות: - + > תמונה של [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html) diff --git a/translations/he/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/he/lessons/4-ComputerVision/07-ConvNets/lab/README.md index ab1afdd4..52820825 100644 --- a/translations/he/lessons/4-ComputerVision/07-ConvNets/lab/README.md +++ b/translations/he/lessons/4-ComputerVision/07-ConvNets/lab/README.md @@ -1,12 +1,3 @@ - # סיווג פנים של חיות מחמד משימת מעבדה מתוך [תוכנית הלימודים AI למתחילים](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/he/lessons/4-ComputerVision/08-TransferLearning/README.md index 3a6409d1..75106226 100644 --- a/translations/he/lessons/4-ComputerVision/08-TransferLearning/README.md +++ b/translations/he/lessons/4-ComputerVision/08-TransferLearning/README.md @@ -1,12 +1,3 @@ - # רשתות מאומנות מראש ולמידת העברה אימון רשתות CNN יכול לקחת זמן רב, ודורש כמות גדולה של נתונים. עם זאת, חלק גדול מהזמן מושקע בלמידת המסננים ברמה נמוכה שהרשת יכולה להשתמש בהם כדי לחלץ דפוסים מתמונות. עולה שאלה טבעית - האם ניתן להשתמש ברשת עצבית שאומנה על מערך נתונים אחד ולהתאים אותה לסיווג תמונות שונות מבלי לדרוש תהליך אימון מלא? diff --git a/translations/he/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/he/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md index 223ced74..258ed0bc 100644 --- a/translations/he/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md +++ b/translations/he/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md @@ -1,12 +1,3 @@ - # טריקים לאימון למידה עמוקה ככל שרשתות עצביות נעשות עמוקות יותר, תהליך האימון שלהן הופך למאתגר יותר ויותר. אחת הבעיות המרכזיות היא מה שמכונה [גרדיאנטים נעלמים](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) או [גרדיאנטים מתפוצצים](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [הפוסט הזה](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) מספק מבוא טוב לבעיות הללו. diff --git a/translations/he/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/he/lessons/4-ComputerVision/08-TransferLearning/lab/README.md index 59bbb0d1..dd90eb4a 100644 --- a/translations/he/lessons/4-ComputerVision/08-TransferLearning/lab/README.md +++ b/translations/he/lessons/4-ComputerVision/08-TransferLearning/lab/README.md @@ -1,12 +1,3 @@ - # סיווג חיות מחמד של אוקספורד באמצעות למידה מעבירה משימת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/he/lessons/4-ComputerVision/09-Autoencoders/README.md index d0f38c51..ced4a5ad 100644 --- a/translations/he/lessons/4-ComputerVision/09-Autoencoders/README.md +++ b/translations/he/lessons/4-ComputerVision/09-Autoencoders/README.md @@ -1,12 +1,3 @@ - # אוטואנקודרים בעת אימון רשתות CNN, אחת הבעיות היא הצורך בכמות גדולה של נתונים מתויגים. במקרה של סיווג תמונות, יש להפריד את התמונות לקבוצות שונות, מה שדורש מאמץ ידני. @@ -46,7 +37,7 @@ VAE הוא אוטואנקודר שלומד לחזות *התפלגות סטטיס * אנו דוגמים וקטור `sample` מההתפלגות N(zmean,exp(zlog\_sigma)) * המפענח מנסה לפענח את התמונה המקורית באמצעות `sample` כוקטור קלט - + > תמונה מתוך [פוסט בבלוג](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) מאת Isaak Dykeman @@ -57,13 +48,13 @@ VAE הוא אוטואנקודר שלומד לחזות *התפלגות סטטיס יתרון חשוב של VAEs הוא שהם מאפשרים לנו ליצור תמונות חדשות יחסית בקלות, מכיוון שאנו יודעים מאיזו התפלגות לדגום וקטורים לטנטיים. לדוגמה, אם נאמן VAE עם וקטור לטנטי דו-ממדי על MNIST, נוכל לשנות את רכיבי הוקטור הלטנטי כדי לקבל ספרות שונות: -vaemnist +vaemnist > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) שימו לב כיצד התמונות מתמזגות זו בזו, כאשר אנו מתחילים לקבל וקטורים לטנטיים מחלקים שונים של מרחב הפרמטרים הלטנטיים. ניתן גם להמחיש את המרחב הזה ב-2D: -vaemnist cluster +vaemnist cluster > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/he/lessons/4-ComputerVision/10-GANs/README.md b/translations/he/lessons/4-ComputerVision/10-GANs/README.md index d85ce879..8dadf544 100644 --- a/translations/he/lessons/4-ComputerVision/10-GANs/README.md +++ b/translations/he/lessons/4-ComputerVision/10-GANs/README.md @@ -1,12 +1,3 @@ - # רשתות גנרטיביות מתחרותיות (GANs) בפרק הקודם למדנו על **מודלים גנרטיביים**: מודלים שיכולים לייצר תמונות חדשות הדומות לאלו שבמערך האימון. VAE היה דוגמה טובה למודל גנרטיבי. @@ -17,7 +8,7 @@ CO_OP_TRANSLATOR_METADATA: הרעיון המרכזי של GAN הוא להפעיל שתי רשתות נוירונים שמתאמנות אחת נגד השנייה: - + > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) @@ -41,7 +32,7 @@ CO_OP_TRANSLATOR_METADATA: > ✅ מכיוון ששכבת הקונבולוציה מיושמת כפילטר לינארי שעובר על התמונה, deconvolution דומה למעשה לקונבולוציה, וניתן ליישם אותו באמצעות אותה לוגיקה של שכבה. - + > תמונה מאת [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/he/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/he/lessons/4-ComputerVision/11-ObjectDetection/README.md index dc647592..e4736954 100644 --- a/translations/he/lessons/4-ComputerVision/11-ObjectDetection/README.md +++ b/translations/he/lessons/4-ComputerVision/11-ObjectDetection/README.md @@ -1,12 +1,3 @@ - # זיהוי אובייקטים המודלים של סיווג תמונות שעסקנו בהם עד כה לקחו תמונה והפיקו תוצאה קטגורית, כמו הקטגוריה 'מספר' בבעיה של MNIST. עם זאת, במקרים רבים אנחנו לא רוצים רק לדעת שתמונה מציגה אובייקטים - אנחנו רוצים להיות מסוגלים לקבוע את המיקום המדויק שלהם. זה בדיוק הנקודה של **זיהוי אובייקטים**. diff --git a/translations/he/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/he/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md index 8563325c..54553bba 100644 --- a/translations/he/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md +++ b/translations/he/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md @@ -1,12 +1,3 @@ - # זיהוי ראשים באמצעות Hollywood Heads Dataset מטלת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/he/lessons/4-ComputerVision/12-Segmentation/README.md index e49b5b2f..61d7872d 100644 --- a/translations/he/lessons/4-ComputerVision/12-Segmentation/README.md +++ b/translations/he/lessons/4-ComputerVision/12-Segmentation/README.md @@ -1,12 +1,3 @@ - # סגמנטציה למדנו בעבר על זיהוי אובייקטים, שמאפשר לנו לאתר אובייקטים בתמונה על ידי חיזוי *תיבות גבול*. עם זאת, עבור משימות מסוימות אנחנו לא רק צריכים תיבות גבול, אלא גם לוקליזציה מדויקת יותר של האובייקט. משימה זו נקראת **סגמנטציה**. @@ -20,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA: לדוגמה, בסגמנטציה של מופעים, הכבשים הללו הן אובייקטים שונים, אך בסגמנטציה סמנטית כל הכבשים מיוצגות כקטגוריה אחת. - + > תמונה מתוך [הפוסט הזה](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) @@ -29,7 +20,7 @@ CO_OP_TRANSLATOR_METADATA: * **מקודד** שמחלץ תכונות מהתמונה המקורית. * **מפענח** שממיר את התכונות הללו לתוך **תמונת המסכה**, עם אותו גודל ומספר ערוצים התואם למספר הקטגוריות. - + > תמונה מתוך [הפרסום הזה](https://arxiv.org/pdf/2001.05566.pdf) @@ -43,7 +34,7 @@ CO_OP_TRANSLATOR_METADATA: > ✅ טכניקה זו מתאימה במיוחד לסוג זה של הדמיה רפואית, אך אילו יישומים נוספים בעולם האמיתי אתם יכולים לדמיין? -navi +navi > תמונה מתוך מאגר PH2 diff --git a/translations/he/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/he/lessons/4-ComputerVision/12-Segmentation/lab/README.md index 63c5f1fb..42747ea6 100644 --- a/translations/he/lessons/4-ComputerVision/12-Segmentation/lab/README.md +++ b/translations/he/lessons/4-ComputerVision/12-Segmentation/lab/README.md @@ -1,12 +1,3 @@ - # חיתוך גוף האדם משימת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/4-ComputerVision/README.md b/translations/he/lessons/4-ComputerVision/README.md index 413ad21e..48ccc839 100644 --- a/translations/he/lessons/4-ComputerVision/README.md +++ b/translations/he/lessons/4-ComputerVision/README.md @@ -1,12 +1,3 @@ - # ראייה ממוחשבת ![סיכום תוכן ראייה ממוחשבת באיור](../../../../translated_images/he/ai-computervision.6506ebebac3fbf76.webp) diff --git a/translations/he/lessons/5-NLP/13-TextRep/README.md b/translations/he/lessons/5-NLP/13-TextRep/README.md index 823d0ad8..5bef3917 100644 --- a/translations/he/lessons/5-NLP/13-TextRep/README.md +++ b/translations/he/lessons/5-NLP/13-TextRep/README.md @@ -1,12 +1,3 @@ - # ייצוג טקסט כטנסורים ## [מבחן לפני השיעור](https://ff-quizzes.netlify.app/en/ai/quiz/25) @@ -25,7 +16,7 @@ CO_OP_TRANSLATOR_METADATA: אם אנחנו רוצים לפתור משימות עיבוד שפה טבעית (NLP) באמצעות רשתות נוירונים, אנחנו צריכים דרך לייצג טקסט כטנסורים. מחשבים כבר מייצגים תווים טקסטואליים כמספרים שממופים לגופנים על המסך שלך באמצעות קידודים כמו ASCII או UTF-8. -תמונה המציגה דיאגרמה שממפה תו לייצוג ASCII ובינארי +תמונה המציגה דיאגרמה שממפה תו לייצוג ASCII ובינארי > [מקור התמונה](https://www.seobility.net/en/wiki/ASCII) @@ -48,7 +39,7 @@ CO_OP_TRANSLATOR_METADATA: כאשר פותרים משימות כמו סיווג טקסט, אנו צריכים להיות מסוגלים לייצג טקסט על ידי וקטור בגודל קבוע, אותו נשתמש כקלט למסווג הסופי הצפוף. אחת הדרכים הפשוטות לעשות זאת היא לשלב את כל ייצוגי המילים הבודדות, למשל על ידי חיבורם. אם נחבר את קידודי ה-one-hot של כל מילה, נקבל וקטור של תדירויות, שמראה כמה פעמים כל מילה מופיעה בתוך הטקסט. ייצוג כזה של טקסט נקרא **bag of words** (BoW). - + > תמונה מאת המחבר diff --git a/translations/he/lessons/5-NLP/13-TextRep/assignment.md b/translations/he/lessons/5-NLP/13-TextRep/assignment.md index 83dd4cae..e66469f8 100644 --- a/translations/he/lessons/5-NLP/13-TextRep/assignment.md +++ b/translations/he/lessons/5-NLP/13-TextRep/assignment.md @@ -1,12 +1,3 @@ - # משימה: מחברות באמצעות המחברות הקשורות לשיעור זה (בגרסת PyTorch או TensorFlow), הריצו אותן מחדש עם מערך נתונים משלכם, אולי אחד מ-Kaggle, בשימוש עם קרדיט מתאים. כתבו מחדש את המחברת כדי להדגיש את הממצאים שלכם. נסו מערכי נתונים חדשניים שעשויים להיות מפתיעים, כמו [זה על תצפיות עב"מים](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) מ-NUFORC. diff --git a/translations/he/lessons/5-NLP/14-Embeddings/README.md b/translations/he/lessons/5-NLP/14-Embeddings/README.md index a5416f77..520298ef 100644 --- a/translations/he/lessons/5-NLP/14-Embeddings/README.md +++ b/translations/he/lessons/5-NLP/14-Embeddings/README.md @@ -1,12 +1,3 @@ - # הטמעות ## [שאלון לפני השיעור](https://ff-quizzes.netlify.app/en/ai/quiz/27) diff --git a/translations/he/lessons/5-NLP/14-Embeddings/assignment.md b/translations/he/lessons/5-NLP/14-Embeddings/assignment.md index ae909f92..d5de7884 100644 --- a/translations/he/lessons/5-NLP/14-Embeddings/assignment.md +++ b/translations/he/lessons/5-NLP/14-Embeddings/assignment.md @@ -1,12 +1,3 @@ - # משימה: מחברות בעזרת המחברות הקשורות לשיעור זה (בגרסת PyTorch או TensorFlow), הריצו אותן מחדש עם מערך נתונים משלכם, אולי כזה שמצאתם ב-Kaggle, תוך ציון המקור. ערכו מחדש את המחברת כדי להדגיש את הממצאים שלכם. נסו סוג אחר של מערך נתונים ותעדו את הממצאים שלכם, תוך שימוש בטקסט כמו [מילות השירים של הביטלס](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics). diff --git a/translations/he/lessons/5-NLP/15-LanguageModeling/README.md b/translations/he/lessons/5-NLP/15-LanguageModeling/README.md index 18530b22..4089ca17 100644 --- a/translations/he/lessons/5-NLP/15-LanguageModeling/README.md +++ b/translations/he/lessons/5-NLP/15-LanguageModeling/README.md @@ -1,12 +1,3 @@ - # מודל שפה הטמעות סמנטיות, כמו Word2Vec ו-GloVe, הן למעשה צעד ראשון לקראת **מודל שפה** - יצירת מודלים שמבינים (או מייצגים) בצורה כלשהי את טבע השפה. diff --git a/translations/he/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/he/lessons/5-NLP/15-LanguageModeling/lab/README.md index 390a075b..cd4fa476 100644 --- a/translations/he/lessons/5-NLP/15-LanguageModeling/lab/README.md +++ b/translations/he/lessons/5-NLP/15-LanguageModeling/lab/README.md @@ -1,12 +1,3 @@ - # אימון מודל Skip-Gram משימת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/5-NLP/16-RNN/README.md b/translations/he/lessons/5-NLP/16-RNN/README.md index b26c7ed7..b97a414e 100644 --- a/translations/he/lessons/5-NLP/16-RNN/README.md +++ b/translations/he/lessons/5-NLP/16-RNN/README.md @@ -1,12 +1,3 @@ - # רשתות עצביות חוזרות ## [שאלון לפני ההרצאה](https://ff-quizzes.netlify.app/en/ai/quiz/31) @@ -31,7 +22,7 @@ CO_OP_TRANSLATOR_METADATA: לתא RNN פשוט יש שני מטריצות משקל בפנים: אחת ממירה סמל קלט (נקרא לה W), ואחת ממירה מצב קלט (H). במקרה זה, הפלט של הרשת מחושב כ-σ(W×Xi+H×Si-1+b), כאשר σ היא פונקציית האקטיבציה ו-b הוא הטיה נוספת. -אנטומיה של תא RNN +אנטומיה של תא RNN > תמונה מאת המחבר diff --git a/translations/he/lessons/5-NLP/16-RNN/assignment.md b/translations/he/lessons/5-NLP/16-RNN/assignment.md index 5920ae56..93b180ad 100644 --- a/translations/he/lessons/5-NLP/16-RNN/assignment.md +++ b/translations/he/lessons/5-NLP/16-RNN/assignment.md @@ -1,12 +1,3 @@ - # משימה: מחברות באמצעות המחברות הקשורות לשיעור זה (בגרסת PyTorch או TensorFlow), הריצו אותן מחדש עם מערך נתונים משלכם, אולי כזה מ-Kaggle, תוך שימוש עם ייחוס מתאים. כתבו מחדש את המחברת כדי להדגיש את הממצאים שלכם. נסו סוג אחר של מערך נתונים ותעדו את הממצאים שלכם, באמצעות טקסט כמו [מערך הנתונים הזה מתחרות Kaggle על ציוצי מזג אוויר](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv). diff --git a/translations/he/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/he/lessons/5-NLP/17-GenerativeNetworks/README.md index ff966982..bb176c23 100644 --- a/translations/he/lessons/5-NLP/17-GenerativeNetworks/README.md +++ b/translations/he/lessons/5-NLP/17-GenerativeNetworks/README.md @@ -1,12 +1,3 @@ - # רשתות גנרטיביות ## [שאלון לפני ההרצאה](https://ff-quizzes.netlify.app/en/ai/quiz/33) @@ -36,7 +27,7 @@ CO_OP_TRANSLATOR_METADATA: בעת יצירת טקסט (בזמן הסקת מסקנות), נתחיל עם **הנחיה** כלשהי, שתועבר דרך תאי RNN כדי ליצור את מצב הביניים שלה, ואז מהמצב הזה מתחילה היצירה. ניצור תו אחד בכל פעם, ונעביר את המצב ואת התו שנוצר לתא RNN נוסף כדי ליצור את הבא, עד שניצור מספיק תווים. - + > תמונה מאת המחבר diff --git a/translations/he/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/he/lessons/5-NLP/17-GenerativeNetworks/lab/README.md index e8087491..97ee5204 100644 --- a/translations/he/lessons/5-NLP/17-GenerativeNetworks/lab/README.md +++ b/translations/he/lessons/5-NLP/17-GenerativeNetworks/lab/README.md @@ -1,12 +1,3 @@ - # יצירת טקסט ברמת מילים באמצעות RNNs משימת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/5-NLP/18-Transformers/README.md b/translations/he/lessons/5-NLP/18-Transformers/README.md index 34df8704..3f590a65 100644 --- a/translations/he/lessons/5-NLP/18-Transformers/README.md +++ b/translations/he/lessons/5-NLP/18-Transformers/README.md @@ -1,12 +1,3 @@ - # מנגנוני קשב ומודלים של טרנספורמרים ## [שאלון לפני ההרצאה](https://ff-quizzes.netlify.app/en/ai/quiz/35) @@ -56,7 +47,7 @@ CO_OP_TRANSLATOR_METADATA: * הטמעה ניתנת לאימון, בדומה להטמעת טוקנים. זו הגישה שנשקול כאן. אנו מיישמים שכבות הטמעה על גבי הטוקנים והמיקומים שלהם, ומקבלים וקטורי הטמעה באותם ממדים, אותם אנו מחברים יחד. * פונקציית קידוד מיקום קבועה, כפי שהוצע במאמר המקורי. - + > תמונה מאת המחבר diff --git a/translations/he/lessons/5-NLP/18-Transformers/assignment.md b/translations/he/lessons/5-NLP/18-Transformers/assignment.md index d83adede..5255d60a 100644 --- a/translations/he/lessons/5-NLP/18-Transformers/assignment.md +++ b/translations/he/lessons/5-NLP/18-Transformers/assignment.md @@ -1,12 +1,3 @@ - # משימה: Transformers התנסו ב-Transformers על HuggingFace! נסו כמה מהסקריפטים שהם מספקים כדי לעבוד עם המודלים השונים הזמינים באתר שלהם: https://huggingface.co/docs/transformers/run_scripts. נסו אחד מהמאגרי הנתונים שלהם, ולאחר מכן ייבאו אחד משלכם מתוך תוכנית הלימודים הזו או מתוך Kaggle ובדקו אם תוכלו ליצור טקסטים מעניינים. צרו מחברת עם הממצאים שלכם. diff --git a/translations/he/lessons/5-NLP/19-NER/README.md b/translations/he/lessons/5-NLP/19-NER/README.md index df2a9d59..bc7030fa 100644 --- a/translations/he/lessons/5-NLP/19-NER/README.md +++ b/translations/he/lessons/5-NLP/19-NER/README.md @@ -1,12 +1,3 @@ - # זיהוי ישויות בשם עד כה, התמקדנו בעיקר במשימה אחת של עיבוד שפה טבעית (NLP) - סיווג. עם זאת, ישנן משימות נוספות שניתן לבצע באמצעות רשתות עצביות. אחת מהן היא **[זיהוי ישויות בשם](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), שעוסקת בזיהוי ישויות ספציפיות בטקסט, כמו מקומות, שמות אנשים, טווחי זמן, נוסחאות כימיות ועוד. @@ -17,7 +8,7 @@ CO_OP_TRANSLATOR_METADATA: נניח שברצונך לפתח צ'אטבוט בשפה טבעית, בדומה ל-Amazon Alexa או Google Assistant. הדרך שבה צ'אטבוטים חכמים עובדים היא *להבין* מה המשתמש רוצה על ידי ביצוע סיווג טקסט על המשפט שהוזן. תוצאת הסיווג היא מה שנקרא **כוונה** (intent), שמגדירה מה הצ'אטבוט צריך לעשות. -Bot NER +Bot NER > תמונה מאת המחבר diff --git a/translations/he/lessons/5-NLP/19-NER/lab/README.md b/translations/he/lessons/5-NLP/19-NER/lab/README.md index 50784b88..20f0a045 100644 --- a/translations/he/lessons/5-NLP/19-NER/lab/README.md +++ b/translations/he/lessons/5-NLP/19-NER/lab/README.md @@ -1,12 +1,3 @@ - # זיהוי ישויות בשם (NER) משימת מעבדה מתוך [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/he/lessons/5-NLP/20-LangModels/README.md b/translations/he/lessons/5-NLP/20-LangModels/README.md index cfb6a9f7..768d0b1b 100644 --- a/translations/he/lessons/5-NLP/20-LangModels/README.md +++ b/translations/he/lessons/5-NLP/20-LangModels/README.md @@ -1,12 +1,3 @@ - # מודלים גדולים של שפה מאומנים מראש בכל המשימות הקודמות שלנו, אימנו רשת עצבית לבצע משימה מסוימת באמצעות מערך נתונים מתויג. עם מודלים גדולים של טרנספורמרים, כמו BERT, אנו משתמשים במידול שפה בצורה עצמאית כדי לבנות מודל שפה, אשר לאחר מכן מתמחה למשימה ספציפית באמצעות אימון נוסף בתחום מסוים. עם זאת, הוכח כי מודלים גדולים של שפה יכולים גם לפתור משימות רבות ללא כל אימון ספציפי לתחום. משפחת מודלים המסוגלת לעשות זאת נקראת **GPT**: Generative Pre-Trained Transformer. diff --git a/translations/he/lessons/5-NLP/README.md b/translations/he/lessons/5-NLP/README.md index 9945a46c..53d366ac 100644 --- a/translations/he/lessons/5-NLP/README.md +++ b/translations/he/lessons/5-NLP/README.md @@ -1,12 +1,3 @@ - # עיבוד שפה טבעית ![סיכום משימות NLP בציור](../../../../translated_images/he/ai-nlp.b22dcb8ca4707cea.webp) diff --git a/translations/he/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/he/lessons/6-Other/21-GeneticAlgorithms/README.md index 3db5b20d..3aae8181 100644 --- a/translations/he/lessons/6-Other/21-GeneticAlgorithms/README.md +++ b/translations/he/lessons/6-Other/21-GeneticAlgorithms/README.md @@ -1,12 +1,3 @@ - # אלגוריתמים גנטיים ## [שאלון לפני ההרצאה](https://ff-quizzes.netlify.app/en/ai/quiz/41) diff --git a/translations/he/lessons/6-Other/22-DeepRL/README.md b/translations/he/lessons/6-Other/22-DeepRL/README.md index fd381c52..d02c0bbf 100644 --- a/translations/he/lessons/6-Other/22-DeepRL/README.md +++ b/translations/he/lessons/6-Other/22-DeepRL/README.md @@ -1,12 +1,3 @@ - # למידה חיזוקית עמוקה למידה חיזוקית (RL) נחשבת לאחד מהפרדיגמות הבסיסיות של למידת מכונה, לצד למידה מונחית ולמידה בלתי מונחית. בעוד שבלמידה מונחית אנו מסתמכים על מערך נתונים עם תוצאות ידועות, RL מבוססת על **למידה מתוך עשייה**. לדוגמה, כשאנו רואים לראשונה משחק מחשב, אנו מתחילים לשחק, גם בלי לדעת את החוקים, ובמהרה אנו מצליחים לשפר את הכישורים שלנו רק דרך תהליך המשחק והתאמת ההתנהגות שלנו. @@ -34,7 +25,7 @@ CO_OP_TRANSLATOR_METADATA: גרסה פשוטה של איזון זו ידועה כבעיה של **CartPole**. בעולם ה-CartPole, יש לנו מחוון אופקי שיכול לזוז שמאלה או ימינה, והמטרה היא לאזן מוט אנכי על גבי המחוון בזמן שהוא זז. -a cartpole +a cartpole כדי ליצור ולהשתמש בסביבה זו, אנו צריכים כמה שורות קוד ב-Python: diff --git a/translations/he/lessons/6-Other/22-DeepRL/lab/README.md b/translations/he/lessons/6-Other/22-DeepRL/lab/README.md index e87c3db8..1f2cb0bc 100644 --- a/translations/he/lessons/6-Other/22-DeepRL/lab/README.md +++ b/translations/he/lessons/6-Other/22-DeepRL/lab/README.md @@ -1,12 +1,3 @@ - ## הסביבה סביבת Mountain Car מורכבת ממכונית שנתקעה בתוך עמק. המטרה שלך היא לקפוץ החוצה מהעמק ולהגיע לדגל. הפעולות שאתה יכול לבצע הן להאיץ שמאלה, להאיץ ימינה, או לא לעשות דבר. ניתן לצפות במיקום המכונית לאורך ציר ה-x ובמהירות שלה. diff --git a/translations/he/lessons/6-Other/23-MultiagentSystems/README.md b/translations/he/lessons/6-Other/23-MultiagentSystems/README.md index 1c4793fa..98006935 100644 --- a/translations/he/lessons/6-Other/23-MultiagentSystems/README.md +++ b/translations/he/lessons/6-Other/23-MultiagentSystems/README.md @@ -1,12 +1,3 @@ - # מערכות רב-סוכנים אחת הדרכים האפשריות להשגת אינטליגנציה היא הגישה המכונה **מתהווה** (או **סינרגטית**), המבוססת על העובדה שהתנהגות משולבת של סוכנים פשוטים יחסית יכולה להוביל להתנהגות מורכבת יותר (או אינטליגנטית) של המערכת כולה. באופן תיאורטי, הדבר מבוסס על עקרונות של [אינטליגנציה קולקטיבית](https://en.wikipedia.org/wiki/Collective_intelligence), [מתהוות](https://en.wikipedia.org/wiki/Global_brain) ו[סייברנטיקה אבולוציונית](https://en.wikipedia.org/wiki/Global_brain), אשר טוענים שמערכות ברמה גבוהה יותר מקבלות ערך מוסף כאשר הן משולבות בצורה נכונה ממערכות ברמה נמוכה יותר (מה שמכונה *עקרון המעבר למטאסיסטם*). @@ -60,7 +51,7 @@ ask turtles [ אחד הדברים הנהדרים ב-NetLogo הוא שהיא מכילה ספריית מודלים פעילים שניתן לנסות. גשו ל-**File → Models Library**, ותמצאו קטגוריות רבות של מודלים לבחירה. -ספריית מודלים של NetLogo +ספריית מודלים של NetLogo > צילום מסך של ספריית המודלים מאת דמיטרי סושניקוב diff --git a/translations/he/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/he/lessons/6-Other/23-MultiagentSystems/assignment.md index edcdaa65..d6c50750 100644 --- a/translations/he/lessons/6-Other/23-MultiagentSystems/assignment.md +++ b/translations/he/lessons/6-Other/23-MultiagentSystems/assignment.md @@ -1,12 +1,3 @@ - # משימת NetLogo קחו אחד מהמודלים בספריית NetLogo והשתמשו בו כדי לדמות מצב מציאותי בצורה הקרובה ביותר. דוגמה טובה תהיה לשנות את מודל הווירוס בתיקיית Alternative Visualizations כדי להראות כיצד ניתן להשתמש בו לדמות את התפשטות COVID-19. האם תוכלו לבנות מודל שמחקה התפשטות ויראלית במציאות? diff --git a/translations/he/lessons/7-Ethics/README.md b/translations/he/lessons/7-Ethics/README.md index f911484b..4d74749b 100644 --- a/translations/he/lessons/7-Ethics/README.md +++ b/translations/he/lessons/7-Ethics/README.md @@ -1,12 +1,3 @@ - # בינה מלאכותית אתית ואחראית אתם כמעט מסיימים את הקורס הזה, ואני מקווה שעד עכשיו ברור לכם שבינה מלאכותית מבוססת על מספר שיטות מתמטיות פורמליות שמאפשרות לנו למצוא קשרים בנתונים ולאמן מודלים לשחזר היבטים מסוימים של התנהגות אנושית. בנקודה זו בהיסטוריה, אנו רואים בבינה מלאכותית כלי רב עוצמה לחילוץ תבניות מנתונים וליישום התבניות הללו לפתרון בעיות חדשות. diff --git a/translations/he/lessons/README.md b/translations/he/lessons/README.md index da7210b1..f86fc11b 100644 --- a/translations/he/lessons/README.md +++ b/translations/he/lessons/README.md @@ -1,12 +1,3 @@ - # סקירה כללית ![סקירה כללית באיור](../../../translated_images/he/ai-overview.0857791951d19500.webp) diff --git a/translations/he/lessons/X-Extras/X1-MultiModal/README.md b/translations/he/lessons/X-Extras/X1-MultiModal/README.md index dccb8494..53075733 100644 --- a/translations/he/lessons/X-Extras/X1-MultiModal/README.md +++ b/translations/he/lessons/X-Extras/X1-MultiModal/README.md @@ -1,12 +1,3 @@ - # רשתות מולטי-מודליות לאחר ההצלחה של מודלי טרנספורמר במשימות עיבוד שפה טבעית (NLP), אותן ארכיטקטורות או דומות להן יושמו גם במשימות ראייה ממוחשבת. יש עניין גובר בבניית מודלים שמשלבים יכולות של ראייה ושפה טבעית. אחד הניסיונות הללו נעשה על ידי OpenAI, והוא נקרא CLIP ו-DALL.E. diff --git a/translations/he/lessons/sketchnotes/LICENSE.md b/translations/he/lessons/sketchnotes/LICENSE.md index 6cff03ed..37076318 100644 --- a/translations/he/lessons/sketchnotes/LICENSE.md +++ b/translations/he/lessons/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - ייחוס-שיתוף זהה 4.0 בינלאומי ======================================================================= diff --git a/translations/he/lessons/sketchnotes/README.md b/translations/he/lessons/sketchnotes/README.md index 8f4eb37f..d4445df8 100644 --- a/translations/he/lessons/sketchnotes/README.md +++ b/translations/he/lessons/sketchnotes/README.md @@ -1,12 +1,3 @@ - ניתן להוריד את כל הסקיצות של תכנית הלימודים מכאן. 🎨 נוצר על ידי: טומומי אימורה (טוויטר: [@girlie_mac](https://twitter.com/girlie_mac), גיטהאב: [girliemac](https://github.com/girliemac)) diff --git a/translations/he/troubleshoot.md b/translations/he/troubleshoot.md index dbaa5867..5b2a1d0d 100644 --- a/translations/he/troubleshoot.md +++ b/translations/he/troubleshoot.md @@ -1,12 +1,3 @@ - # מדריך פתרון תקלות ל-AI-For-Beginners מדריך זה יעזור לכם לפתור בעיות נפוצות בעת שימוש או תרומה למאגר [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners). כל בעיה כוללת רקע, תסמינים, הסברים ופתרונות שלב-אחר-שלב. diff --git a/translations/id/.co-op-translator.json b/translations/id/.co-op-translator.json new file mode 100644 index 00000000..0acb9919 --- /dev/null +++ b/translations/id/.co-op-translator.json @@ -0,0 +1,398 @@ +{ + "AGENTS.md": { + "original_hash": "6b11a37115944252ab3ed04e358d830d", + "translation_date": "2025-10-03T09:25:38+00:00", + "source_file": "AGENTS.md", + "language_code": "id" + }, + "README.md": { + "original_hash": "1984fc89dd304a8a33ab5584691a99aa", + "translation_date": "2026-01-30T02:13:48+00:00", + "source_file": "README.md", + "language_code": "id" + }, + "SECURITY.md": { + "original_hash": "a583f49d359c7ebba61433e4dfcd05a9", + "translation_date": "2025-08-29T12:11:53+00:00", + "source_file": "SECURITY.md", + "language_code": "id" + }, + "etc/CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-08-29T12:52:28+00:00", + "source_file": "etc/CODE_OF_CONDUCT.md", + "language_code": "id" + }, + "etc/CONTRIBUTING.md": { + "original_hash": "847a587aa1b83f4d00858183ff3ed18a", + "translation_date": "2025-08-29T12:52:13+00:00", + "source_file": "etc/CONTRIBUTING.md", + "language_code": "id" + }, + "etc/Mindmap.md": { + "original_hash": "f2f88dbd2debd38e26149b27b1fd272d", + "translation_date": "2025-08-29T12:51:19+00:00", + "source_file": "etc/Mindmap.md", + "language_code": "id" + }, + "etc/SUPPORT.md": { + "original_hash": "fdfc08baee91e402938a2b1f94fe0949", + "translation_date": "2025-08-29T12:50:48+00:00", + "source_file": "etc/SUPPORT.md", + "language_code": "id" + }, + "etc/TRANSLATIONS.md": { + "original_hash": "62b3e3ad5182edb905eec649a87eeeb4", + "translation_date": "2025-08-29T12:51:53+00:00", + "source_file": "etc/TRANSLATIONS.md", + "language_code": "id" + }, + "etc/quiz-app/README.md": { + "original_hash": "d699cf8509f74baa5b0b838de5cf0662", + "translation_date": "2025-08-29T12:52:47+00:00", + "source_file": "etc/quiz-app/README.md", + "language_code": "id" + }, + "examples/README.md": { + "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7", + "translation_date": "2025-10-03T11:32:36+00:00", + "source_file": "examples/README.md", + "language_code": "id" + }, + "lessons/0-course-setup/for-teachers.md": { + "original_hash": "a094ef9927883de1cfcee51dbd143381", + "translation_date": "2025-08-29T12:16:15+00:00", + "source_file": "lessons/0-course-setup/for-teachers.md", + "language_code": "id" + }, + "lessons/0-course-setup/how-to-run.md": { + "original_hash": "a4717bd9103b9f6cd84d534b83534689", + "translation_date": "2026-01-16T03:44:39+00:00", + "source_file": "lessons/0-course-setup/how-to-run.md", + "language_code": "id" + }, + "lessons/0-course-setup/setup.md": { + "original_hash": "7b4e5b8956915870d0a0ed3cc5890042", + "translation_date": "2025-12-12T20:02:16+00:00", + "source_file": "lessons/0-course-setup/setup.md", + "language_code": "id" + }, + "lessons/1-Intro/README.md": { + "original_hash": "f57e8aa46141fd220b16ffed8f11aec7", + "translation_date": "2025-11-18T21:48:28+00:00", + "source_file": "lessons/1-Intro/README.md", + "language_code": "id" + }, + "lessons/1-Intro/assignment.md": { + "original_hash": "a334df77a82aaaf2a29c77065d3e481e", + "translation_date": "2025-11-18T21:49:27+00:00", + "source_file": "lessons/1-Intro/assignment.md", + "language_code": "id" + }, + "lessons/2-Symbolic/README.md": { + "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4", + "translation_date": "2026-01-16T03:45:50+00:00", + "source_file": "lessons/2-Symbolic/README.md", + "language_code": "id" + }, + "lessons/2-Symbolic/assignment.md": { + "original_hash": "a057a8604f3976c3e309884453f1fad0", + "translation_date": "2025-08-29T12:31:27+00:00", + "source_file": "lessons/2-Symbolic/assignment.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/03-Perceptron/README.md": { + "original_hash": "c34cbba802058b6fa267e1a294d4e510", + "translation_date": "2025-09-23T10:43:07+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": { + "original_hash": "ba5d1eb353d20d3e7181066b3c424b99", + "translation_date": "2025-08-29T12:36:22+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/README.md": { + "original_hash": "789d6c3fb6fc7948a470b33078a5983a", + "translation_date": "2025-09-23T10:42:47+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": { + "original_hash": "48fdd704d483e19bc3d7464074c9fcbe", + "translation_date": "2025-08-29T12:35:26+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/05-Frameworks/README.md": { + "original_hash": "ddd216f558a255260a9374008002c971", + "translation_date": "2025-09-23T10:43:24+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": { + "original_hash": "e452d897efb9a89700f41021834cf6e5", + "translation_date": "2025-08-29T12:37:28+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md", + "language_code": "id" + }, + "lessons/3-NeuralNetworks/README.md": { + "original_hash": "f862a99d88088163df12270e2f2ad6c3", + "translation_date": "2025-10-03T12:51:08+00:00", + "source_file": "lessons/3-NeuralNetworks/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/06-IntroCV/README.md": { + "original_hash": "feeca98225cb420afc89415f24f63d92", + "translation_date": "2025-09-23T10:39:05+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/06-IntroCV/lab/README.md": { + "original_hash": "3d53d6409f80970f7281a45dee35328a", + "translation_date": "2025-08-29T12:23:55+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": { + "original_hash": "53faab85adfcebd8c10bcd71dc2fa557", + "translation_date": "2025-09-23T10:38:25+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/07-ConvNets/README.md": { + "original_hash": "a560d5b845962cf33dc102266e409568", + "translation_date": "2025-09-23T10:38:10+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/07-ConvNets/lab/README.md": { + "original_hash": "b70fcf7fcee862990f848c679090943f", + "translation_date": "2025-10-03T14:56:19+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/08-TransferLearning/README.md": { + "original_hash": "178c0b5ee5395733eb18aec51e71a0a9", + "translation_date": "2025-09-23T10:38:41+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": { + "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99", + "translation_date": "2025-08-29T12:22:01+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": { + "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2", + "translation_date": "2025-08-29T12:22:38+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/09-Autoencoders/README.md": { + "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d", + "translation_date": "2025-09-23T10:40:04+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/10-GANs/README.md": { + "original_hash": "0ff65b4da07b23697235de2beb2a3c25", + "translation_date": "2025-09-23T10:40:39+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/11-ObjectDetection/README.md": { + "original_hash": "d76a7eda28de5210c8b1ba50a6216c69", + "translation_date": "2025-09-23T10:39:28+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": { + "original_hash": "ad568d55ae65c856fe929fc2b278510a", + "translation_date": "2025-08-29T12:25:22+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/12-Segmentation/README.md": { + "original_hash": "6568aaae7e0e4afed4b5d74b5b223700", + "translation_date": "2025-09-23T10:40:25+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/12-Segmentation/lab/README.md": { + "original_hash": "365f0decfe0f47b460bbde8227c5009d", + "translation_date": "2025-08-29T12:27:19+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md", + "language_code": "id" + }, + "lessons/4-ComputerVision/README.md": { + "original_hash": "58a52f000089c1d8906a4daa4ab1169b", + "translation_date": "2025-08-29T12:18:59+00:00", + "source_file": "lessons/4-ComputerVision/README.md", + "language_code": "id" + }, + "lessons/5-NLP/13-TextRep/README.md": { + "original_hash": "dbd3f73e4139f030ecb2e20387d70fee", + "translation_date": "2025-09-23T10:46:31+00:00", + "source_file": "lessons/5-NLP/13-TextRep/README.md", + "language_code": "id" + }, + "lessons/5-NLP/13-TextRep/assignment.md": { + "original_hash": "cdc1f2e631f055f3473b36d18e4760b3", + "translation_date": "2025-08-29T12:50:37+00:00", + "source_file": "lessons/5-NLP/13-TextRep/assignment.md", + "language_code": "id" + }, + "lessons/5-NLP/14-Embeddings/README.md": { + "original_hash": "b708c9b85b833864c73c6281f1e6b96e", + "translation_date": "2025-09-23T10:46:13+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/README.md", + "language_code": "id" + }, + "lessons/5-NLP/14-Embeddings/assignment.md": { + "original_hash": "bc690ecf68b38d311cc9e12f3144a28c", + "translation_date": "2025-08-29T12:49:40+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/assignment.md", + "language_code": "id" + }, + "lessons/5-NLP/15-LanguageModeling/README.md": { + "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57", + "translation_date": "2025-09-23T10:44:09+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/README.md", + "language_code": "id" + }, + "lessons/5-NLP/15-LanguageModeling/lab/README.md": { + "original_hash": "5130f01fdc5ebb83032b23d489027aac", + "translation_date": "2025-08-29T12:43:35+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md", + "language_code": "id" + }, + "lessons/5-NLP/16-RNN/README.md": { + "original_hash": "e2273cc150380a5e191903cea858f021", + "translation_date": "2025-09-23T10:45:23+00:00", + "source_file": "lessons/5-NLP/16-RNN/README.md", + "language_code": "id" + }, + "lessons/5-NLP/16-RNN/assignment.md": { + "original_hash": "47f7d3c6a5373543e051e4d1140ce898", + "translation_date": "2025-08-29T12:48:32+00:00", + "source_file": "lessons/5-NLP/16-RNN/assignment.md", + "language_code": "id" + }, + "lessons/5-NLP/17-GenerativeNetworks/README.md": { + "original_hash": "51be6057374d01d70e07dd5ec88ebc0d", + "translation_date": "2025-09-23T10:43:50+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md", + "language_code": "id" + }, + "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": { + "original_hash": "439e12796197a90e7623d4c9c057b9c2", + "translation_date": "2025-08-29T12:42:56+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md", + "language_code": "id" + }, + "lessons/5-NLP/18-Transformers/README.md": { + "original_hash": "f335dfcb4a993920504c387973a36957", + "translation_date": "2025-09-23T10:44:19+00:00", + "source_file": "lessons/5-NLP/18-Transformers/README.md", + "language_code": "id" + }, + "lessons/5-NLP/18-Transformers/assignment.md": { + "original_hash": "177f3ea3995d725e6f9f5c66af16edcd", + "translation_date": "2025-08-29T12:45:19+00:00", + "source_file": "lessons/5-NLP/18-Transformers/assignment.md", + "language_code": "id" + }, + "lessons/5-NLP/19-NER/README.md": { + "original_hash": "6522312ff835796ca34136a9462fafb2", + "translation_date": "2025-09-23T10:45:04+00:00", + "source_file": "lessons/5-NLP/19-NER/README.md", + "language_code": "id" + }, + "lessons/5-NLP/19-NER/lab/README.md": { + "original_hash": "032bda5068f543d6c1fcb30c34231461", + "translation_date": "2025-08-29T12:47:19+00:00", + "source_file": "lessons/5-NLP/19-NER/lab/README.md", + "language_code": "id" + }, + "lessons/5-NLP/20-LangModels/README.md": { + "original_hash": "97836d30a6bec736f8e3b4411c572bc2", + "translation_date": "2025-09-23T10:44:46+00:00", + "source_file": "lessons/5-NLP/20-LangModels/README.md", + "language_code": "id" + }, + "lessons/5-NLP/README.md": { + "original_hash": "8ef02a9318257ea140ed3ed74442096d", + "translation_date": "2025-08-29T12:41:43+00:00", + "source_file": "lessons/5-NLP/README.md", + "language_code": "id" + }, + "lessons/6-Other/21-GeneticAlgorithms/README.md": { + "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a", + "translation_date": "2025-09-23T10:36:48+00:00", + "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md", + "language_code": "id" + }, + "lessons/6-Other/22-DeepRL/README.md": { + "original_hash": "04395657fc01648f8f70484d0e55ab67", + "translation_date": "2025-09-23T10:37:41+00:00", + "source_file": "lessons/6-Other/22-DeepRL/README.md", + "language_code": "id" + }, + "lessons/6-Other/22-DeepRL/lab/README.md": { + "original_hash": "7bd8dc72040e98e35e7225e34058cd4e", + "translation_date": "2025-08-29T12:15:59+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/README.md", + "language_code": "id" + }, + "lessons/6-Other/23-MultiagentSystems/README.md": { + "original_hash": "38a1185ae3d54b180378bbd71ae3ef16", + "translation_date": "2025-09-23T10:37:04+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/README.md", + "language_code": "id" + }, + "lessons/6-Other/23-MultiagentSystems/assignment.md": { + "original_hash": "cf654ca60c7f86c8dad28596fb42994b", + "translation_date": "2025-08-29T12:14:34+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md", + "language_code": "id" + }, + "lessons/7-Ethics/README.md": { + "original_hash": "437c988596e751072e41a5aad3fcc5d9", + "translation_date": "2025-08-29T12:31:52+00:00", + "source_file": "lessons/7-Ethics/README.md", + "language_code": "id" + }, + "lessons/README.md": { + "original_hash": "5fef1a0b22498d7188959e2a2cb08af7", + "translation_date": "2025-08-29T12:12:09+00:00", + "source_file": "lessons/README.md", + "language_code": "id" + }, + "lessons/X-Extras/X1-MultiModal/README.md": { + "original_hash": "9c592c26aca16ca085d268c732284187", + "translation_date": "2025-08-29T12:18:02+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/README.md", + "language_code": "id" + }, + "lessons/sketchnotes/LICENSE.md": { + "original_hash": "45ab63a2cd8f5faef6c9b150618837a4", + "translation_date": "2025-08-29T12:40:25+00:00", + "source_file": "lessons/sketchnotes/LICENSE.md", + "language_code": "id" + }, + "lessons/sketchnotes/README.md": { + "original_hash": "050b8bddebafba55b129414e6ab096ab", + "translation_date": "2025-08-29T12:37:39+00:00", + "source_file": "lessons/sketchnotes/README.md", + "language_code": "id" + }, + "troubleshoot.md": { + "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86", + "translation_date": "2025-10-03T09:47:49+00:00", + "source_file": "troubleshoot.md", + "language_code": "id" + } +} \ No newline at end of file diff --git a/translations/id/AGENTS.md b/translations/id/AGENTS.md index 9d3445e5..cee6d4eb 100644 --- a/translations/id/AGENTS.md +++ b/translations/id/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## Gambaran Proyek diff --git a/translations/id/README.md b/translations/id/README.md index 8d3454fa..18b34a94 100644 --- a/translations/id/README.md +++ b/translations/id/README.md @@ -1,12 +1,3 @@ - [![GitHub license](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE) [![GitHub contributors](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/) [![GitHub issues](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/) @@ -23,22 +14,23 @@ CO_OP_TRANSLATOR_METADATA: # Kecerdasan Buatan untuk Pemula - Kurikulum -|![Sketchnote oleh @girlie_mac https://twitter.com/girlie_mac](../../../../translated_images/id/ai-overview.0857791951d19500.webp)| +|![Sketchnote oleh @girlie_mac https://twitter.com/girlie_mac](../../translated_images/id/ai-overview.0857791951d19500.webp)| |:---:| -| AI For Beginners - _Sketchnote oleh [@girlie_mac](https://twitter.com/girlie_mac)_ | +| Kecerdasan Buatan untuk Pemula - _Sketchnote oleh [@girlie_mac](https://twitter.com/girlie_mac)_ | + +Jelajahi dunia **Kecerdasan Buatan** (AI) dengan kurikulum 12 minggu dan 24 pelajaran kami! Ini termasuk pelajaran praktis, kuis, dan lab. Kurikulumnya ramah pemula dan mencakup alat seperti TensorFlow dan PyTorch, serta etika dalam AI. -Jelajahi dunia **Kecerdasan Buatan** (AI) dengan kurikulum 12 minggu dan 24 pelajaran kami! Ini mencakup pelajaran praktis, kuis, dan lab. Kurikulum ini ramah pemula dan membahas alat seperti TensorFlow dan PyTorch, serta etika dalam AI. ### 🌐 Dukungan Multi-Bahasa #### Didukung melalui GitHub Action (Otomatis & Selalu Terbaru) -[Arab](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgaria](../bg/README.md) | [Burma (Myanmar)](../my/README.md) | [Cina (Sederhana)](../zh/README.md) | [Cina (Tradisional, Hong Kong)](../hk/README.md) | [Cina (Tradisional, Makau)](../mo/README.md) | [Cina (Tradisional, Taiwan)](../tw/README.md) | [Kroasia](../hr/README.md) | [Ceko](../cs/README.md) | [Denmark](../da/README.md) | [Belanda](../nl/README.md) | [Estonia](../et/README.md) | [Finlandia](../fi/README.md) | [Prancis](../fr/README.md) | [Jerman](../de/README.md) | [Yunani](../el/README.md) | [Ibrani](../he/README.md) | [Hindi](../hi/README.md) | [Hongaria](../hu/README.md) | [Indonesia](./README.md) | [Italia](../it/README.md) | [Jepang](../ja/README.md) | [Kannada](../kn/README.md) | [Korea](../ko/README.md) | [Lituania](../lt/README.md) | [Melayu](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Pidgin Nigeria](../pcm/README.md) | [Norwegia](../no/README.md) | [Persia (Farsi)](../fa/README.md) | [Polandia](../pl/README.md) | [Portugis (Brasil)](../br/README.md) | [Portugis (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumania](../ro/README.md) | [Rusia](../ru/README.md) | [Serbia (Sirilik)](../sr/README.md) | [Slowakia](../sk/README.md) | [Slovenia](../sl/README.md) | [Spanyol](../es/README.md) | [Swahili](../sw/README.md) | [Swedia](../sv/README.md) | [Tagalog (Filipina)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turki](../tr/README.md) | [Ukraina](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnam](../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](./README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../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) > **Lebih suka Clone Secara Lokal?** -> Repositori ini mencakup lebih dari 50 bahasa terjemahan yang secara signifikan meningkatkan ukuran unduhan. Untuk mengkloning tanpa terjemahan, gunakan sparse checkout: +> Repositori ini mencakup lebih dari 50 terjemahan bahasa yang secara signifikan meningkatkan ukuran unduhan. Untuk clone tanpa terjemahan, gunakan sparse checkout: > ```bash > git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git > cd AI-For-Beginners @@ -47,7 +39,7 @@ Jelajahi dunia **Kecerdasan Buatan** (AI) dengan kurikulum 12 minggu dan 24 pela > Ini memberi Anda semua yang Anda butuhkan untuk menyelesaikan kursus dengan unduhan yang jauh lebih cepat. -**Jika Anda ingin mendukung bahasa terjemahan tambahan, daftar didukung tersedia [di sini](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** +**Jika Anda ingin mendukung bahasa terjemahan tambahan, daftar bahasanya tersedia [di sini](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** ## Bergabung dengan Komunitas [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) @@ -56,111 +48,113 @@ Jelajahi dunia **Kecerdasan Buatan** (AI) dengan kurikulum 12 minggu dan 24 pela **[Peta Pikiran Kursus](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** -Dalam kurikulum ini, Anda akan mempelajari: +Dalam kurikulum ini, Anda akan belajar: -* Pendekatan berbeda untuk Kecerdasan Buatan, termasuk pendekatan simbolik "lama tapi emas" dengan **Representasi Pengetahuan** dan penalaran ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* **Jaringan Saraf** dan **Pembelajaran Mendalam**, yang menjadi inti AI modern. Kami akan menggambarkan konsep-konsep di balik topik penting ini menggunakan kode dalam dua framework paling populer - [TensorFlow](http://Tensorflow.org) dan [PyTorch](http://pytorch.org). -* **Arsitektur Saraf** untuk bekerja dengan gambar dan teks. Kami akan membahas model-model terbaru meskipun mungkin kurang dalam hal state-of-the-art. +* Pendekatan berbeda untuk Kecerdasan Buatan, termasuk pendekatan simbolik "lama" dengan **Representasi Pengetahuan** dan penalaran ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* **Jaringan Syaraf** dan **Pembelajaran Mendalam**, yang merupakan inti dari AI modern. Kami akan mengilustrasikan konsep di balik topik penting ini menggunakan kode dalam dua kerangka kerja paling populer - [TensorFlow](http://Tensorflow.org) dan [PyTorch](http://pytorch.org). +* **Arsitektur Neural** untuk bekerja dengan gambar dan teks. Kami akan membahas model-model terbaru tetapi mungkin agak kurang dalam state-of-the-art. * Pendekatan AI yang kurang populer, seperti **Algoritma Genetika** dan **Sistem Multi-Agen**. -Yang tidak akan kami bahas dalam kurikulum ini: +Apa yang tidak akan kami bahas dalam kurikulum ini: > [Temukan semua sumber daya tambahan untuk kursus ini dalam koleksi Microsoft Learn kami](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* Kasus bisnis penggunaan **AI dalam Bisnis**. Pertimbangkan mengikuti jalur pembelajaran [Pengenalan AI untuk pengguna bisnis](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) di Microsoft Learn, atau [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), yang dikembangkan bekerja sama dengan [INSEAD](https://www.insead.edu/). -* **Pembelajaran Mesin Klasik**, yang dijelaskan dengan baik di dalam [Kurikulum Pembelajaran Mesin untuk Pemula](http://github.com/Microsoft/ML-for-Beginners) kami. -* Aplikasi AI praktis yang dibangun menggunakan **[Layanan Kognitif](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Untuk ini, kami rekomendasikan memulai dengan modul Microsoft Learn untuk [visi komputer](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [pemrosesan bahasa alami](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generative AI dengan Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** dan lainnya. -* **Framework Cloud ML Spesifik**, seperti [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), atau [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Pertimbangkan menggunakan jalur pembelajaran [Membangun dan mengoperasikan solusi pembelajaran mesin dengan Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) dan [Membangun dan Mengoperasikan Solusi Pembelajaran Mesin dengan Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum). -* **AI Percakapan** dan **Chat Bot**. Ada jalur pembelajaran terpisah [Membuat solusi AI percakapan](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), dan Anda juga bisa merujuk ke [posting blog ini](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) untuk detail lebih lanjut. -* **Matematika Mendalam** di balik pembelajaran mendalam. Untuk ini, kami merekomendasikan [Pembelajaran Mendalam](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) oleh Ian Goodfellow, Yoshua Bengio, dan Aaron Courville, yang juga tersedia secara daring di [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). +* Studi kasus bisnis penggunaan **AI dalam Bisnis**. Pertimbangkan untuk mengambil jalur pembelajaran [Pengenalan AI untuk pengguna bisnis](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) di Microsoft Learn, atau [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), yang dikembangkan bekerja sama dengan [INSEAD](https://www.insead.edu/). +* **Pembelajaran Mesin Klasik**, yang telah dijelaskan dengan baik dalam [Kurikulum Pembelajaran Mesin untuk Pemula](http://github.com/Microsoft/ML-for-Beginners). +* Aplikasi AI praktis yang dibangun menggunakan **[Layanan Kognitif](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Untuk ini, kami menyarankan Anda memulai dengan modul Microsoft Learn untuk [visi komputer](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [pemrosesan bahasa alami](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[AI Generatif dengan Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** dan lainnya. +* **Framework Cloud ML spesifik**, seperti [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), atau [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Pertimbangkan menggunakan jalur pembelajaran [Bangun dan operasikan solusi pembelajaran mesin dengan Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) dan [Bangun dan Operasikan Solusi Pembelajaran Mesin dengan Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum). +* **AI Percakapan** dan **Chat Bot**. Ada jalur pembelajaran terpisah [Buat solusi AI percakapan](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), dan Anda juga dapat merujuk ke [posting blog ini](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) untuk detail lebih lanjut. +* **Matematika Mendalam** di balik pembelajaran mendalam. Untuk ini, kami merekomendasikan [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) oleh Ian Goodfellow, Yoshua Bengio dan Aaron Courville, yang juga tersedia online di [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -Untuk pengantar yang ringan tentang topik _AI di Cloud_, Anda dapat mempertimbangkan mengikuti Jalur Pembelajaran [Memulai dengan kecerdasan buatan di Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum). +Untuk pengenalan halus ke topik _AI di Cloud_, Anda dapat mempertimbangkan jalur pembelajaran [Mulai dengan kecerdasan buatan di Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum). # Konten -| | Tautan Pelajaran | PyTorch/Keras/TensorFlow | Lab | -| :-: | :---------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | +| | Tautan Pelajaran | PyTorch/Keras/TensorFlow | Lab | +| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | | 0 | [Pengaturan Kursus](./lessons/0-course-setup/setup.md) | [Siapkan Lingkungan Pengembangan Anda](./lessons/0-course-setup/how-to-run.md) | | -| I | [**Pengenalan AI**](./lessons/1-Intro/README.md) | | | -| 01 | [Pengenalan dan Sejarah AI](./lessons/1-Intro/README.md) | - | - | +| I | [**Pendahuluan AI**](./lessons/1-Intro/README.md) | | | +| 01 | [Pendahuluan dan Sejarah AI](./lessons/1-Intro/README.md) | - | - | | II | **AI Simbolik** | | 02 | [Representasi Pengetahuan dan Sistem Pakar](./lessons/2-Symbolic/README.md) | [Sistem Pakar](./lessons/2-Symbolic/Animals.ipynb) / [Ontologi](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Graf Konsep](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | -| III | [**Pengenalan Jaringan Saraf**](./lessons/3-NeuralNetworks/README.md) ||| +| III | [**Pengenalan Jaringan Neural**](./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 | [Multi-Layered Perceptron dan Membuat Framework Sendiri](./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 | [Intro ke Frameworks (PyTorch/TensorFlow) dan Overfitting](./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 | [**Computer Vision**](./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)| [Jelajahi Computer Vision di Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | -| 06 | [Intro ke Computer Vision. 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 | [Convolutional Neural Networks](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Arsitektur 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 | [Jaringan yang Telah Dilatih dan Transfer Learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) dan [Trik Pelatihan](./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 | [Autoencoders dan 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 | [Generative Adversarial Networks & Transfer Gaya Artistik](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | +| 04 | [Perceptron Berlapis dan Membuat Framework Sendiri](./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 | [Pengenalan Framework (PyTorch/TensorFlow) dan Overfitting](./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 | [**Penglihatan Komputer**](./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)| [Jelajahi Penglihatan Komputer di Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | +| 06 | [Pengenalan Penglihatan Komputer. 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 | [Jaringan Neural Konvolusional](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Arsitektur 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 | [Jaringan Pralatih dan Transfer Learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) dan [Trik Pelatihan](./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 | [Autoencoder dan 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 | [Jaringan Adversarial Generatif & Transfer Gaya Artistik](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | | 11 | [Deteksi Objek](./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 | [Segmentasi Semantik. 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 | [**Natural Language Processing**](./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) | [Jelajahi Natural Language Processing di Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| +| V | [**Pengolahan Bahasa Alami**](./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) | [Jelajahi Pengolahan Bahasa Alami di Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| | 13 | [Representasi Teks. 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 | [Embedding kata semantik. Word2Vec dan 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 | [Pemodelan Bahasa. Melatih embeddings sendiri](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | -| 16 | [Recurrent Neural Networks](./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 | [Generative Recurrent Networks](./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) | | +| 14 | [Embedding Kata Semantik. Word2Vec dan 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 | [Pemodelan Bahasa. Melatih embedding Anda sendiri](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | +| 16 | [Jaringan Neural Rekuren](./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 | [Jaringan Rekuren Generatif](./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 | [Transformer. 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 | [Named Entity Recognition](./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 | [Model Bahasa Besar, Pemrograman Prompt dan Tugas 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 | **Teknik AI Lainnya** || | -| 21 | [Algoritme Genetik](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | -| 22 | [Deep Reinforcement Learning](./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 | [Algoritma Genetika](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | +| 22 | [Pembelajaran Penguatan Mendalam](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) | | 23 | [Sistem Multi-Agen](./lessons/6-Other/23-MultiagentSystems/README.md) | | | | VII | **Etika AI** | | | -| 24 | [Etika AI dan AI yang Bertanggung Jawab](./lessons/7-Ethics/README.md) | [Microsoft Learn: Prinsip AI yang Bertanggung Jawab](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | +| 24 | [Etika AI dan AI Bertanggung Jawab](./lessons/7-Ethics/README.md) | [Microsoft Learn: Prinsip AI Bertanggung Jawab](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | | IX | **Tambahan** | | | | 25 | [Jaringan Multi-Modal, CLIP dan VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | ## Setiap pelajaran berisi -* Materi bacaan pendahuluan -* Jupyter Notebook yang dapat dijalankan, yang sering kali spesifik untuk framework (**PyTorch** atau **TensorFlow**). Notebook yang bisa dijalankan juga berisi banyak materi teoretis, jadi untuk memahami topik Anda perlu melalui setidaknya satu versi notebook (baik PyTorch atau TensorFlow). -* **Lab** tersedia untuk beberapa topik, yang memberi Anda kesempatan untuk mencoba menerapkan materi yang telah Anda pelajari ke masalah tertentu. -* Beberapa bagian mengandung tautan ke modul [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) yang membahas topik terkait. +* Materi pra-baca +* Jupyter Notebook yang dapat dijalankan, yang seringkali spesifik untuk framework (**PyTorch** atau **TensorFlow**). Notebook yang dapat dijalankan juga berisi banyak materi teoretis, jadi untuk memahami topiknya Anda perlu mempelajari setidaknya satu versi notebook (baik PyTorch atau TensorFlow). +* **Lab** yang tersedia untuk beberapa topik, yang memberi Anda kesempatan untuk mencoba menerapkan materi yang telah Anda pelajari pada masalah tertentu. +* Beberapa bagian berisi tautan ke modul [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) yang membahas topik terkait. ## Memulai -### 🎯 Baru di AI? Mulai Di Sini! +### 🎯 Baru di AI? Mulailah Di Sini! -Jika Anda benar-benar baru di AI dan menginginkan contoh cepat dan praktis, lihat [**Contoh Ramah Pemula**](./examples/README.md)! Ini mencakup: +Jika Anda benar-benar baru dalam AI dan ingin contoh praktis yang cepat, lihat [**Contoh Ramah Pemula**](./examples/README.md) kami! Ini termasuk: -- 🌟 **Halo Dunia AI** - Program AI pertama Anda (pengenalan pola) -- 🧠 **Jaringan Neural Sederhana** - Bangun jaringan neural dari awal -- 🖼️ **Klasifikator Gambar** - Klasifikasikan gambar dengan komentar terperinci +- 🌟 **Hello AI World** - Program AI pertama Anda (pengenalan pola) +- 🧠 **Jaringan Neural Sederhana** - Membangun jaringan neural dari awal + +- 🖼️ **Pengklasifikasi Gambar** - Mengklasifikasikan gambar dengan komentar mendetail - 💬 **Sentimen Teks** - Menganalisis teks positif/negatif -Contoh-contoh ini dirancang untuk membantu Anda memahami konsep AI sebelum memasuki kurikulum penuh. +Contoh-contoh ini dirancang untuk membantu Anda memahami konsep AI sebelum menyelami kurikulum lengkap. ### 📚 Pengaturan Kurikulum Lengkap -- Kami telah membuat [pelajaran pengaturan](./lessons/0-course-setup/setup.md) untuk membantu Anda dalam mengatur lingkungan pengembangan Anda. - Untuk Pendidik, kami juga telah membuat [pelajaran pengaturan kurikulum](./lessons/0-course-setup/for-teachers.md)! +- Kami telah membuat [pelajaran pengaturan](./lessons/0-course-setup/setup.md) untuk membantu Anda mengatur lingkungan pengembangan Anda. +- Untuk Pendidik, kami juga telah membuat [pelajaran pengaturan kurikulum](./lessons/0-course-setup/for-teachers.md)! - Cara [Menjalankan kode di VSCode atau Codespace](./lessons/0-course-setup/how-to-run.md) Ikuti langkah-langkah ini: -Fork Repository: Klik tombol "Fork" di pojok kanan atas halaman ini. +Fork Repositori: Klik tombol "Fork" di sudut kanan atas halaman ini. -Clone Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git` +Clone Repositori: `git clone https://github.com/microsoft/AI-For-Beginners.git` -Jangan lupa beri bintang (🌟) pada repo ini agar lebih mudah ditemukan nanti. +Jangan lupa beri bintang (🌟) repo ini agar mudah ditemukan nanti. -## Bertemu dengan Learners lain +## Bertemu dengan Pelajar Lain -Bergabunglah dengan [server Discord AI resmi kami](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) untuk bertemu dan berjejaring dengan peserta lain yang mengambil kursus ini serta mendapatkan dukungan. +Bergabunglah dengan [server Discord AI resmi kami](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) untuk bertemu dan berjejaring dengan pelajar lain yang mengikuti kursus ini dan dapatkan dukungan. -Jika Anda memiliki umpan balik produk atau pertanyaan saat membangun, kunjungi [Forum Pengembang Azure AI Foundry](https://aka.ms/foundry/forum) +Jika Anda memiliki masukan produk atau pertanyaan saat membangun, kunjungi [Forum Pengembang Azure AI Foundry](https://aka.ms/foundry/forum) ## Kuis -> **Catatan tentang kuis**: Semua kuis terdapat di folder Quiz-app di etc\quiz-app, atau [Online Di Sini](https://ff-quizzes.netlify.app/) Kuis ini terhubung dari dalam pelajaran, aplikasi kuis dapat dijalankan secara lokal atau di-deploy ke Azure; ikuti petunjuk di folder `quiz-app`. Kuis-kuis ini sedang secara bertahap dialihbahasakan. +> **Catatan tentang kuis**: Semua kuis terdapat di folder Quiz-app di etc\quiz-app, atau [Online Di Sini](https://ff-quizzes.netlify.app/) Kuis ini dihubungkan dari dalam pelajaran, aplikasi kuis dapat dijalankan secara lokal atau diterapkan ke Azure; ikuti instruksi di folder `quiz-app`. Mereka sedang diproses untuk dilokalkan secara bertahap. -## Bantuan Dibutuhkan +## Butuh Bantuan -Apakah Anda memiliki saran atau menemukan kesalahan ejaan atau kode? Buatlah issue atau buat pull request. +Apakah Anda memiliki saran atau menemukan kesalahan ejaan atau kode? Ajukan isu atau buat pull request. ## Terima Kasih Khusus @@ -168,59 +162,59 @@ Apakah Anda memiliki saran atau menemukan kesalahan ejaan atau kode? Buatlah iss * **🔥 Editor:** [Jen Looper](https://twitter.com/jenlooper), PhD * **🎨 Ilustrator Sketchnote:** [Tomomi Imura](https://twitter.com/girlie_mac) * **✅ Pembuat Kuis:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) -* **🙏 Kontributor Utama:** [Evgenii Pishchik](https://github.com/Pe4enIks) +* **🙏 Kontributor Inti:** [Evgenii Pishchik](https://github.com/Pe4enIks) ## Kurikulum Lainnya -Tim kami menghasilkan kurikulum lain! Lihat: +Tim kami juga menghasilkan kurikulum lain! Lihat: ### LangChain -[![LangChain4j for Beginners](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js for Beginners](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain4j untuk Pemula](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![LangChain.js untuk Pemula](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- ### Azure / Edge / MCP / Agen -[![AZD for Beginners](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Edge AI for Beginners](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![MCP for Beginners](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents for Beginners](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AZD untuk Pemula](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Edge AI untuk Pemula](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![MCP untuk Pemula](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Agents untuk Pemula](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- ### Seri AI Generatif -[![Generative AI for Beginners](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) +[![AI Generatif untuk Pemula](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Generatif (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![AI Generatif (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![AI Generatif (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- ### Pembelajaran Inti -[![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) +[![ML untuk Pemula](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Ilmu Data untuk Pemula](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![AI untuk Pemula](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![Keamanan Siber untuk Pemula](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Pengembangan Web untuk Pemula](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT untuk Pemula](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![Pengembangan XR untuk Pemula](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- ### Seri Copilot -[![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) -[![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Copilot untuk Pemrograman Berpasangan AI](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot untuk C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) +[![Petualangan Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Mendapatkan Bantuan -Jika Anda mengalami kebuntuan atau memiliki pertanyaan tentang membangun aplikasi AI. Bergabunglah dengan sesama pelajar dan pengembang berpengalaman dalam diskusi tentang MCP. Ini adalah komunitas yang mendukung di mana pertanyaan disambut dan pengetahuan dibagikan secara bebas. +Jika Anda mengalami kesulitan atau memiliki pertanyaan tentang membangun aplikasi AI. Bergabunglah dengan pelajar lain dan pengembang berpengalaman dalam diskusi tentang MCP. Ini adalah komunitas yang mendukung di mana pertanyaan disambut dan pengetahuan dibagikan dengan bebas. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Jika Anda memiliki umpan balik produk atau kesalahan saat membangun, kunjungi: +Jika Anda memiliki masukan produk atau menemukan kesalahan saat membangun, kunjungi: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) @@ -228,5 +222,5 @@ Jika Anda memiliki umpan balik produk atau kesalahan saat membangun, kunjungi: **Penafian**: -Dokumen ini telah diterjemahkan menggunakan layanan terjemahan AI [Co-op Translator](https://github.com/Azure/co-op-translator). Meskipun kami berusaha untuk akurat, harap diperhatikan bahwa terjemahan otomatis mungkin mengandung kesalahan atau ketidakakuratan. Dokumen asli dalam bahasa aslinya harus dianggap sebagai sumber yang sahih. Untuk informasi penting, disarankan menggunakan terjemahan profesional oleh manusia. Kami tidak bertanggung jawab atas kesalahpahaman atau penafsiran yang salah yang timbul dari penggunaan terjemahan ini. +Dokumen ini telah diterjemahkan menggunakan layanan terjemahan AI [Co-op Translator](https://github.com/Azure/co-op-translator). Meskipun kami berupaya untuk memberikan terjemahan yang akurat, harap diketahui bahwa terjemahan otomatis mungkin mengandung kesalahan atau ketidakakuratan. Dokumen asli dalam bahasa aslinya harus dianggap sebagai sumber yang otoritatif. Untuk informasi penting, disarankan menggunakan terjemahan profesional oleh manusia. Kami tidak bertanggung jawab atas kesalahpahaman atau penafsiran yang salah yang timbul dari penggunaan terjemahan ini. \ No newline at end of file diff --git a/translations/id/SECURITY.md b/translations/id/SECURITY.md index 20d85ce6..e86cc243 100644 --- a/translations/id/SECURITY.md +++ b/translations/id/SECURITY.md @@ -1,12 +1,3 @@ - ## Keamanan Microsoft sangat serius dalam menjaga keamanan produk dan layanan perangkat lunak kami, termasuk semua repositori kode sumber yang dikelola melalui organisasi GitHub kami, seperti [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), dan [organisasi GitHub kami lainnya](https://opensource.microsoft.com/). diff --git a/translations/id/etc/CODE_OF_CONDUCT.md b/translations/id/etc/CODE_OF_CONDUCT.md index ca19f78c..ebaecd53 100644 --- a/translations/id/etc/CODE_OF_CONDUCT.md +++ b/translations/id/etc/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # Kode Etik Sumber Terbuka Microsoft Proyek ini telah mengadopsi [Kode Etik Sumber Terbuka Microsoft](https://opensource.microsoft.com/codeofconduct/). diff --git a/translations/id/etc/CONTRIBUTING.md b/translations/id/etc/CONTRIBUTING.md index 80b4bc05..249da0f0 100644 --- a/translations/id/etc/CONTRIBUTING.md +++ b/translations/id/etc/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # Berkontribusi Proyek ini menyambut kontribusi dan saran. Sebagian besar kontribusi mengharuskan Anda diff --git a/translations/id/etc/Mindmap.md b/translations/id/etc/Mindmap.md index 04184dbf..d5e6fa13 100644 --- a/translations/id/etc/Mindmap.md +++ b/translations/id/etc/Mindmap.md @@ -1,12 +1,3 @@ - # AI ## [Pengantar AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md) diff --git a/translations/id/etc/SUPPORT.md b/translations/id/etc/SUPPORT.md index fd40eae8..9859cffd 100644 --- a/translations/id/etc/SUPPORT.md +++ b/translations/id/etc/SUPPORT.md @@ -1,12 +1,3 @@ - # Dukungan ## Cara melaporkan masalah dan mendapatkan bantuan diff --git a/translations/id/etc/TRANSLATIONS.md b/translations/id/etc/TRANSLATIONS.md index b5d003d4..e4a20ead 100644 --- a/translations/id/etc/TRANSLATIONS.md +++ b/translations/id/etc/TRANSLATIONS.md @@ -1,12 +1,3 @@ - # Berkontribusi dengan menerjemahkan pelajaran Kami menyambut terjemahan untuk pelajaran dalam kurikulum ini! diff --git a/translations/id/etc/quiz-app/README.md b/translations/id/etc/quiz-app/README.md index b5793faf..96a7afba 100644 --- a/translations/id/etc/quiz-app/README.md +++ b/translations/id/etc/quiz-app/README.md @@ -1,12 +1,3 @@ - # Kuis Kuis ini adalah kuis sebelum dan sesudah kuliah untuk kurikulum AI di https://aka.ms/ai-beginners diff --git a/translations/id/examples/README.md b/translations/id/examples/README.md index e462b39e..1b7017b0 100644 --- a/translations/id/examples/README.md +++ b/translations/id/examples/README.md @@ -1,12 +1,3 @@ - # Contoh AI Ramah Pemula Selamat datang! Direktori ini berisi contoh sederhana dan mandiri untuk membantu Anda memulai dengan AI dan pembelajaran mesin. Setiap contoh dirancang agar mudah dipahami dengan komentar yang rinci dan penjelasan langkah demi langkah. diff --git a/translations/id/lessons/0-course-setup/for-teachers.md b/translations/id/lessons/0-course-setup/for-teachers.md index 3007a51f..446b7742 100644 --- a/translations/id/lessons/0-course-setup/for-teachers.md +++ b/translations/id/lessons/0-course-setup/for-teachers.md @@ -1,12 +1,3 @@ - # Untuk Pendidik Apakah Anda ingin menggunakan kurikulum ini di kelas Anda? Silakan saja! diff --git a/translations/id/lessons/0-course-setup/how-to-run.md b/translations/id/lessons/0-course-setup/how-to-run.md index 70334b26..79901a5b 100644 --- a/translations/id/lessons/0-course-setup/how-to-run.md +++ b/translations/id/lessons/0-course-setup/how-to-run.md @@ -1,12 +1,3 @@ - # Cara Menjalankan Kode Kurikulum ini berisi banyak contoh dan lab yang dapat dieksekusi yang ingin Anda jalankan. Untuk melakukan ini, Anda memerlukan kemampuan untuk menjalankan kode Python di Jupyter Notebooks yang disediakan sebagai bagian dari kurikulum ini. Anda memiliki beberapa opsi untuk menjalankan kodenya: diff --git a/translations/id/lessons/0-course-setup/setup.md b/translations/id/lessons/0-course-setup/setup.md index 8d8aa33a..2837eba8 100644 --- a/translations/id/lessons/0-course-setup/setup.md +++ b/translations/id/lessons/0-course-setup/setup.md @@ -1,12 +1,3 @@ - # Memulai dengan Kurikulum Ini ## Apakah Anda seorang pelajar? diff --git a/translations/id/lessons/1-Intro/README.md b/translations/id/lessons/1-Intro/README.md index 6d6567b4..8e4cfcec 100644 --- a/translations/id/lessons/1-Intro/README.md +++ b/translations/id/lessons/1-Intro/README.md @@ -1,12 +1,3 @@ - # Pengantar AI ![Ringkasan konten Pengantar AI dalam bentuk doodle](../../../../translated_images/id/ai-intro.bf28d1ac4235881c.webp) diff --git a/translations/id/lessons/1-Intro/assignment.md b/translations/id/lessons/1-Intro/assignment.md index 11cb7e30..b68e1554 100644 --- a/translations/id/lessons/1-Intro/assignment.md +++ b/translations/id/lessons/1-Intro/assignment.md @@ -1,12 +1,3 @@ - # Game Jam Game adalah salah satu bidang yang sangat dipengaruhi oleh perkembangan AI dan ML. Dalam tugas ini, tulislah sebuah makalah singkat tentang sebuah game yang Anda sukai yang telah dipengaruhi oleh evolusi AI. Game tersebut harus cukup lama sehingga telah dipengaruhi oleh beberapa jenis sistem pemrosesan komputer. Contoh yang baik adalah Catur atau Go, tetapi Anda juga bisa melihat video game seperti Pong atau Pac-Man. Tulislah esai yang membahas masa lalu, masa kini, dan masa depan AI dalam game tersebut. diff --git a/translations/id/lessons/2-Symbolic/README.md b/translations/id/lessons/2-Symbolic/README.md index a55d774c..c58cd036 100644 --- a/translations/id/lessons/2-Symbolic/README.md +++ b/translations/id/lessons/2-Symbolic/README.md @@ -1,15 +1,6 @@ - # Representasi Pengetahuan dan Sistem Pakar -![Ringkasan konten AI Simbolik](../../../../../../translated_images/id/ai-symbolic.715a30cb610411a6.webp) +![Ringkasan konten AI Simbolik](../../../../translated_images/id/ai-symbolic.715a30cb610411a6.webp) > Sketchnote oleh [Tomomi Imura](https://twitter.com/girlie_mac) @@ -41,7 +32,7 @@ Sering kali, kita tidak mendefinisikan pengetahuan secara ketat, tetapi menyelar Dengan demikian, masalah **representasi pengetahuan** adalah menemukan cara efektif untuk merepresentasikan pengetahuan di dalam komputer dalam bentuk data, agar dapat digunakan secara otomatis. Ini dapat dilihat sebagai spektrum: -![Spektrum representasi pengetahuan](../../../../../../translated_images/id/knowledge-spectrum.b60df631852c0217.webp) +![Spektrum representasi pengetahuan](../../../../translated_images/id/knowledge-spectrum.b60df631852c0217.webp) > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) @@ -94,7 +85,7 @@ Sintaks Blok | Inden | | | Salah satu keberhasilan awal AI simbolik adalah yang disebut **sistem pakar**—sistem komputer yang dirancang untuk bertindak sebagai ahli dalam domain masalah terbatas. Sistem ini didasarkan pada **basis pengetahuan** yang diambil dari satu atau lebih ahli manusia, dan mereka memiliki **mesin inferensi** yang melakukan penalaran di atasnya. -![Arsitektur Manusia](../../../../../../translated_images/id/arch-human.5d4d35f1bba3ab1c.webp) | ![Sistem Berbasis Pengetahuan](../../../../../../translated_images/id/arch-kbs.3ec5c150b09fa8da.webp) +![Arsitektur Manusia](../../../../translated_images/id/arch-human.5d4d35f1bba3ab1c.webp) | ![Sistem Berbasis Pengetahuan](../../../../translated_images/id/arch-kbs.3ec5c150b09fa8da.webp) ---------------------------------------------|------------------------------------------------ Struktur sederhana sistem saraf manusia | Arsitektur sistem berbasis pengetahuan @@ -106,7 +97,7 @@ Sistem pakar dibangun seperti sistem penalaran manusia, yang berisi **memori jan Sebagai contoh, mari kita lihat sistem pakar berikut untuk menentukan hewan berdasarkan karakteristik fisiknya: -![Pohon AND-OR](../../../../../../translated_images/id/AND-OR-Tree.5592d2c70187f283.webp) +![Pohon AND-OR](../../../../translated_images/id/AND-OR-Tree.5592d2c70187f283.webp) > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/id/lessons/2-Symbolic/assignment.md b/translations/id/lessons/2-Symbolic/assignment.md index c96af336..b3ccb67a 100644 --- a/translations/id/lessons/2-Symbolic/assignment.md +++ b/translations/id/lessons/2-Symbolic/assignment.md @@ -1,12 +1,3 @@ - # Membangun Ontologi Membangun basis pengetahuan adalah tentang mengategorikan sebuah model yang merepresentasikan fakta-fakta tentang suatu topik. Pilih sebuah topik - seperti seseorang, sebuah tempat, atau sebuah benda - lalu bangun model dari topik tersebut. Gunakan beberapa teknik dan strategi pembangunan model yang dijelaskan dalam pelajaran ini. Contohnya adalah membuat ontologi dari sebuah ruang tamu dengan furnitur, lampu, dan sebagainya. Bagaimana ruang tamu berbeda dari dapur? Kamar mandi? Bagaimana Anda tahu itu adalah ruang tamu dan bukan ruang makan? Gunakan [Protégé](https://protege.stanford.edu/) untuk membangun ontologi Anda. diff --git a/translations/id/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/id/lessons/3-NeuralNetworks/03-Perceptron/README.md index 884d4eee..2f6c9bfb 100644 --- a/translations/id/lessons/3-NeuralNetworks/03-Perceptron/README.md +++ b/translations/id/lessons/3-NeuralNetworks/03-Perceptron/README.md @@ -1,12 +1,3 @@ - # Pengantar Jaringan Neural: Perceptron ## [Kuis Pra-Pelajaran](https://ff-quizzes.netlify.app/en/ai/quiz/5) @@ -15,7 +6,7 @@ Salah satu upaya pertama untuk mengimplementasikan sesuatu yang mirip dengan jar | | | |--------------|-----------| -|Frank Rosenblatt | The Mark 1 Perceptron| +|Frank Rosenblatt | The Mark 1 Perceptron| > Gambar [dari Wikipedia](https://en.wikipedia.org/wiki/Perceptron) @@ -34,7 +25,7 @@ y(x) = f(wTx) di mana f adalah fungsi aktivasi langkah. - + ## Melatih Perceptron diff --git a/translations/id/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/id/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md index 1f81e3b7..d13a33d8 100644 --- a/translations/id/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md +++ b/translations/id/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md @@ -1,12 +1,3 @@ - # Klasifikasi Multi-Kelas dengan Perceptron Tugas Lab dari [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/README.md index db33618e..f65602f8 100644 --- a/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/README.md +++ b/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/README.md @@ -1,12 +1,3 @@ - # Pengantar Jaringan Neural. Multi-Layered Perceptron Pada bagian sebelumnya, Anda telah mempelajari model jaringan neural paling sederhana - perceptron satu lapis, sebuah model klasifikasi linear dua kelas. @@ -65,7 +56,7 @@ Algoritma gradient descent tetap sama, tetapi akan lebih sulit untuk menghitung Perhatikan bahwa bagian paling kiri dari semua ekspresi tersebut adalah sama, sehingga kita dapat secara efektif menghitung turunan mulai dari fungsi kerugian dan bergerak "mundur" melalui grafik komputasi. Oleh karena itu, metode pelatihan perceptron multi-lapis disebut **backpropagation**, atau 'backprop'. -compute graph +compute graph > TODO: sitasi gambar diff --git a/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md index 37d1dbf2..c8c8782a 100644 --- a/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md +++ b/translations/id/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md @@ -1,12 +1,3 @@ - # Klasifikasi MNIST dengan Kerangka Kerja Kita Sendiri Tugas Lab dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/id/lessons/3-NeuralNetworks/05-Frameworks/README.md index 14a5a26e..cc1a6364 100644 --- a/translations/id/lessons/3-NeuralNetworks/05-Frameworks/README.md +++ b/translations/id/lessons/3-NeuralNetworks/05-Frameworks/README.md @@ -1,12 +1,3 @@ - # Kerangka Jaringan Neural Seperti yang telah kita pelajari sebelumnya, untuk dapat melatih jaringan neural secara efisien, kita perlu melakukan dua hal: diff --git a/translations/id/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/id/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md index 072a7101..03d1473d 100644 --- a/translations/id/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md +++ b/translations/id/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md @@ -1,12 +1,3 @@ - # Klasifikasi dengan PyTorch/TensorFlow Tugas Lab dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/3-NeuralNetworks/README.md b/translations/id/lessons/3-NeuralNetworks/README.md index c3f7eace..65daac3e 100644 --- a/translations/id/lessons/3-NeuralNetworks/README.md +++ b/translations/id/lessons/3-NeuralNetworks/README.md @@ -1,12 +1,3 @@ - # Pengantar Jaringan Neural ![Ringkasan konten pengantar Jaringan Neural dalam bentuk doodle](../../../../translated_images/id/ai-neuralnetworks.1c687ae40bc86e83.webp) diff --git a/translations/id/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/id/lessons/4-ComputerVision/06-IntroCV/README.md index f7f13226..7fb69f9d 100644 --- a/translations/id/lessons/4-ComputerVision/06-IntroCV/README.md +++ b/translations/id/lessons/4-ComputerVision/06-IntroCV/README.md @@ -1,12 +1,3 @@ - # Pengantar Computer Vision [Computer Vision](https://wikipedia.org/wiki/Computer_vision) adalah disiplin ilmu yang bertujuan untuk memungkinkan komputer memahami gambar digital pada tingkat tinggi. Definisi ini cukup luas, karena *pemahaman* dapat berarti banyak hal, termasuk menemukan objek dalam gambar (**deteksi objek**), memahami apa yang sedang terjadi (**deteksi peristiwa**), mendeskripsikan gambar dalam teks, atau merekonstruksi sebuah adegan dalam 3D. Ada juga tugas-tugas khusus terkait gambar manusia: estimasi usia dan emosi, deteksi dan identifikasi wajah, serta estimasi pose 3D, untuk menyebut beberapa contoh. @@ -115,7 +106,7 @@ Baca lebih lanjut tentang optical flow [dalam tutorial hebat ini](https://learno Dalam lab ini, Anda akan merekam video dengan gerakan sederhana, dan tujuan Anda adalah mengekstrak gerakan atas/bawah/kiri/kanan menggunakan optical flow. -Frame Gerakan Telapak Tangan +Frame Gerakan Telapak Tangan --- diff --git a/translations/id/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/id/lessons/4-ComputerVision/06-IntroCV/lab/README.md index 5d5a5238..065ef9a8 100644 --- a/translations/id/lessons/4-ComputerVision/06-IntroCV/lab/README.md +++ b/translations/id/lessons/4-ComputerVision/06-IntroCV/lab/README.md @@ -1,12 +1,3 @@ - # Mendeteksi Gerakan menggunakan Optical Flow Tugas Lab dari [Kurikulum AI untuk Pemula](https://aka.ms/ai-beginners). diff --git a/translations/id/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/id/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md index 34e62a22..ce72c0c3 100644 --- a/translations/id/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md +++ b/translations/id/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md @@ -1,12 +1,3 @@ - # Arsitektur CNN yang Terkenal ### VGG-16 @@ -25,7 +16,7 @@ Seperti yang dapat Anda lihat, VGG mengikuti arsitektur piramida tradisional, ya ResNet adalah keluarga model yang diusulkan oleh Microsoft Research pada tahun 2015. Ide utama dari ResNet adalah menggunakan **blok residual**: - + > Gambar dari [makalah ini](https://arxiv.org/pdf/1512.03385.pdf) @@ -37,7 +28,7 @@ Anda juga dapat menganggap jaringan ini mampu menyesuaikan kompleksitasnya denga Arsitektur Google Inception membawa ide ini lebih jauh, dan membangun setiap lapisan jaringan sebagai kombinasi dari beberapa jalur berbeda: - + > Gambar dari [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) diff --git a/translations/id/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/id/lessons/4-ComputerVision/07-ConvNets/README.md index a0be66ba..a72bad91 100644 --- a/translations/id/lessons/4-ComputerVision/07-ConvNets/README.md +++ b/translations/id/lessons/4-ComputerVision/07-ConvNets/README.md @@ -1,12 +1,3 @@ - # Convolutional Neural Networks Kita telah melihat sebelumnya bahwa jaringan neural cukup baik dalam menangani gambar, bahkan perceptron satu lapis mampu mengenali angka tulisan tangan dari dataset MNIST dengan akurasi yang cukup baik. Namun, dataset MNIST sangatlah spesial, di mana semua angka sudah dipusatkan di dalam gambar, sehingga tugas menjadi lebih sederhana. @@ -24,7 +15,7 @@ Untuk mengekstrak pola, kita akan menggunakan konsep **filter konvolusi**. Seper Sebagai contoh, jika kita menerapkan filter tepi vertikal dan horizontal 3x3 pada angka MNIST, kita dapat memperoleh sorotan (misalnya nilai tinggi) di mana terdapat tepi vertikal dan horizontal dalam gambar asli kita. Jadi, kedua filter tersebut dapat digunakan untuk "mencari" tepi. Demikian pula, kita dapat merancang filter berbeda untuk mencari pola tingkat rendah lainnya: - + > Gambar dari [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html) diff --git a/translations/id/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/id/lessons/4-ComputerVision/07-ConvNets/lab/README.md index 74a174e3..1f3a3d7d 100644 --- a/translations/id/lessons/4-ComputerVision/07-ConvNets/lab/README.md +++ b/translations/id/lessons/4-ComputerVision/07-ConvNets/lab/README.md @@ -1,12 +1,3 @@ - # Klasifikasi Wajah Hewan Peliharaan Tugas Lab dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/id/lessons/4-ComputerVision/08-TransferLearning/README.md index 3d3d0c98..b433569e 100644 --- a/translations/id/lessons/4-ComputerVision/08-TransferLearning/README.md +++ b/translations/id/lessons/4-ComputerVision/08-TransferLearning/README.md @@ -1,12 +1,3 @@ - # Jaringan Pra-Latih dan Transfer Learning Melatih CNN bisa memakan waktu lama, dan membutuhkan banyak data untuk tugas tersebut. Namun, sebagian besar waktu dihabiskan untuk mempelajari filter tingkat rendah terbaik yang dapat digunakan jaringan untuk mengekstrak pola dari gambar. Pertanyaan alami muncul - bisakah kita menggunakan jaringan neural yang telah dilatih pada satu dataset dan mengadaptasinya untuk mengklasifikasikan gambar yang berbeda tanpa memerlukan proses pelatihan penuh? diff --git a/translations/id/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/id/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md index 0709de15..6810b88e 100644 --- a/translations/id/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md +++ b/translations/id/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md @@ -1,12 +1,3 @@ - # Trik Pelatihan Deep Learning Saat jaringan neural menjadi semakin dalam, proses pelatihannya menjadi semakin menantang. Salah satu masalah utama adalah yang disebut [vanishing gradients](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) atau [exploding gradients](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Postingan ini](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) memberikan pengantar yang baik tentang masalah tersebut. diff --git a/translations/id/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/id/lessons/4-ComputerVision/08-TransferLearning/lab/README.md index 45b92bcb..332f1210 100644 --- a/translations/id/lessons/4-ComputerVision/08-TransferLearning/lab/README.md +++ b/translations/id/lessons/4-ComputerVision/08-TransferLearning/lab/README.md @@ -1,12 +1,3 @@ - # Klasifikasi Oxford Pets menggunakan Transfer Learning Tugas Praktikum dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/id/lessons/4-ComputerVision/09-Autoencoders/README.md index 983a1239..43c35a64 100644 --- a/translations/id/lessons/4-ComputerVision/09-Autoencoders/README.md +++ b/translations/id/lessons/4-ComputerVision/09-Autoencoders/README.md @@ -1,12 +1,3 @@ - # Autoencoder Saat melatih CNN, salah satu masalah yang dihadapi adalah kebutuhan akan banyak data berlabel. Dalam kasus klasifikasi gambar, kita perlu memisahkan gambar ke dalam berbagai kelas, yang memerlukan upaya manual. @@ -46,7 +37,7 @@ Ringkasnya: * Kita mengambil sampel vektor `sample` dari distribusi N(zmean,exp(zlog\_sigma)) * Decoder mencoba mendekode gambar asli menggunakan `sample` sebagai vektor input - + > Gambar dari [blog post ini](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) oleh Isaak Dykeman @@ -57,13 +48,13 @@ Variational auto-encoder menggunakan fungsi loss yang kompleks yang terdiri dari Salah satu keuntungan penting dari VAE adalah memungkinkan kita untuk menghasilkan gambar baru dengan relatif mudah, karena kita tahu distribusi mana yang harus digunakan untuk mengambil sampel vektor laten. Sebagai contoh, jika kita melatih VAE dengan vektor laten 2D pada MNIST, kita kemudian dapat memvariasikan komponen vektor laten untuk mendapatkan digit yang berbeda: -vaemnist +vaemnist > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) Perhatikan bagaimana gambar-gambar saling menyatu, saat kita mulai mendapatkan vektor laten dari bagian yang berbeda dari ruang parameter laten. Kita juga dapat memvisualisasikan ruang ini dalam 2D: -vaemnist cluster +vaemnist cluster > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/id/lessons/4-ComputerVision/10-GANs/README.md b/translations/id/lessons/4-ComputerVision/10-GANs/README.md index ef3ac42d..4a45f644 100644 --- a/translations/id/lessons/4-ComputerVision/10-GANs/README.md +++ b/translations/id/lessons/4-ComputerVision/10-GANs/README.md @@ -1,12 +1,3 @@ - # Generative Adversarial Networks Di bagian sebelumnya, kita telah mempelajari tentang **model generatif**: model yang dapat menghasilkan gambar baru yang mirip dengan gambar dalam dataset pelatihan. VAE adalah contoh yang baik dari model generatif. @@ -17,7 +8,7 @@ Namun, jika kita mencoba menghasilkan sesuatu yang benar-benar bermakna, seperti Ide utama dari GAN adalah memiliki dua jaringan neural yang dilatih saling berlawanan: - + > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) @@ -41,7 +32,7 @@ Generator sedikit lebih rumit. Anda dapat menganggapnya sebagai kebalikan dari d > ✅ Karena lapisan konvolusi diimplementasikan sebagai filter linier yang melintasi gambar, dekonvolusi pada dasarnya mirip dengan konvolusi dan dapat diimplementasikan menggunakan logika lapisan yang sama. - + > Gambar oleh [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/id/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/id/lessons/4-ComputerVision/11-ObjectDetection/README.md index 20881df1..ded40435 100644 --- a/translations/id/lessons/4-ComputerVision/11-ObjectDetection/README.md +++ b/translations/id/lessons/4-ComputerVision/11-ObjectDetection/README.md @@ -1,12 +1,3 @@ - # Deteksi Objek Model klasifikasi gambar yang telah kita bahas sejauh ini mengambil gambar dan menghasilkan hasil kategoris, seperti kelas 'angka' dalam masalah MNIST. Namun, dalam banyak kasus, kita tidak hanya ingin mengetahui bahwa sebuah gambar menggambarkan objek - kita ingin menentukan lokasi mereka secara tepat. Inilah tujuan dari **deteksi objek**. diff --git a/translations/id/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/id/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md index e779dd50..d903ec5a 100644 --- a/translations/id/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md +++ b/translations/id/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md @@ -1,12 +1,3 @@ - # Deteksi Kepala menggunakan Dataset Hollywood Heads Tugas Lab dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/id/lessons/4-ComputerVision/12-Segmentation/README.md index 042b2396..2e3d15eb 100644 --- a/translations/id/lessons/4-ComputerVision/12-Segmentation/README.md +++ b/translations/id/lessons/4-ComputerVision/12-Segmentation/README.md @@ -1,12 +1,3 @@ - # Segmentasi Kita sebelumnya telah mempelajari tentang Deteksi Objek, yang memungkinkan kita untuk menemukan objek dalam gambar dengan memprediksi *bounding boxes*-nya. Namun, untuk beberapa tugas, kita tidak hanya membutuhkan bounding boxes, tetapi juga pelokalan objek yang lebih presisi. Tugas ini disebut **segmentasi**. @@ -20,7 +11,7 @@ Segmentasi dapat dilihat sebagai **klasifikasi piksel**, di mana untuk **setiap* Dalam segmentasi instance, domba-domba ini adalah objek yang berbeda, tetapi dalam segmentasi semantik semua domba direpresentasikan sebagai satu kelas. - + > Gambar dari [blog ini](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) @@ -29,7 +20,7 @@ Ada berbagai arsitektur neural untuk segmentasi, tetapi semuanya memiliki strukt * **Encoder** mengekstrak fitur dari gambar input. * **Decoder** mengubah fitur tersebut menjadi **gambar mask**, dengan ukuran dan jumlah saluran yang sesuai dengan jumlah kelas. - + > Gambar dari [publikasi ini](https://arxiv.org/pdf/2001.05566.pdf) @@ -43,7 +34,7 @@ Dalam pelajaran ini, kita akan melihat segmentasi dalam aksi dengan melatih jari > ✅ Teknik ini sangat cocok untuk jenis pencitraan medis ini, tetapi aplikasi dunia nyata apa lagi yang dapat Anda bayangkan? -navi +navi > Gambar dari Database PH2 diff --git a/translations/id/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/id/lessons/4-ComputerVision/12-Segmentation/lab/README.md index 242e3fe0..a1db2e6d 100644 --- a/translations/id/lessons/4-ComputerVision/12-Segmentation/lab/README.md +++ b/translations/id/lessons/4-ComputerVision/12-Segmentation/lab/README.md @@ -1,12 +1,3 @@ - # Segmentasi Tubuh Manusia Tugas Praktikum dari [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/4-ComputerVision/README.md b/translations/id/lessons/4-ComputerVision/README.md index be75a2a6..e70bfa30 100644 --- a/translations/id/lessons/4-ComputerVision/README.md +++ b/translations/id/lessons/4-ComputerVision/README.md @@ -1,12 +1,3 @@ - # Penglihatan Komputer ![Ringkasan konten Penglihatan Komputer dalam bentuk doodle](../../../../translated_images/id/ai-computervision.6506ebebac3fbf76.webp) diff --git a/translations/id/lessons/5-NLP/13-TextRep/README.md b/translations/id/lessons/5-NLP/13-TextRep/README.md index d0f4c583..fcbb89e5 100644 --- a/translations/id/lessons/5-NLP/13-TextRep/README.md +++ b/translations/id/lessons/5-NLP/13-TextRep/README.md @@ -1,12 +1,3 @@ - # Representasi Teks sebagai Tensor ## [Kuis Pra-Kuliah](https://ff-quizzes.netlify.app/en/ai/quiz/25) @@ -25,7 +16,7 @@ Tujuan kita adalah mengklasifikasikan berita tersebut ke dalam salah satu katego Jika kita ingin menyelesaikan tugas Pemrosesan Bahasa Alami (NLP) dengan jaringan saraf, kita memerlukan cara untuk merepresentasikan teks sebagai tensor. Komputer sudah merepresentasikan karakter teks sebagai angka yang dipetakan ke font di layar Anda menggunakan encoding seperti ASCII atau UTF-8. -Gambar menunjukkan diagram pemetaan karakter ke representasi ASCII dan biner +Gambar menunjukkan diagram pemetaan karakter ke representasi ASCII dan biner > [Sumber gambar](https://www.seobility.net/en/wiki/ASCII) @@ -48,7 +39,7 @@ Dalam beberapa kasus, kita mungkin mempertimbangkan menggunakan tri-gram -- komb Saat menyelesaikan tugas seperti klasifikasi teks, kita perlu dapat merepresentasikan teks dengan satu vektor berukuran tetap, yang akan kita gunakan sebagai input untuk pengklasifikasi padat akhir. Salah satu cara termudah untuk melakukannya adalah dengan menggabungkan semua representasi kata individu, misalnya dengan menambahkannya. Jika kita menambahkan one-hot encoding dari setiap kata, kita akan mendapatkan vektor frekuensi, yang menunjukkan berapa kali setiap kata muncul dalam teks. Representasi teks semacam ini disebut **bag of words** (BoW). - + > Gambar oleh penulis diff --git a/translations/id/lessons/5-NLP/13-TextRep/assignment.md b/translations/id/lessons/5-NLP/13-TextRep/assignment.md index d704e843..096248df 100644 --- a/translations/id/lessons/5-NLP/13-TextRep/assignment.md +++ b/translations/id/lessons/5-NLP/13-TextRep/assignment.md @@ -1,12 +1,3 @@ - # Tugas: Notebook Gunakan notebook yang terkait dengan pelajaran ini (baik versi PyTorch maupun TensorFlow), jalankan ulang menggunakan dataset Anda sendiri, mungkin dari Kaggle, dengan mencantumkan atribusi. Tulis ulang notebook untuk menyoroti temuan Anda sendiri. Cobalah beberapa dataset inovatif yang mungkin memberikan kejutan, seperti [dataset tentang penampakan UFO ini](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) dari NUFORC. diff --git a/translations/id/lessons/5-NLP/14-Embeddings/README.md b/translations/id/lessons/5-NLP/14-Embeddings/README.md index ec851097..ea2b12e3 100644 --- a/translations/id/lessons/5-NLP/14-Embeddings/README.md +++ b/translations/id/lessons/5-NLP/14-Embeddings/README.md @@ -1,12 +1,3 @@ - # Embeddings ## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/27) diff --git a/translations/id/lessons/5-NLP/14-Embeddings/assignment.md b/translations/id/lessons/5-NLP/14-Embeddings/assignment.md index 2a3b2510..64d35e11 100644 --- a/translations/id/lessons/5-NLP/14-Embeddings/assignment.md +++ b/translations/id/lessons/5-NLP/14-Embeddings/assignment.md @@ -1,12 +1,3 @@ - # Tugas: Notebooks Gunakan notebook yang terkait dengan pelajaran ini (baik versi PyTorch maupun TensorFlow), jalankan ulang menggunakan dataset Anda sendiri, mungkin dari Kaggle, dengan mencantumkan atribusi. Tulis ulang notebook untuk menyoroti temuan Anda sendiri. Cobalah jenis dataset yang berbeda dan dokumentasikan temuan Anda, menggunakan teks seperti [lirik lagu Beatles ini](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics). diff --git a/translations/id/lessons/5-NLP/15-LanguageModeling/README.md b/translations/id/lessons/5-NLP/15-LanguageModeling/README.md index f8f33f8e..13cb94ac 100644 --- a/translations/id/lessons/5-NLP/15-LanguageModeling/README.md +++ b/translations/id/lessons/5-NLP/15-LanguageModeling/README.md @@ -1,12 +1,3 @@ - # Pemodelan Bahasa Embedding semantik, seperti Word2Vec dan GloVe, sebenarnya adalah langkah awal menuju **pemodelan bahasa** - menciptakan model yang dapat *memahami* (atau *merepresentasikan*) sifat dari bahasa. diff --git a/translations/id/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/id/lessons/5-NLP/15-LanguageModeling/lab/README.md index ba667d91..ff78b3a1 100644 --- a/translations/id/lessons/5-NLP/15-LanguageModeling/lab/README.md +++ b/translations/id/lessons/5-NLP/15-LanguageModeling/lab/README.md @@ -1,12 +1,3 @@ - # Melatih Model Skip-Gram Tugas Praktikum dari [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/5-NLP/16-RNN/README.md b/translations/id/lessons/5-NLP/16-RNN/README.md index 3d8aa08b..1a35dc72 100644 --- a/translations/id/lessons/5-NLP/16-RNN/README.md +++ b/translations/id/lessons/5-NLP/16-RNN/README.md @@ -1,12 +1,3 @@ - # Jaringan Saraf Rekurens ## [Kuis Pra-Kuliah](https://ff-quizzes.netlify.app/en/ai/quiz/31) @@ -31,7 +22,7 @@ Mari kita lihat bagaimana sebuah sel RNN sederhana diorganisasi. Sel ini menerim Sebuah sel RNN sederhana memiliki dua matriks bobot di dalamnya: satu untuk mentransformasi simbol input (kita sebut W), dan satu lagi untuk mentransformasi state input (H). Dalam kasus ini, output jaringan dihitung sebagai σ(W×Xi+H×Si-1+b), di mana σ adalah fungsi aktivasi dan b adalah bias tambahan. -Anatomi Sel RNN +Anatomi Sel RNN > Gambar oleh penulis diff --git a/translations/id/lessons/5-NLP/16-RNN/assignment.md b/translations/id/lessons/5-NLP/16-RNN/assignment.md index 9fd3ec1e..93266e7f 100644 --- a/translations/id/lessons/5-NLP/16-RNN/assignment.md +++ b/translations/id/lessons/5-NLP/16-RNN/assignment.md @@ -1,12 +1,3 @@ - # Tugas: Notebook Gunakan notebook yang terkait dengan pelajaran ini (baik versi PyTorch maupun TensorFlow), jalankan ulang menggunakan dataset Anda sendiri, mungkin dari Kaggle, dengan mencantumkan atribusi. Tulis ulang notebook tersebut untuk menyoroti temuan Anda sendiri. Cobalah jenis dataset yang berbeda dan dokumentasikan temuan Anda, menggunakan teks seperti [dataset kompetisi Kaggle tentang tweet cuaca ini](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv). diff --git a/translations/id/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/id/lessons/5-NLP/17-GenerativeNetworks/README.md index ecddacae..28f847f2 100644 --- a/translations/id/lessons/5-NLP/17-GenerativeNetworks/README.md +++ b/translations/id/lessons/5-NLP/17-GenerativeNetworks/README.md @@ -1,12 +1,3 @@ - # Jaringan Generatif ## [Kuis Pra-Kuliah](https://ff-quizzes.netlify.app/en/ai/quiz/33) @@ -36,7 +27,7 @@ Kita akan melatih RNN ini untuk menghasilkan teks langkah demi langkah. Pada set Saat menghasilkan teks (selama inferensi), kita mulai dengan beberapa **prompt**, yang dilewatkan melalui sel RNN untuk menghasilkan status intermediate-nya, dan kemudian dari status ini proses generasi dimulai. Kita menghasilkan satu karakter pada satu waktu, dan melewatkan status serta karakter yang dihasilkan ke sel RNN lainnya untuk menghasilkan karakter berikutnya, hingga kita menghasilkan cukup karakter. - + > Gambar oleh penulis diff --git a/translations/id/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/id/lessons/5-NLP/17-GenerativeNetworks/lab/README.md index 0217dfea..52e09401 100644 --- a/translations/id/lessons/5-NLP/17-GenerativeNetworks/lab/README.md +++ b/translations/id/lessons/5-NLP/17-GenerativeNetworks/lab/README.md @@ -1,12 +1,3 @@ - # Generasi Teks Tingkat Kata menggunakan RNN Tugas Lab dari [Kurikulum AI untuk Pemula](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/5-NLP/18-Transformers/README.md b/translations/id/lessons/5-NLP/18-Transformers/README.md index 19d7ef12..93af76dd 100644 --- a/translations/id/lessons/5-NLP/18-Transformers/README.md +++ b/translations/id/lessons/5-NLP/18-Transformers/README.md @@ -1,12 +1,3 @@ - # Mekanisme Perhatian dan Transformer ## [Kuis sebelum pelajaran](https://ff-quizzes.netlify.app/en/ai/quiz/35) @@ -56,7 +47,7 @@ Ide dari encoding posisi adalah sebagai berikut. * Embedding yang dapat dilatih, mirip dengan embedding token. Ini adalah pendekatan yang kita pertimbangkan di sini. Kita menerapkan lapisan embedding di atas token dan posisinya, menghasilkan vektor embedding dengan dimensi yang sama, yang kemudian kita tambahkan bersama. * Fungsi encoding posisi tetap, seperti yang diusulkan dalam makalah asli. - + > Gambar oleh penulis diff --git a/translations/id/lessons/5-NLP/18-Transformers/assignment.md b/translations/id/lessons/5-NLP/18-Transformers/assignment.md index 6ab92579..33abce51 100644 --- a/translations/id/lessons/5-NLP/18-Transformers/assignment.md +++ b/translations/id/lessons/5-NLP/18-Transformers/assignment.md @@ -1,12 +1,3 @@ - # Tugas: Transformers Bereksperimenlah dengan Transformers di HuggingFace! Cobalah beberapa skrip yang mereka sediakan untuk bekerja dengan berbagai model yang tersedia di situs mereka: https://huggingface.co/docs/transformers/run_scripts. Cobalah salah satu dataset mereka, lalu impor salah satu dataset Anda sendiri dari kurikulum ini atau dari Kaggle dan lihat apakah Anda dapat menghasilkan teks yang menarik. Buatlah sebuah notebook dengan temuan Anda. diff --git a/translations/id/lessons/5-NLP/19-NER/README.md b/translations/id/lessons/5-NLP/19-NER/README.md index fe0fa1eb..3d2537bf 100644 --- a/translations/id/lessons/5-NLP/19-NER/README.md +++ b/translations/id/lessons/5-NLP/19-NER/README.md @@ -1,12 +1,3 @@ - # Named Entity Recognition Hingga saat ini, kita sebagian besar telah berfokus pada satu tugas NLP - klasifikasi. Namun, ada juga tugas NLP lainnya yang dapat diselesaikan dengan jaringan neural. Salah satu tugas tersebut adalah **[Named Entity Recognition](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), yang berhubungan dengan mengenali entitas spesifik dalam teks, seperti tempat, nama orang, interval waktu, rumus kimia, dan sebagainya. @@ -17,7 +8,7 @@ Hingga saat ini, kita sebagian besar telah berfokus pada satu tugas NLP - klasif Misalkan Anda ingin mengembangkan chatbot berbasis bahasa alami, seperti Amazon Alexa atau Google Assistant. Cara kerja chatbot cerdas adalah dengan *memahami* apa yang diinginkan pengguna melalui klasifikasi teks pada kalimat masukan. Hasil dari klasifikasi ini disebut **intent**, yang menentukan apa yang harus dilakukan oleh chatbot. -Bot NER +Bot NER > Gambar oleh penulis diff --git a/translations/id/lessons/5-NLP/19-NER/lab/README.md b/translations/id/lessons/5-NLP/19-NER/lab/README.md index 53c25cd0..d48e280e 100644 --- a/translations/id/lessons/5-NLP/19-NER/lab/README.md +++ b/translations/id/lessons/5-NLP/19-NER/lab/README.md @@ -1,12 +1,3 @@ - # NER Tugas Lab dari [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/id/lessons/5-NLP/20-LangModels/README.md b/translations/id/lessons/5-NLP/20-LangModels/README.md index d5549f45..ce85d08c 100644 --- a/translations/id/lessons/5-NLP/20-LangModels/README.md +++ b/translations/id/lessons/5-NLP/20-LangModels/README.md @@ -1,12 +1,3 @@ - # Model Bahasa Besar yang Telah Dilatih Sebelumnya Dalam semua tugas sebelumnya, kita melatih jaringan neural untuk melakukan tugas tertentu menggunakan dataset berlabel. Dengan model transformer besar, seperti BERT, kita menggunakan pemodelan bahasa secara mandiri untuk membangun model bahasa, yang kemudian disesuaikan untuk tugas spesifik dengan pelatihan lebih lanjut yang sesuai dengan domain. Namun, telah terbukti bahwa model bahasa besar juga dapat menyelesaikan banyak tugas tanpa pelatihan khusus domain. Keluarga model yang mampu melakukan hal tersebut disebut **GPT**: Generative Pre-Trained Transformer. diff --git a/translations/id/lessons/5-NLP/README.md b/translations/id/lessons/5-NLP/README.md index a504137b..da537e75 100644 --- a/translations/id/lessons/5-NLP/README.md +++ b/translations/id/lessons/5-NLP/README.md @@ -1,12 +1,3 @@ - # Pemrosesan Bahasa Alami ![Ringkasan tugas NLP dalam bentuk doodle](../../../../translated_images/id/ai-nlp.b22dcb8ca4707cea.webp) diff --git a/translations/id/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/id/lessons/6-Other/21-GeneticAlgorithms/README.md index 8c053b19..d538303b 100644 --- a/translations/id/lessons/6-Other/21-GeneticAlgorithms/README.md +++ b/translations/id/lessons/6-Other/21-GeneticAlgorithms/README.md @@ -1,12 +1,3 @@ - # Algoritma Genetika ## [Kuis sebelum kuliah](https://ff-quizzes.netlify.app/en/ai/quiz/41) diff --git a/translations/id/lessons/6-Other/22-DeepRL/README.md b/translations/id/lessons/6-Other/22-DeepRL/README.md index 3478b96b..de8e7d4b 100644 --- a/translations/id/lessons/6-Other/22-DeepRL/README.md +++ b/translations/id/lessons/6-Other/22-DeepRL/README.md @@ -1,12 +1,3 @@ - # Pembelajaran Penguatan Mendalam Pembelajaran penguatan (Reinforcement Learning atau RL) dianggap sebagai salah satu paradigma dasar dalam pembelajaran mesin, selain pembelajaran terawasi dan pembelajaran tanpa pengawasan. Dalam pembelajaran terawasi, kita bergantung pada dataset dengan hasil yang sudah diketahui, sedangkan RL didasarkan pada **belajar dengan melakukan**. Misalnya, ketika kita pertama kali melihat sebuah permainan komputer, kita mulai bermain meskipun tidak tahu aturannya, dan segera kita dapat meningkatkan kemampuan kita hanya melalui proses bermain dan menyesuaikan perilaku. @@ -34,7 +25,7 @@ Anda mungkin pernah melihat perangkat keseimbangan modern seperti *Segway* atau Versi sederhana dari keseimbangan ini dikenal sebagai masalah **CartPole**. Dalam dunia CartPole, kita memiliki slider horizontal yang dapat bergerak ke kiri atau ke kanan, dan tujuannya adalah menyeimbangkan tiang vertikal di atas slider saat bergerak. -a cartpole +a cartpole Untuk membuat dan menggunakan lingkungan ini, kita membutuhkan beberapa baris kode Python: diff --git a/translations/id/lessons/6-Other/22-DeepRL/lab/README.md b/translations/id/lessons/6-Other/22-DeepRL/lab/README.md index bcdd8279..bbffd37f 100644 --- a/translations/id/lessons/6-Other/22-DeepRL/lab/README.md +++ b/translations/id/lessons/6-Other/22-DeepRL/lab/README.md @@ -1,12 +1,3 @@ - ## Lingkungan Lingkungan Mountain Car terdiri dari sebuah mobil yang terjebak di dalam lembah. Tujuan Anda adalah melompat keluar dari lembah dan mencapai bendera. Tindakan yang dapat Anda lakukan adalah mempercepat ke kiri, ke kanan, atau tidak melakukan apa-apa. Anda dapat mengamati posisi mobil di sepanjang sumbu x, dan kecepatannya. diff --git a/translations/id/lessons/6-Other/23-MultiagentSystems/README.md b/translations/id/lessons/6-Other/23-MultiagentSystems/README.md index d0397f1d..35529f09 100644 --- a/translations/id/lessons/6-Other/23-MultiagentSystems/README.md +++ b/translations/id/lessons/6-Other/23-MultiagentSystems/README.md @@ -1,12 +1,3 @@ - # Sistem Multi-Agen Salah satu cara untuk mencapai kecerdasan adalah pendekatan yang disebut **emergent** (atau **sinergis**), yang didasarkan pada fakta bahwa perilaku gabungan dari banyak agen yang relatif sederhana dapat menghasilkan perilaku sistem secara keseluruhan yang lebih kompleks (atau cerdas). Secara teori, ini didasarkan pada prinsip [Kecerdasan Kolektif](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentisme](https://en.wikipedia.org/wiki/Global_brain), dan [Sibernetika Evolusioner](https://en.wikipedia.org/wiki/Global_brain), yang menyatakan bahwa sistem tingkat tinggi memperoleh nilai tambah tertentu ketika dikombinasikan dengan benar dari sistem tingkat rendah (disebut *prinsip transisi metasistem*). @@ -60,7 +51,7 @@ Anda dapat [mengunduh](https://ccl.northwestern.edu/netlogo/download.shtml) dan Hal yang hebat tentang NetLogo adalah ia memiliki perpustakaan model yang dapat Anda coba. Pergi ke **File → Models Library**, dan Anda memiliki banyak kategori model untuk dipilih. -NetLogo Models Library +NetLogo Models Library > Tangkapan layar perpustakaan model oleh Dmitry Soshnikov diff --git a/translations/id/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/id/lessons/6-Other/23-MultiagentSystems/assignment.md index 9eae616b..f777d090 100644 --- a/translations/id/lessons/6-Other/23-MultiagentSystems/assignment.md +++ b/translations/id/lessons/6-Other/23-MultiagentSystems/assignment.md @@ -1,12 +1,3 @@ - # Tugas NetLogo Ambil salah satu model dari perpustakaan NetLogo dan gunakan untuk mensimulasikan situasi kehidupan nyata sedekat mungkin. Contoh yang baik adalah mengubah model Virus di folder Alternative Visualizations untuk menunjukkan bagaimana model tersebut dapat digunakan untuk memodelkan penyebaran COVID-19. Bisakah Anda membuat model yang meniru penyebaran virus di kehidupan nyata? diff --git a/translations/id/lessons/7-Ethics/README.md b/translations/id/lessons/7-Ethics/README.md index 0297d243..1019e488 100644 --- a/translations/id/lessons/7-Ethics/README.md +++ b/translations/id/lessons/7-Ethics/README.md @@ -1,12 +1,3 @@ - # AI yang Etis dan Bertanggung Jawab Anda hampir menyelesaikan kursus ini, dan saya harap sekarang Anda sudah memahami bahwa AI didasarkan pada sejumlah metode matematika formal yang memungkinkan kita menemukan hubungan dalam data dan melatih model untuk meniru beberapa aspek perilaku manusia. Pada titik ini dalam sejarah, kita menganggap AI sebagai alat yang sangat kuat untuk mengekstrak pola dari data, dan menerapkan pola tersebut untuk menyelesaikan masalah baru. diff --git a/translations/id/lessons/README.md b/translations/id/lessons/README.md index da01d59c..ef012f56 100644 --- a/translations/id/lessons/README.md +++ b/translations/id/lessons/README.md @@ -1,12 +1,3 @@ - # Gambaran Umum ![Gambaran Umum dalam sebuah sketsa](../../../translated_images/id/ai-overview.0857791951d19500.webp) diff --git a/translations/id/lessons/X-Extras/X1-MultiModal/README.md b/translations/id/lessons/X-Extras/X1-MultiModal/README.md index 895057bb..4dd48fd9 100644 --- a/translations/id/lessons/X-Extras/X1-MultiModal/README.md +++ b/translations/id/lessons/X-Extras/X1-MultiModal/README.md @@ -1,12 +1,3 @@ - # Jaringan Multi-Modal Setelah keberhasilan model transformer dalam menyelesaikan tugas NLP, arsitektur yang sama atau serupa telah diterapkan pada tugas penglihatan komputer. Ada minat yang semakin besar untuk membangun model yang dapat *menggabungkan* kemampuan penglihatan dan bahasa alami. Salah satu upaya tersebut dilakukan oleh OpenAI, yang disebut CLIP dan DALL.E. diff --git a/translations/id/lessons/sketchnotes/LICENSE.md b/translations/id/lessons/sketchnotes/LICENSE.md index f5c0f4b2..0fbc35f5 100644 --- a/translations/id/lessons/sketchnotes/LICENSE.md +++ b/translations/id/lessons/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - Hak Atribusi-BerbagiSerupa 4.0 Internasional ======================================================================= diff --git a/translations/id/lessons/sketchnotes/README.md b/translations/id/lessons/sketchnotes/README.md index 2b1b3357..6bd9508f 100644 --- a/translations/id/lessons/sketchnotes/README.md +++ b/translations/id/lessons/sketchnotes/README.md @@ -1,12 +1,3 @@ - Semua sketchnote kurikulum dapat diunduh di sini. 🎨 Dibuat oleh: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac)) diff --git a/translations/id/troubleshoot.md b/translations/id/troubleshoot.md index a853447e..8e00b8e3 100644 --- a/translations/id/troubleshoot.md +++ b/translations/id/troubleshoot.md @@ -1,12 +1,3 @@ - # Panduan Pemecahan Masalah AI-For-Beginners Panduan ini membantu Anda mengatasi masalah umum yang sering terjadi saat menggunakan atau berkontribusi pada repositori [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners). Setiap masalah mencakup latar belakang, gejala, penjelasan, dan solusi langkah demi langkah. diff --git a/translations/vi/.co-op-translator.json b/translations/vi/.co-op-translator.json new file mode 100644 index 00000000..2dc91474 --- /dev/null +++ b/translations/vi/.co-op-translator.json @@ -0,0 +1,398 @@ +{ + "AGENTS.md": { + "original_hash": "6b11a37115944252ab3ed04e358d830d", + "translation_date": "2025-10-03T09:25:19+00:00", + "source_file": "AGENTS.md", + "language_code": "vi" + }, + "README.md": { + "original_hash": "1984fc89dd304a8a33ab5584691a99aa", + "translation_date": "2026-01-30T02:12:13+00:00", + "source_file": "README.md", + "language_code": "vi" + }, + "SECURITY.md": { + "original_hash": "a583f49d359c7ebba61433e4dfcd05a9", + "translation_date": "2025-08-29T12:11:37+00:00", + "source_file": "SECURITY.md", + "language_code": "vi" + }, + "etc/CODE_OF_CONDUCT.md": { + "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56", + "translation_date": "2025-08-29T12:52:22+00:00", + "source_file": "etc/CODE_OF_CONDUCT.md", + "language_code": "vi" + }, + "etc/CONTRIBUTING.md": { + "original_hash": "847a587aa1b83f4d00858183ff3ed18a", + "translation_date": "2025-08-29T12:52:03+00:00", + "source_file": "etc/CONTRIBUTING.md", + "language_code": "vi" + }, + "etc/Mindmap.md": { + "original_hash": "f2f88dbd2debd38e26149b27b1fd272d", + "translation_date": "2025-08-29T12:50:54+00:00", + "source_file": "etc/Mindmap.md", + "language_code": "vi" + }, + "etc/SUPPORT.md": { + "original_hash": "fdfc08baee91e402938a2b1f94fe0949", + "translation_date": "2025-08-29T12:50:42+00:00", + "source_file": "etc/SUPPORT.md", + "language_code": "vi" + }, + "etc/TRANSLATIONS.md": { + "original_hash": "62b3e3ad5182edb905eec649a87eeeb4", + "translation_date": "2025-08-29T12:51:44+00:00", + "source_file": "etc/TRANSLATIONS.md", + "language_code": "vi" + }, + "etc/quiz-app/README.md": { + "original_hash": "d699cf8509f74baa5b0b838de5cf0662", + "translation_date": "2025-08-29T12:52:33+00:00", + "source_file": "etc/quiz-app/README.md", + "language_code": "vi" + }, + "examples/README.md": { + "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7", + "translation_date": "2025-10-03T11:32:24+00:00", + "source_file": "examples/README.md", + "language_code": "vi" + }, + "lessons/0-course-setup/for-teachers.md": { + "original_hash": "a094ef9927883de1cfcee51dbd143381", + "translation_date": "2025-08-29T12:16:06+00:00", + "source_file": "lessons/0-course-setup/for-teachers.md", + "language_code": "vi" + }, + "lessons/0-course-setup/how-to-run.md": { + "original_hash": "a4717bd9103b9f6cd84d534b83534689", + "translation_date": "2026-01-16T03:40:24+00:00", + "source_file": "lessons/0-course-setup/how-to-run.md", + "language_code": "vi" + }, + "lessons/0-course-setup/setup.md": { + "original_hash": "7b4e5b8956915870d0a0ed3cc5890042", + "translation_date": "2025-12-12T20:00:23+00:00", + "source_file": "lessons/0-course-setup/setup.md", + "language_code": "vi" + }, + "lessons/1-Intro/README.md": { + "original_hash": "f57e8aa46141fd220b16ffed8f11aec7", + "translation_date": "2025-11-18T21:45:49+00:00", + "source_file": "lessons/1-Intro/README.md", + "language_code": "vi" + }, + "lessons/1-Intro/assignment.md": { + "original_hash": "a334df77a82aaaf2a29c77065d3e481e", + "translation_date": "2025-11-18T21:47:31+00:00", + "source_file": "lessons/1-Intro/assignment.md", + "language_code": "vi" + }, + "lessons/2-Symbolic/README.md": { + "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4", + "translation_date": "2026-01-16T03:41:43+00:00", + "source_file": "lessons/2-Symbolic/README.md", + "language_code": "vi" + }, + "lessons/2-Symbolic/assignment.md": { + "original_hash": "a057a8604f3976c3e309884453f1fad0", + "translation_date": "2025-08-29T12:31:21+00:00", + "source_file": "lessons/2-Symbolic/assignment.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/03-Perceptron/README.md": { + "original_hash": "c34cbba802058b6fa267e1a294d4e510", + "translation_date": "2025-09-23T10:33:21+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": { + "original_hash": "ba5d1eb353d20d3e7181066b3c424b99", + "translation_date": "2025-08-29T12:36:15+00:00", + "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/README.md": { + "original_hash": "789d6c3fb6fc7948a470b33078a5983a", + "translation_date": "2025-09-23T10:32:59+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": { + "original_hash": "48fdd704d483e19bc3d7464074c9fcbe", + "translation_date": "2025-08-29T12:35:19+00:00", + "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/05-Frameworks/README.md": { + "original_hash": "ddd216f558a255260a9374008002c971", + "translation_date": "2025-09-23T10:33:45+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": { + "original_hash": "e452d897efb9a89700f41021834cf6e5", + "translation_date": "2025-08-29T12:37:22+00:00", + "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md", + "language_code": "vi" + }, + "lessons/3-NeuralNetworks/README.md": { + "original_hash": "f862a99d88088163df12270e2f2ad6c3", + "translation_date": "2025-10-03T12:50:52+00:00", + "source_file": "lessons/3-NeuralNetworks/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/06-IntroCV/README.md": { + "original_hash": "feeca98225cb420afc89415f24f63d92", + "translation_date": "2025-09-23T10:27:56+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/06-IntroCV/lab/README.md": { + "original_hash": "3d53d6409f80970f7281a45dee35328a", + "translation_date": "2025-08-29T12:23:46+00:00", + "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": { + "original_hash": "53faab85adfcebd8c10bcd71dc2fa557", + "translation_date": "2025-09-23T10:27:20+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/07-ConvNets/README.md": { + "original_hash": "a560d5b845962cf33dc102266e409568", + "translation_date": "2025-09-23T10:27:03+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/07-ConvNets/lab/README.md": { + "original_hash": "b70fcf7fcee862990f848c679090943f", + "translation_date": "2025-10-03T14:56:10+00:00", + "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/08-TransferLearning/README.md": { + "original_hash": "178c0b5ee5395733eb18aec51e71a0a9", + "translation_date": "2025-09-23T10:27:34+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": { + "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99", + "translation_date": "2025-08-29T12:21:25+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": { + "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2", + "translation_date": "2025-08-29T12:22:30+00:00", + "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/09-Autoencoders/README.md": { + "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d", + "translation_date": "2025-09-23T10:29:05+00:00", + "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/10-GANs/README.md": { + "original_hash": "0ff65b4da07b23697235de2beb2a3c25", + "translation_date": "2025-09-23T10:29:51+00:00", + "source_file": "lessons/4-ComputerVision/10-GANs/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/11-ObjectDetection/README.md": { + "original_hash": "d76a7eda28de5210c8b1ba50a6216c69", + "translation_date": "2025-09-23T10:28:30+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": { + "original_hash": "ad568d55ae65c856fe929fc2b278510a", + "translation_date": "2025-08-29T12:25:11+00:00", + "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/12-Segmentation/README.md": { + "original_hash": "6568aaae7e0e4afed4b5d74b5b223700", + "translation_date": "2025-09-23T10:29:32+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/12-Segmentation/lab/README.md": { + "original_hash": "365f0decfe0f47b460bbde8227c5009d", + "translation_date": "2025-08-29T12:27:12+00:00", + "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md", + "language_code": "vi" + }, + "lessons/4-ComputerVision/README.md": { + "original_hash": "58a52f000089c1d8906a4daa4ab1169b", + "translation_date": "2025-08-29T12:18:53+00:00", + "source_file": "lessons/4-ComputerVision/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/13-TextRep/README.md": { + "original_hash": "dbd3f73e4139f030ecb2e20387d70fee", + "translation_date": "2025-09-23T10:36:26+00:00", + "source_file": "lessons/5-NLP/13-TextRep/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/13-TextRep/assignment.md": { + "original_hash": "cdc1f2e631f055f3473b36d18e4760b3", + "translation_date": "2025-08-29T12:50:31+00:00", + "source_file": "lessons/5-NLP/13-TextRep/assignment.md", + "language_code": "vi" + }, + "lessons/5-NLP/14-Embeddings/README.md": { + "original_hash": "b708c9b85b833864c73c6281f1e6b96e", + "translation_date": "2025-09-23T10:36:10+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/14-Embeddings/assignment.md": { + "original_hash": "bc690ecf68b38d311cc9e12f3144a28c", + "translation_date": "2025-08-29T12:49:29+00:00", + "source_file": "lessons/5-NLP/14-Embeddings/assignment.md", + "language_code": "vi" + }, + "lessons/5-NLP/15-LanguageModeling/README.md": { + "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57", + "translation_date": "2025-09-23T10:34:29+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/15-LanguageModeling/lab/README.md": { + "original_hash": "5130f01fdc5ebb83032b23d489027aac", + "translation_date": "2025-08-29T12:43:27+00:00", + "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/16-RNN/README.md": { + "original_hash": "e2273cc150380a5e191903cea858f021", + "translation_date": "2025-09-23T10:35:48+00:00", + "source_file": "lessons/5-NLP/16-RNN/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/16-RNN/assignment.md": { + "original_hash": "47f7d3c6a5373543e051e4d1140ce898", + "translation_date": "2025-08-29T12:48:26+00:00", + "source_file": "lessons/5-NLP/16-RNN/assignment.md", + "language_code": "vi" + }, + "lessons/5-NLP/17-GenerativeNetworks/README.md": { + "original_hash": "51be6057374d01d70e07dd5ec88ebc0d", + "translation_date": "2025-09-23T10:34:11+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": { + "original_hash": "439e12796197a90e7623d4c9c057b9c2", + "translation_date": "2025-08-29T12:42:50+00:00", + "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/18-Transformers/README.md": { + "original_hash": "f335dfcb4a993920504c387973a36957", + "translation_date": "2025-09-23T10:34:39+00:00", + "source_file": "lessons/5-NLP/18-Transformers/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/18-Transformers/assignment.md": { + "original_hash": "177f3ea3995d725e6f9f5c66af16edcd", + "translation_date": "2025-08-29T12:45:13+00:00", + "source_file": "lessons/5-NLP/18-Transformers/assignment.md", + "language_code": "vi" + }, + "lessons/5-NLP/19-NER/README.md": { + "original_hash": "6522312ff835796ca34136a9462fafb2", + "translation_date": "2025-09-23T10:35:24+00:00", + "source_file": "lessons/5-NLP/19-NER/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/19-NER/lab/README.md": { + "original_hash": "032bda5068f543d6c1fcb30c34231461", + "translation_date": "2025-08-29T12:47:05+00:00", + "source_file": "lessons/5-NLP/19-NER/lab/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/20-LangModels/README.md": { + "original_hash": "97836d30a6bec736f8e3b4411c572bc2", + "translation_date": "2025-09-23T10:35:06+00:00", + "source_file": "lessons/5-NLP/20-LangModels/README.md", + "language_code": "vi" + }, + "lessons/5-NLP/README.md": { + "original_hash": "8ef02a9318257ea140ed3ed74442096d", + "translation_date": "2025-08-29T12:41:19+00:00", + "source_file": "lessons/5-NLP/README.md", + "language_code": "vi" + }, + "lessons/6-Other/21-GeneticAlgorithms/README.md": { + "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a", + "translation_date": "2025-09-23T10:25:43+00:00", + "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md", + "language_code": "vi" + }, + "lessons/6-Other/22-DeepRL/README.md": { + "original_hash": "04395657fc01648f8f70484d0e55ab67", + "translation_date": "2025-09-23T10:26:40+00:00", + "source_file": "lessons/6-Other/22-DeepRL/README.md", + "language_code": "vi" + }, + "lessons/6-Other/22-DeepRL/lab/README.md": { + "original_hash": "7bd8dc72040e98e35e7225e34058cd4e", + "translation_date": "2025-08-29T12:15:53+00:00", + "source_file": "lessons/6-Other/22-DeepRL/lab/README.md", + "language_code": "vi" + }, + "lessons/6-Other/23-MultiagentSystems/README.md": { + "original_hash": "38a1185ae3d54b180378bbd71ae3ef16", + "translation_date": "2025-09-23T10:26:00+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/README.md", + "language_code": "vi" + }, + "lessons/6-Other/23-MultiagentSystems/assignment.md": { + "original_hash": "cf654ca60c7f86c8dad28596fb42994b", + "translation_date": "2025-08-29T12:14:28+00:00", + "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md", + "language_code": "vi" + }, + "lessons/7-Ethics/README.md": { + "original_hash": "437c988596e751072e41a5aad3fcc5d9", + "translation_date": "2025-08-29T12:31:34+00:00", + "source_file": "lessons/7-Ethics/README.md", + "language_code": "vi" + }, + "lessons/README.md": { + "original_hash": "5fef1a0b22498d7188959e2a2cb08af7", + "translation_date": "2025-08-29T12:12:04+00:00", + "source_file": "lessons/README.md", + "language_code": "vi" + }, + "lessons/X-Extras/X1-MultiModal/README.md": { + "original_hash": "9c592c26aca16ca085d268c732284187", + "translation_date": "2025-08-29T12:17:33+00:00", + "source_file": "lessons/X-Extras/X1-MultiModal/README.md", + "language_code": "vi" + }, + "lessons/sketchnotes/LICENSE.md": { + "original_hash": "45ab63a2cd8f5faef6c9b150618837a4", + "translation_date": "2025-08-29T12:38:48+00:00", + "source_file": "lessons/sketchnotes/LICENSE.md", + "language_code": "vi" + }, + "lessons/sketchnotes/README.md": { + "original_hash": "050b8bddebafba55b129414e6ab096ab", + "translation_date": "2025-08-29T12:37:34+00:00", + "source_file": "lessons/sketchnotes/README.md", + "language_code": "vi" + }, + "troubleshoot.md": { + "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86", + "translation_date": "2025-10-03T09:47:20+00:00", + "source_file": "troubleshoot.md", + "language_code": "vi" + } +} \ No newline at end of file diff --git a/translations/vi/AGENTS.md b/translations/vi/AGENTS.md index 746bfd40..b2fe1c8f 100644 --- a/translations/vi/AGENTS.md +++ b/translations/vi/AGENTS.md @@ -1,12 +1,3 @@ - # AGENTS.md ## Tổng quan dự án diff --git a/translations/vi/README.md b/translations/vi/README.md index 0bac4dbd..4661b0ff 100644 --- a/translations/vi/README.md +++ b/translations/vi/README.md @@ -1,21 +1,12 @@ - -[![GitHub license](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE) -[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/) -[![GitHub issues](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/) -[![GitHub pull-requests](https://img.shields.io/github/issues-pr/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/pulls/) -[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) +[![Giấy phép GitHub](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE) +[![Người đóng góp GitHub](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/) +[![Vấn đề GitHub](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/) +[![Yêu cầu kéo GitHub](https://img.shields.io/github/issues-pr/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/pulls/) +[![Chào mừng PR](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) -[![GitHub watchers](https://img.shields.io/github/watchers/microsoft/AI-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/AI-For-Beginners/watchers/) -[![GitHub forks](https://img.shields.io/github/forks/microsoft/AI-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/AI-For-Beginners/network/) -[![GitHub stars](https://img.shields.io/github/stars/microsoft/AI-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/AI-For-Beginners/stargazers/) +[![Người quan sát GitHub](https://img.shields.io/github/watchers/microsoft/AI-For-Beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/AI-For-Beginners/watchers/) +[![Forks GitHub](https://img.shields.io/github/forks/microsoft/AI-For-Beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/AI-For-Beginners/network/) +[![Ngôi sao GitHub](https://img.shields.io/github/stars/microsoft/AI-For-Beginners.svg?style=social&label=Star)](https://GitHub.com/microsoft/AI-For-Beginners/stargazers/) [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/microsoft/ai-for-beginners/HEAD) [![Gitter](https://badges.gitter.im/Microsoft/ai-for-beginners.svg)](https://gitter.im/Microsoft/ai-for-beginners?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge) @@ -23,28 +14,29 @@ CO_OP_TRANSLATOR_METADATA: # Trí Tuệ Nhân Tạo cho Người Mới Bắt Đầu - Chương Trình Học -|![Sketchnote by @girlie_mac https://twitter.com/girlie_mac](../../../../translated_images/vi/ai-overview.0857791951d19500.webp)| +|![Sketchnote by @girlie_mac https://twitter.com/girlie_mac](../../translated_images/vi/ai-overview.0857791951d19500.webp)| |:---:| | AI For Beginners - _Sketchnote bởi [@girlie_mac](https://twitter.com/girlie_mac)_ | -Khám phá thế giới **Trí Tuệ Nhân Tạo** (AI) với chương trình học dài 12 tuần, gồm 24 bài học! Bao gồm các bài học thực hành, câu đố và phòng thí nghiệm. Chương trình phù hợp cho người mới bắt đầu và bao quát công cụ như TensorFlow và PyTorch, cũng như đạo đức trong AI. +Khám phá thế giới của **Trí Tuệ Nhân Tạo** (AI) với chương trình học 12 tuần, 24 bài học! Bao gồm các bài học thực hành, câu đố và phòng lab. Chương trình học thân thiện với người mới bắt đầu và bao gồm các công cụ như TensorFlow và PyTorch, cũng như đạo đức trong AI -### 🌐 Hỗ trợ Đa Ngôn Ngữ -#### Hỗ trợ qua GitHub Action (Tự động & Luôn cập nhật) +### 🌐 Hỗ Trợ Đa Ngôn Ngữ + +#### Hỗ trợ qua GitHub Action (Tự động & Luôn Cập Nhật) -[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](./README.md) +[Tiếng Ả Rập](../ar/README.md) | [Tiếng Bengal](../bn/README.md) | [Tiếng Bulgaria](../bg/README.md) | [Tiếng Miến Điện (Myanmar)](../my/README.md) | [Tiếng Trung (Giản thể)](../zh-CN/README.md) | [Tiếng Trung (Phồn thể, Hồng Kông)](../zh-HK/README.md) | [Tiếng Trung (Phồn thể, Macau)](../zh-MO/README.md) | [Tiếng Trung (Phồn thể, Đài Loan)](../zh-TW/README.md) | [Tiếng Croatia](../hr/README.md) | [Tiếng Séc](../cs/README.md) | [Tiếng Đan Mạch](../da/README.md) | [Tiếng Hà Lan](../nl/README.md) | [Tiếng Estonia](../et/README.md) | [Tiếng Phần Lan](../fi/README.md) | [Tiếng Pháp](../fr/README.md) | [Tiếng Đức](../de/README.md) | [Tiếng Hy Lạp](../el/README.md) | [Tiếng Hebrew](../he/README.md) | [Tiếng Hindi](../hi/README.md) | [Tiếng Hungary](../hu/README.md) | [Tiếng Indonesia](../id/README.md) | [Tiếng Ý](../it/README.md) | [Tiếng Nhật](../ja/README.md) | [Tiếng Kannada](../kn/README.md) | [Tiếng Hàn](../ko/README.md) | [Tiếng Lithuania](../lt/README.md) | [Tiếng Malay](../ms/README.md) | [Tiếng Malayalam](../ml/README.md) | [Tiếng Marathi](../mr/README.md) | [Tiếng Nepal](../ne/README.md) | [Tiếng Pidgin Nigeria](../pcm/README.md) | [Tiếng Na Uy](../no/README.md) | [Tiếng Ba Tư (Farsi)](../fa/README.md) | [Tiếng Ba Lan](../pl/README.md) | [Tiếng Bồ Đào Nha (Brazil)](../pt-BR/README.md) | [Tiếng Bồ Đào Nha (Bồ Đào Nha)](../pt-PT/README.md) | [Tiếng Punjab (Gurmukhi)](../pa/README.md) | [Tiếng Romania](../ro/README.md) | [Tiếng Nga](../ru/README.md) | [Tiếng Serbia (Chữ Kirin)](../sr/README.md) | [Tiếng Slovakia](../sk/README.md) | [Tiếng Slovenia](../sl/README.md) | [Tiếng Tây Ban Nha](../es/README.md) | [Tiếng Swahili](../sw/README.md) | [Tiếng Thụy Điển](../sv/README.md) | [Tiếng Tagalog (Filipino)](../tl/README.md) | [Tiếng Tamil](../ta/README.md) | [Tiếng Telugu](../te/README.md) | [Tiếng Thái](../th/README.md) | [Tiếng Thổ Nhĩ Kỳ](../tr/README.md) | [Tiếng Ukraina](../uk/README.md) | [Tiếng Urdu](../ur/README.md) | [Tiếng Việt](./README.md) -> **Ưu tiên tải về máy?** +> **Ưu tiên Sao Chép Cục Bộ?** -> Kho chứa này bao gồm hơn 50 bản dịch ngôn ngữ làm tăng đáng kể kích thước tải về. Để tải về mà không có các bản dịch, hãy dùng sparse checkout: +> Kho lưu trữ này bao gồm hơn 50 bản dịch ngôn ngữ, điều này làm tăng đáng kể kích thước tải xuống. Để sao chép mà không có bản dịch, sử dụng 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' > ``` -> Điều này cung cấp cho bạn mọi thứ cần thiết để hoàn thành khóa học với tốc độ tải về nhanh hơn nhiều. +> Điều này cung cấp cho bạn tất cả những gì cần thiết để hoàn thành khóa học với tốc độ tải xuống nhanh hơn nhiều. **Nếu bạn muốn có thêm các ngôn ngữ dịch được hỗ trợ, danh sách có tại [đây](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** @@ -54,180 +46,181 @@ Khám phá thế giới **Trí Tuệ Nhân Tạo** (AI) với chương trình h ## Bạn sẽ học được gì -**[Bản đồ tư duy của Khóa học](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** +**[Sơ đồ tư duy của khóa học](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)** -Trong chương trình này, bạn sẽ học: +Trong chương trình học này, bạn sẽ học: -* Các phương pháp khác nhau về Trí Tuệ Nhân Tạo, bao gồm phương pháp "cổ điển" biểu tượng với **Biểu diễn Kiến thức** và suy luận ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). -* **Mạng Nơ-ron** và **Học sâu**, là cốt lõi của AI hiện đại. Chúng tôi sẽ minh họa các khái niệm trọng yếu này bằng mã trong hai framework phổ biến nhất - [TensorFlow](http://Tensorflow.org) và [PyTorch](http://pytorch.org). -* **Kiến trúc Nơ-ron** để làm việc với hình ảnh và văn bản. Chúng tôi sẽ đề cập các mô hình gần đây nhưng có thể chưa hoàn toàn hiện đại nhất. -* Các phương pháp AI ít phổ biến hơn, chẳng hạn như **Thuật toán Di truyền** và **Hệ thống Đa tác nhân**. +* Các phương pháp tiếp cận khác nhau đối với Trí Tuệ Nhân Tạo, bao gồm phương pháp biểu tượng "cổ điển" với **Biểu diễn Kiến thức** và suy luận ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)). +* **Mạng Nơ-ron** và **Học Sâu**, là cốt lõi của AI hiện đại. Chúng tôi sẽ minh họa các khái niệm đằng sau các chủ đề quan trọng này bằng mã trong hai khung phổ biến nhất - [TensorFlow](http://Tensorflow.org) và [PyTorch](http://pytorch.org). +* **Kiến Trúc Nơ-ron** cho làm việc với hình ảnh và văn bản. Chúng tôi sẽ đề cập các mô hình mới đây nhưng có thể thiếu một chút về trạng thái nghệ thuật hiện tại. +* Các phương pháp AI ít phổ biến hơn, như **Thuật Toán Di Truyền** và **Hệ Thống Đa Tác Nhân**. Những gì chúng tôi sẽ không đề cập trong chương trình này: -> [Tìm tất cả nguồn tài nguyên bổ sung cho khóa học này trong bộ sưu tập Microsoft Learn của chúng tôi](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) +> [Tìm tất cả tài nguyên bổ sung cho khóa học này trong bộ sưu tập Microsoft Learn của chúng tôi](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -* Các trường hợp ứng dụng **AI trong Kinh doanh**. Bạn có thể tham khảo khóa học [Giới thiệu về AI cho người dùng kinh doanh](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) trên Microsoft Learn, hoặc [Trường Kinh doanh AI](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), phát triển hợp tác với [INSEAD](https://www.insead.edu/). -* **Máy học Cổ điển**, được mô tả rõ trong chương trình [Máy học cho Người Mới Bắt Đầu](http://github.com/Microsoft/ML-for-Beginners). -* Các ứng dụng AI thực tế xây dựng bằng **[Dịch vụ Nhận thức](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Để bắt đầu, chúng tôi khuyên bạn học các module trên Microsoft Learn về [thị giác máy tính](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [xử lý ngôn ngữ tự nhiên](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[AI Sinh tác với Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** và các lĩnh vực khác. -* Các **Khung Máy học trên Đám mây** cụ thể, như [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), hoặc [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Bạn có thể tham khảo các khóa học [Xây dựng và vận hành các giải pháp máy học với Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) và [Xây dựng và vận hành các giải pháp máy học với Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum). -* **Trí tuệ trò chuyện** và **Chat Bots**. Có một lộ trình học riêng dành cho [Tạo giải pháp AI trò chuyện](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), bạn cũng có thể tham khảo [bài viết blog này](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) để biết thêm chi tiết. -* **Toán học chuyên sâu** phía sau học sâu. Để nắm vững, chúng tôi khuyên đọc cuốn [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) của Ian Goodfellow, Yoshua Bengio và Aaron Courville, cũng có online tại [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). +* Các trường hợp kinh doanh sử dụng **AI trong Kinh doanh**. Hãy xem xét tham gia con đường học [Giới thiệu về AI cho người dùng doanh nghiệp](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) trên Microsoft Learn, hoặc [Trường Kinh doanh AI](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), phát triển hợp tác với [INSEAD](https://www.insead.edu/). +* **Học Máy Cổ Điển**, được mô tả rõ trong chương trình học [Học Máy cho Người Mới Bắt Đầu](http://github.com/Microsoft/ML-for-Beginners). +* Các ứng dụng AI thực tế xây dựng bằng **[Dịch vụ Nhận thức](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Để làm điều này, chúng tôi khuyến nghị bạn bắt đầu với các module Microsoft Learn cho [thị giác](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [xử lý ngôn ngữ tự nhiên](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[AI Sinh Tạo với Dịch vụ Azure OpenAI](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** và các module khác. +* Các **Khung Đám Mây** ML cụ thể, như [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), hoặc [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Xem xét sử dụng các con đường học [Xây dựng và vận hành giải pháp học máy với Azure ML](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) và [Xây dựng và vận hành giải pháp học máy với Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum). +* **AI Đàm Thoại** và **Chat Bot**. Có con đường học riêng [Tạo giải pháp AI đàm thoại](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), và bạn cũng có thể tham khảo [bài đăng blog này](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) để biết thêm chi tiết. +* **Toán Học Sâu** đằng sau học sâu. Để làm điều này, chúng tôi khuyến nghị [Học sâu](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) của Ian Goodfellow, Yoshua Bengio và Aaron Courville, cũng có sẵn trực tuyến tại [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/). -Để có một giới thiệu nhẹ nhàng về các chủ đề _AI trên Đám mây_, bạn có thể học lộ trình [Bắt đầu với trí tuệ nhân tạo trên Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum). +Để có giới thiệu nhẹ nhàng về các chủ đề _AI trên Đám Mây_, bạn có thể cân nhắc tham gia Đường dẫn Học tập [Bắt đầu với trí tuệ nhân tạo trên Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum). # Nội dung -| | Liên Kết Bài Học | PyTorch/Keras/TensorFlow | Phòng thí nghiệm | +| | Liên kết Bài học | PyTorch/Keras/TensorFlow | Phòng Lab | | :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | -| 0 | [Thiết lập Khóa Học](./lessons/0-course-setup/setup.md) | [Thiết lập Môi trường Phát triển của bạn](./lessons/0-course-setup/how-to-run.md) | | -| I | [**Giới Thiệu về AI**](./lessons/1-Intro/README.md) | | | +| 0 | [Thiết lập Khóa học](./lessons/0-course-setup/setup.md) | [Thiết lập Môi trường Phát triển Của Bạn](./lessons/0-course-setup/how-to-run.md) | | +| I | [**Giới thiệu về AI**](./lessons/1-Intro/README.md) | | | | 01 | [Giới thiệu và Lịch sử AI](./lessons/1-Intro/README.md) | - | - | | II | **AI Biểu Tượng** | -| 02 | [Biểu Diễn Kiến Thức và Hệ Thống Chuyên Gia](./lessons/2-Symbolic/README.md) | [Hệ Thống Chuyên Gia](./lessons/2-Symbolic/Animals.ipynb) / [Ôn tập Ontology](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Đồ thị Khái niệm](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | -| III | [**Giới Thiệu về Mạng Nơ-ron**](./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 | [Mạng Perceptron đa lớp và Tạo ra Framework riêng của chúng ta](./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 | [Giới thiệu về Frameworks (PyTorch/TensorFlow) và Overfitting](./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 | [**Thị giác máy tính**](./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)| [Khám phá Thị giác máy tính trên Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | -| 06 | [Giới thiệu về Thị giác máy tính. 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 | [Mạng nơ-ron tích chập](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Kiến trúc 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 | [Mạng đã được huấn luyện sẵn và Học chuyển đổi](./lessons/4-ComputerVision/08-TransferLearning/README.md) và [Các Mẹo Huấn luyện](./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) | +| 02 | [Biểu diễn Kiến thức và Hệ Thống Chuyên Gia](./lessons/2-Symbolic/README.md) | [Hệ Thống Chuyên Gia](./lessons/2-Symbolic/Animals.ipynb) / [Ontology](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Biểu đồ Khái niệm](./lessons/2-Symbolic/MSConceptGraph.ipynb) | | +| III | [**Giới thiệu về Mạng Nơ-ron**](./lessons/3-NeuralNetworks/README.md) ||| +| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Sổ tay](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Thực hành](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) | +| 04 | [Perceptron Đa Lớp và Tạo Khung Công tác của Riêng chúng ta](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Sổ tay](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Thực hành](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) | +| 05 | [Giới thiệu về Khung công tác (PyTorch/TensorFlow) và Quá khớp](./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) | [Thực hành](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) | +| IV | [**Thị giác Máy tính**](./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)| [Khám phá Thị giác Máy tính trên Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) | +| 06 | [Giới thiệu về Thị giác Máy tính. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Sổ tay](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Thực hành](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) | +| 07 | [Mạng Nơ-ron Tích chập](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Kiến trúc 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) | [Thực hành](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) | +| 08 | [Mạng đã huấn luyện sẵn và Học chuyển giao](./lessons/4-ComputerVision/08-TransferLearning/README.md) và [Mẹo huấn luyện](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Thực hành](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) | | 09 | [Autoencoders và 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 | [Mạng đối kháng sinh tạo & Chuyển đổi phong cách nghệ thuật](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | -| 11 | [Phát hiện vật thể](./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 | [Phân đoạn ngữ nghĩa. 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 | [**Xử lý ngôn ngữ tự nhiên**](./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) | [Khám phá Xử lý Ngôn ngữ Tự nhiên trên Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| -| 13 | [Biểu diễn văn bản. 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 | [Biểu diễn từ ngữ ngữ nghĩa. Word2Vec và 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 | [Mô hình ngôn ngữ. Huấn luyện biểu diễn của riêng bạn](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | -| 16 | [Mạng nơ-ron hồi quy](./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 | [Mạng nơ-ron hồi quy sinh tạo](./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) | +| 10 | [Mạng Đối Kháng Sinh Tạo & Chuyển giao Phong cách Nghệ thuật](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | | +| 11 | [Phát hiện Đối tượng](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Thực hành](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) | +| 12 | [Phân đoạn Ngữ nghĩa. 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 | [**Xử lý Ngôn ngữ Tự nhiên**](./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) | [Khám phá Xử lý Ngôn ngữ Tự nhiên trên Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)| +| 13 | [Biểu diễn Văn bản. 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 | [Nhúng từ ngữ ngữ nghĩa. Word2Vec và 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 | [Mô hình Ngôn ngữ. Huấn luyện nhúng riêng của bạn](./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) | [Thực hành](./lessons/5-NLP/15-LanguageModeling/lab/README.md) | +| 16 | [Mạng Nơ-ron Hồi tiếp](./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 | [Mạng Hồi tiếp Sinh tạo](./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) | [Thực hành](./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 | [Nhận dạng thực thể có tên](./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 | [Mô hình ngôn ngữ lớn, Lập trình Prompt và Các tác vụ 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 | **Các kỹ thuật AI khác** || | -| 21 | [Thuật toán di truyền](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | -| 22 | [Học tăng cường sâu](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) | -| 23 | [Hệ thống đa tác nhân](./lessons/6-Other/23-MultiagentSystems/README.md) | | | +| 19 | [Nhận dạng Thực thể có tên](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Thực hành](./lessons/5-NLP/19-NER/lab/README.md) | +| 20 | [Mô hình Ngôn ngữ Lớn, Lập trình Lời nhắc và Nhiệm vụ 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 | **Kỹ thuật AI Khác** || | +| 21 | [Thuật toán Di truyền](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Sổ tay](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | | +| 22 | [Học Tăng cường Sâu](./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) | [Thực hành](./lessons/6-Other/22-DeepRL/lab/README.md) | +| 23 | [Hệ thống Đa tác nhân](./lessons/6-Other/23-MultiagentSystems/README.md) | | | | VII | **Đạo đức AI** | | | -| 24 | [Đạo đức AI và AI có trách nhiệm](./lessons/7-Ethics/README.md) | [Microsoft Learn: Nguyên tắc AI có trách nhiệm](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | +| 24 | [Đạo đức AI và AI có Trách nhiệm](./lessons/7-Ethics/README.md) | [Microsoft Learn: Nguyên tắc AI có Trách nhiệm](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | | | IX | **Phần thêm** | | | -| 25 | [Mạng đa phương thức, CLIP và VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | +| 25 | [Mạng Đa phương thức, CLIP và VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Sổ tay](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | | ## Mỗi bài học bao gồm * Tài liệu đọc trước -* Các Jupyter Notebooks có thể chạy được, thường dành riêng cho framework (**PyTorch** hoặc **TensorFlow**). Notebook có thể chạy cũng chứa rất nhiều tài liệu lý thuyết, để hiểu chủ đề bạn cần đọc qua ít nhất một phiên bản của notebook (bằng PyTorch hoặc TensorFlow). -* **Phòng lab** cho một số chủ đề, giúp bạn có cơ hội thử áp dụng kiến thức đã học vào một bài toán cụ thể. -* Một số phần có liên kết đến các module [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) bao gồm các chủ đề có liên quan. +* Các Jupyter Notebooks có thể chạy được, thường đặc thù cho khung công tác (**PyTorch** hoặc **TensorFlow**). Sổ tay có thể chạy cũng chứa nhiều tài liệu lý thuyết, do đó để hiểu chủ đề bạn cần làm quen ít nhất một phiên bản của sổ tay (PyTorch hoặc TensorFlow). +* **Các phòng thí nghiệm** có sẵn cho một số chủ đề, giúp bạn có cơ hội thử áp dụng tài liệu đã học vào một vấn đề cụ thể. +* Một số phần chứa các liên kết đến các module [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) liên quan. ## Bắt đầu -### 🎯 Mới học AI? Bắt đầu tại đây! +### 🎯 Mới với AI? Bắt đầu Tại đây! -Nếu bạn hoàn toàn mới về AI và muốn các ví dụ thực hành nhanh, hãy xem [**Ví dụ Dành cho Người mới bắt đầu**](./examples/README.md)! Bao gồm: +Nếu bạn hoàn toàn mới với AI và muốn có những ví dụ thực hành nhanh, hãy xem [**Ví dụ dành cho Người mới bắt đầu**](./examples/README.md)! Bao gồm: - 🌟 **Hello AI World** - Chương trình AI đầu tiên của bạn (nhận dạng mẫu) -- 🧠 **Mạng Nơ-ron đơn giản** - Xây dựng mạng nơ-ron từ đầu -- 🖼️ **Phân loại hình ảnh** - Phân loại hình ảnh với các chú thích chi tiết -- 💬 **Phân Tích Cảm Xúc Văn Bản** - Phân tích văn bản tích cực/tiêu cực +- 🧠 **Mạng Nơ-ron Đơn giản** - Xây dựng một mạng nơ-ron từ đầu -Những ví dụ này được thiết kế để giúp bạn hiểu các khái niệm AI trước khi bắt đầu toàn bộ chương trình học. +- 🖼️ **Phân loại Hình ảnh** - Phân loại hình ảnh với các chú thích chi tiết +- 💬 **Phân tích Cảm xúc Văn bản** - Phân tích văn bản tích cực/tiêu cực -### 📚 Cài Đặt Chương Trình Học Toàn Bộ +Các ví dụ này được thiết kế để giúp bạn hiểu các khái niệm AI trước khi đi sâu vào toàn bộ chương trình học. -- Chúng tôi đã tạo một [bài học cài đặt](./lessons/0-course-setup/setup.md) để giúp bạn thiết lập môi trường phát triển. -- Dành cho giáo viên, chúng tôi cũng đã tạo một [bài học cài đặt chương trình học](./lessons/0-course-setup/for-teachers.md) cho bạn! -- Cách [Chạy mã trong VSCode hoặc Codespace](./lessons/0-course-setup/how-to-run.md) +### 📚 Thiết lập Toàn bộ Chương trình + +- Chúng tôi đã tạo một [bài học thiết lập](./lessons/0-course-setup/setup.md) để giúp bạn thiết lập môi trường phát triển của mình. +- Đối với các Nhà giáo dục, chúng tôi cũng đã tạo một [bài học thiết lập chương trình học](./lessons/0-course-setup/for-teachers.md) dành cho bạn! +- Cách [Chạy mã trên VSCode hoặc Codespace](./lessons/0-course-setup/how-to-run.md) Hãy làm theo các bước sau: -Fork kho lưu trữ: Nhấn nút "Fork" ở góc trên bên phải của trang này. +Fork Repository: Nhấn nút "Fork" ở góc trên bên phải của trang này. -Clone kho lưu trữ: `git clone https://github.com/microsoft/AI-For-Beginners.git` +Clone Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git` Đừng quên đánh dấu (🌟) repo này để dễ tìm lại sau. -## Gặp gỡ các học viên khác +## Gặp gỡ các Học viên khác -Tham gia [máy chủ Discord AI chính thức](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) của chúng tôi để gặp gỡ và kết nối với những người học khác đang tham gia khóa học này và nhận hỗ trợ. +Tham gia [máy chủ Discord AI chính thức của chúng tôi](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) để gặp gỡ và kết nối với các học viên khác đang tham gia khóa học này và nhận sự hỗ trợ. -Nếu bạn có phản hồi sản phẩm hoặc câu hỏi trong quá trình xây dựng, hãy truy cập [Diễn đàn Nhà phát triển Azure AI Foundry](https://aka.ms/foundry/forum) +Nếu bạn có phản hồi sản phẩm hoặc câu hỏi trong quá trình xây dựng, hãy truy cập [Diễn đàn Nhà phát triển Azure AI Foundry của chúng tôi](https://aka.ms/foundry/forum) ## Bài Kiểm Tra -> **Lưu ý về bài kiểm tra**: Tất cả bài kiểm tra nằm trong thư mục Quiz-app tại etc\quiz-app, hoặc [Trực tuyến tại đây](https://ff-quizzes.netlify.app/) Chúng được liên kết trong các bài học và ứng dụng bài kiểm tra có thể chạy cục bộ hoặc triển khai lên Azure; làm theo hướng dẫn trong thư mục `quiz-app`. Chúng đang dần được bản địa hóa. +> **Lưu ý về các bài kiểm tra**: Tất cả các bài kiểm tra được chứa trong thư mục Quiz-app ở etc\quiz-app, hoặc [Trực tuyến Tại đây](https://ff-quizzes.netlify.app/). Chúng được liên kết trong các bài học, ứng dụng kiểm tra có thể chạy cục bộ hoặc triển khai lên Azure; làm theo hướng dẫn trong thư mục `quiz-app`. Chúng đang được dần dần địa phương hóa. ## Cần Giúp Đỡ -Bạn có gợi ý hoặc phát hiện lỗi chính tả hay lỗi mã? Hãy tạo issue hoặc pull request. +Bạn có đề xuất hoặc phát hiện lỗi chính tả hay lỗi mã? Hãy tạo vấn đề (issue) hoặc tạo pull request. ## Lời Cảm Ơn Đặc Biệt * **✍️ Tác giả chính:** [Dmitry Soshnikov](http://soshnikov.com), Tiến sĩ * **🔥 Biên tập viên:** [Jen Looper](https://twitter.com/jenlooper), Tiến sĩ -* **🎨 Minh họa sketchnote:** [Tomomi Imura](https://twitter.com/girlie_mac) +* **🎨 Minh họa Sketchnote:** [Tomomi Imura](https://twitter.com/girlie_mac) * **✅ Người tạo bài kiểm tra:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/) -* **🙏 Cộng tác viên chủ chốt:** [Evgenii Pishchik](https://github.com/Pe4enIks) +* **🙏 Những người đóng góp chính:** [Evgenii Pishchik](https://github.com/Pe4enIks) -## Các Chương Trình Học Khác +## Các Chương trình học khác -Nhóm của chúng tôi còn tạo ra các chương trình học khác! Hãy xem: +Nhóm của chúng tôi còn sản xuất các chương trình học khác! Khám phá: ### LangChain -[![LangChain4j cho Người Mới](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) -[![LangChain.js cho Người Mới](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) +[![LangChain4j dành cho Người mới bắt đầu](https://img.shields.io/badge/LangChain4j%20for%20Beginners-22C55E?style=for-the-badge&&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchain4j-for-beginners) +[![LangChain.js dành cho Người mới bắt đầu](https://img.shields.io/badge/LangChain.js%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=0553D6)](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin) --- ### Azure / Edge / MCP / Agents -[![AZD cho Người Mới](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Edge AI cho Người Mới](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![MCP cho Người Mới](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) -[![AI Agents cho Người Mới](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AZD dành cho Người mới bắt đầu](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst) +[![Edge AI dành cho Người mới bắt đầu](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![MCP dành cho Người mới bắt đầu](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Agents dành cho Người mới bắt đầu](https://img.shields.io/badge/AI%20Agents%20for%20Beginners-00C49A?style=for-the-badge&labelColor=E5E7EB&color=00C49A)](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) --- - -### Chuỗi AI Sinh Tạo -[![Generative AI cho Người Mới](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) -[![Generative AI (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) -[![Generative AI (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) -[![Generative AI (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) + +### Chuỗi AI Tạo Sinh +[![AI Tạo Sinh dành cho Người mới bắt đầu](https://img.shields.io/badge/Generative%20AI%20for%20Beginners-8B5CF6?style=for-the-badge&labelColor=E5E7EB&color=8B5CF6)](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) +[![AI Tạo Sinh (.NET)](https://img.shields.io/badge/Generative%20AI%20(.NET)-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) +[![AI Tạo Sinh (Java)](https://img.shields.io/badge/Generative%20AI%20(Java)-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst) +[![AI Tạo Sinh (JavaScript)](https://img.shields.io/badge/Generative%20AI%20(JavaScript)-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) --- - -### Học Cơ Bản -[![ML cho Người Mới](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) -[![Khoa Học Dữ Liệu cho Người Mới](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) -[![AI cho Người Mới](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) -[![An ninh mạng cho Người Mới](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) -[![Phát Triển Web cho Người Mới](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) -[![IoT cho Người Mới](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) -[![Phát Triển XR cho Người Mới](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) + +### Học tập Cốt lõi +[![ML dành cho Người mới bắt đầu](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) +[![Khoa học Dữ liệu dành cho Người mới bắt đầu](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) +[![AI dành cho Người mới bắt đầu](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) +[![An ninh mạng dành cho Người mới bắt đầu](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung) +[![Phát triển Web dành cho Người mới bắt đầu](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) +[![IoT dành cho Người mới bắt đầu](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) +[![Phát triển XR dành cho Người mới bắt đầu](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) --- - + ### Chuỗi Copilot -[![Copilot cho Lập Trình AI Ghép Đôi](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) +[![Copilot cho Lập trình Đôi AI](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) [![Copilot cho C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) -[![Cuộc Phiêu Lưu Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) +[![Cuộc phiêu lưu với Copilot](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) -## Nhận Trợ Giúp +## Nhận Hỗ Trợ -Nếu bạn gặp khó khăn hoặc có câu hỏi về phát triển ứng dụng AI, hãy tham gia cùng những người học và các nhà phát triển giàu kinh nghiệm trong các cuộc thảo luận về MCP. Đây là một cộng đồng hỗ trợ nhiệt tình, nơi mọi câu hỏi đều được hoan nghênh và kiến thức được chia sẻ tự do. +Nếu bạn gặp khó khăn hoặc có bất kỳ câu hỏi nào về việc xây dựng các ứng dụng AI. Hãy tham gia cùng các học viên và nhà phát triển có kinh nghiệm trong các cuộc thảo luận về MCP. Đây là một cộng đồng hỗ trợ, nơi các câu hỏi được chào đón và kiến thức được chia sẻ tự do. [![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG) -Nếu bạn có phản hồi sản phẩm hoặc phát hiện lỗi trong quá trình xây dựng, hãy truy cập: +Nếu bạn có phản hồi sản phẩm hoặc lỗi khi xây dựng, hãy truy cập: [![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum) --- -**Tuyên bố miễn trừ trách nhiệm**: -Tài liệu này đã được dịch bằng dịch vụ dịch thuật AI [Co-op Translator](https://github.com/Azure/co-op-translator). Mặc dù chúng tôi nỗ lực đảm bảo độ chính xác, xin lưu ý rằng bản dịch tự động có thể chứa lỗi hoặc sai sót. Tài liệu gốc bằng ngôn ngữ gốc của nó nên được coi là nguồn tham khảo chính xác nhất. Đối với thông tin quan trọng, khuyến nghị sử dụng dịch vụ dịch thuật chuyên nghiệp bởi con người. Chúng tôi không chịu trách nhiệm về bất kỳ sự hiểu nhầm hoặc giải thích sai nào phát sinh từ việc sử dụng bản dịch này. +**Tuyên bố từ chối trách nhiệm**: +Tài liệu này đã được dịch bằng dịch vụ dịch thuật AI [Co-op Translator](https://github.com/Azure/co-op-translator). Mặc dù chúng tôi cố gắng đảm bảo độ chính xác, xin lưu ý rằng các bản dịch tự động có thể chứa lỗi hoặc không chính xác. Tài liệu gốc bằng ngôn ngữ nguyên bản nên được coi là nguồn thông tin chính thức. Đối với thông tin quan trọng, nên sử dụng dịch vụ dịch thuật chuyên nghiệp bởi con người. Chúng tôi không chịu trách nhiệm về bất kỳ sự hiểu lầm hoặc giải thích sai nào phát sinh từ việc sử dụng bản dịch này. \ No newline at end of file diff --git a/translations/vi/SECURITY.md b/translations/vi/SECURITY.md index f77acd57..9c9319f4 100644 --- a/translations/vi/SECURITY.md +++ b/translations/vi/SECURITY.md @@ -1,12 +1,3 @@ - ## Bảo mật Microsoft coi trọng vấn đề bảo mật của các sản phẩm và dịch vụ phần mềm của mình, bao gồm tất cả các kho mã nguồn được quản lý thông qua các tổ chức GitHub của chúng tôi, bao gồm [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), và [các tổ chức GitHub của chúng tôi](https://opensource.microsoft.com/). diff --git a/translations/vi/etc/CODE_OF_CONDUCT.md b/translations/vi/etc/CODE_OF_CONDUCT.md index e39840c9..b4195463 100644 --- a/translations/vi/etc/CODE_OF_CONDUCT.md +++ b/translations/vi/etc/CODE_OF_CONDUCT.md @@ -1,12 +1,3 @@ - # Quy tắc ứng xử mã nguồn mở của Microsoft Dự án này đã áp dụng [Quy tắc ứng xử mã nguồn mở của Microsoft](https://opensource.microsoft.com/codeofconduct/). diff --git a/translations/vi/etc/CONTRIBUTING.md b/translations/vi/etc/CONTRIBUTING.md index c5885f9d..dcca1625 100644 --- a/translations/vi/etc/CONTRIBUTING.md +++ b/translations/vi/etc/CONTRIBUTING.md @@ -1,12 +1,3 @@ - # Đóng góp Dự án này hoan nghênh các đóng góp và gợi ý. Hầu hết các đóng góp yêu cầu bạn đồng ý với Thỏa thuận Cấp phép Người đóng góp (CLA), xác nhận rằng bạn có quyền và thực sự cấp cho chúng tôi quyền sử dụng đóng góp của bạn. Để biết thêm chi tiết, hãy truy cập https://cla.microsoft.com. diff --git a/translations/vi/etc/Mindmap.md b/translations/vi/etc/Mindmap.md index a92245ba..7133a613 100644 --- a/translations/vi/etc/Mindmap.md +++ b/translations/vi/etc/Mindmap.md @@ -1,12 +1,3 @@ - # AI ## [Giới thiệu về AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md) diff --git a/translations/vi/etc/SUPPORT.md b/translations/vi/etc/SUPPORT.md index 56b59d42..8129e068 100644 --- a/translations/vi/etc/SUPPORT.md +++ b/translations/vi/etc/SUPPORT.md @@ -1,12 +1,3 @@ - # Hỗ trợ ## Cách báo cáo vấn đề và nhận trợ giúp diff --git a/translations/vi/etc/TRANSLATIONS.md b/translations/vi/etc/TRANSLATIONS.md index 743171dc..61daef15 100644 --- a/translations/vi/etc/TRANSLATIONS.md +++ b/translations/vi/etc/TRANSLATIONS.md @@ -1,12 +1,3 @@ - # Đóng góp bằng cách dịch các bài học Chúng tôi hoan nghênh các bản dịch cho các bài học trong chương trình giảng dạy này! diff --git a/translations/vi/etc/quiz-app/README.md b/translations/vi/etc/quiz-app/README.md index 164cf9a5..315a60f5 100644 --- a/translations/vi/etc/quiz-app/README.md +++ b/translations/vi/etc/quiz-app/README.md @@ -1,12 +1,3 @@ - # Câu hỏi trắc nghiệm Các câu hỏi trắc nghiệm này là bài kiểm tra trước và sau bài giảng trong chương trình học AI tại https://aka.ms/ai-beginners diff --git a/translations/vi/examples/README.md b/translations/vi/examples/README.md index 16f33f89..61e5f2cd 100644 --- a/translations/vi/examples/README.md +++ b/translations/vi/examples/README.md @@ -1,12 +1,3 @@ - # Các Ví dụ AI Dễ Hiểu Chào mừng bạn! Thư mục này chứa các ví dụ đơn giản, độc lập để giúp bạn bắt đầu với AI và học máy. Mỗi ví dụ được thiết kế thân thiện với người mới bắt đầu, kèm theo các bình luận chi tiết và hướng dẫn từng bước. diff --git a/translations/vi/lessons/0-course-setup/for-teachers.md b/translations/vi/lessons/0-course-setup/for-teachers.md index ec90d374..9f283f3f 100644 --- a/translations/vi/lessons/0-course-setup/for-teachers.md +++ b/translations/vi/lessons/0-course-setup/for-teachers.md @@ -1,12 +1,3 @@ - # Dành cho Giáo viên Bạn có muốn sử dụng chương trình học này trong lớp học của mình không? Hãy thoải mái sử dụng nhé! diff --git a/translations/vi/lessons/0-course-setup/how-to-run.md b/translations/vi/lessons/0-course-setup/how-to-run.md index ad237d24..881bdbf6 100644 --- a/translations/vi/lessons/0-course-setup/how-to-run.md +++ b/translations/vi/lessons/0-course-setup/how-to-run.md @@ -1,12 +1,3 @@ - # Cách Chạy Mã Lệnh Chương trình học này chứa nhiều ví dụ và bài thực hành có thể chạy được mà bạn sẽ muốn thử. Để làm điều này, bạn cần khả năng thực thi mã Python trong Jupyter Notebooks được cung cấp như một phần của chương trình học này. Bạn có một số lựa chọn để chạy mã: diff --git a/translations/vi/lessons/0-course-setup/setup.md b/translations/vi/lessons/0-course-setup/setup.md index cf4125f8..542f1dcf 100644 --- a/translations/vi/lessons/0-course-setup/setup.md +++ b/translations/vi/lessons/0-course-setup/setup.md @@ -1,12 +1,3 @@ - # Bắt đầu với chương trình học này ## Bạn là sinh viên? diff --git a/translations/vi/lessons/1-Intro/README.md b/translations/vi/lessons/1-Intro/README.md index 10ecea15..b645b678 100644 --- a/translations/vi/lessons/1-Intro/README.md +++ b/translations/vi/lessons/1-Intro/README.md @@ -1,12 +1,3 @@ - # Giới thiệu về AI ![Tóm tắt nội dung Giới thiệu về AI trong một hình vẽ](../../../../translated_images/vi/ai-intro.bf28d1ac4235881c.webp) diff --git a/translations/vi/lessons/1-Intro/assignment.md b/translations/vi/lessons/1-Intro/assignment.md index 6ecd4b20..d973954f 100644 --- a/translations/vi/lessons/1-Intro/assignment.md +++ b/translations/vi/lessons/1-Intro/assignment.md @@ -1,12 +1,3 @@ - # Game Jam Trò chơi là một lĩnh vực đã chịu ảnh hưởng lớn từ sự phát triển của AI và ML. Trong bài tập này, hãy viết một bài luận ngắn về một trò chơi mà bạn yêu thích, đã bị ảnh hưởng bởi sự tiến hóa của AI. Đó nên là một trò chơi đủ cũ để đã trải qua ảnh hưởng từ nhiều loại hệ thống xử lý máy tính khác nhau. Một ví dụ hay là Cờ vua hoặc Cờ vây, nhưng cũng có thể xem xét các trò chơi điện tử như Pong hoặc Pac-Man. Hãy viết một bài luận thảo luận về quá khứ, hiện tại và tương lai AI của trò chơi đó. diff --git a/translations/vi/lessons/2-Symbolic/README.md b/translations/vi/lessons/2-Symbolic/README.md index 3b4bab63..64eacf2e 100644 --- a/translations/vi/lessons/2-Symbolic/README.md +++ b/translations/vi/lessons/2-Symbolic/README.md @@ -1,15 +1,6 @@ - # Đại diện tri thức và hệ chuyên gia -![Tóm tắt nội dung AI ký hiệu](../../../../../../translated_images/vi/ai-symbolic.715a30cb610411a6.webp) +![Tóm tắt nội dung AI ký hiệu](../../../../translated_images/vi/ai-symbolic.715a30cb610411a6.webp) > Sketchnote bởi [Tomomi Imura](https://twitter.com/girlie_mac) @@ -41,7 +32,7 @@ Thông thường, chúng ta không định nghĩa tri thức một cách chặt Do đó, vấn đề **đại diện tri thức** là tìm cách hiệu quả để biểu diễn tri thức bên trong máy tính dưới dạng dữ liệu, nhằm làm cho tri thức có thể sử dụng tự động. Điều này có thể xem như một phổ: -![Phổ đại diện tri thức](../../../../../../translated_images/vi/knowledge-spectrum.b60df631852c0217.webp) +![Phổ đại diện tri thức](../../../../translated_images/vi/knowledge-spectrum.b60df631852c0217.webp) > Hình bởi [Dmitry Soshnikov](http://soshnikov.com) @@ -94,7 +85,7 @@ Cú pháp khối | Thụt lề | | | Một trong những thành công đầu tiên của AI ký hiệu là các **hệ chuyên gia** - các hệ thống máy tính được thiết kế để đóng vai trò chuyên gia trong một lĩnh vực vấn đề giới hạn. Chúng dựa trên **cơ sở tri thức** trích xuất từ một hoặc nhiều chuyên gia con người, và có chứa **bộ suy luận** thực hiện suy luận dựa trên đó. -![Cấu trúc hệ thần kinh con người](../../../../../../translated_images/vi/arch-human.5d4d35f1bba3ab1c.webp) | ![Hệ thống dựa trên tri thức](../../../../../../translated_images/vi/arch-kbs.3ec5c150b09fa8da.webp) +![Cấu trúc hệ thần kinh con người](../../../../translated_images/vi/arch-human.5d4d35f1bba3ab1c.webp) | ![Hệ thống dựa trên tri thức](../../../../translated_images/vi/arch-kbs.3ec5c150b09fa8da.webp) --------------------------------------------------------|---------------------------------------------------- Cấu trúc đơn giản của hệ thần kinh con người | Kiến trúc hệ thống dựa trên tri thức @@ -106,7 +97,7 @@ Hệ chuyên gia được xây dựng như hệ thống suy luận của con ng Lấy ví dụ hệ chuyên gia xác định một con vật dựa trên đặc điểm thể chất: -![Cây AND-OR](../../../../../../translated_images/vi/AND-OR-Tree.5592d2c70187f283.webp) +![Cây AND-OR](../../../../translated_images/vi/AND-OR-Tree.5592d2c70187f283.webp) > Hình bởi [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/vi/lessons/2-Symbolic/assignment.md b/translations/vi/lessons/2-Symbolic/assignment.md index 523e1094..41cc63aa 100644 --- a/translations/vi/lessons/2-Symbolic/assignment.md +++ b/translations/vi/lessons/2-Symbolic/assignment.md @@ -1,12 +1,3 @@ - # Xây dựng một Ontology Xây dựng một cơ sở tri thức là việc phân loại một mô hình đại diện cho các sự thật về một chủ đề. Hãy chọn một chủ đề - như một người, một địa điểm, hoặc một vật - và sau đó xây dựng một mô hình về chủ đề đó. Sử dụng một số kỹ thuật và chiến lược xây dựng mô hình được mô tả trong bài học này. Một ví dụ có thể là tạo một ontology về phòng khách với đồ nội thất, đèn, v.v. Phòng khách khác với nhà bếp như thế nào? Phòng tắm thì sao? Làm thế nào để bạn biết đó là phòng khách chứ không phải phòng ăn? Sử dụng [Protégé](https://protege.stanford.edu/) để xây dựng ontology của bạn. diff --git a/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/README.md index bae4fa20..6fc39478 100644 --- a/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/README.md @@ -1,12 +1,3 @@ - # Giới thiệu về Mạng Nơ-ron: Perceptron ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/5) @@ -15,7 +6,7 @@ Một trong những nỗ lực đầu tiên để triển khai một thứ gì | | | |--------------|-----------| -|Frank Rosenblatt | The Mark 1 Perceptron| +|Frank Rosenblatt | The Mark 1 Perceptron| > Hình ảnh [từ Wikipedia](https://en.wikipedia.org/wiki/Perceptron) @@ -34,7 +25,7 @@ y(x) = f(wTx) trong đó f là hàm kích hoạt dạng bước. - + ## Huấn luyện Perceptron diff --git a/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md index 097919ba..dd79bfe9 100644 --- a/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md @@ -1,12 +1,3 @@ - # Phân Loại Đa Lớp với Perceptron Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/README.md index 1c5d2495..a36e3531 100644 --- a/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/README.md @@ -1,12 +1,3 @@ - # Giới thiệu về Mạng Neural. Perceptron Đa Tầng Trong phần trước, bạn đã tìm hiểu về mô hình mạng neural đơn giản nhất - perceptron một tầng, một mô hình phân loại hai lớp tuyến tính. @@ -65,7 +56,7 @@ Thuật toán gradient descent vẫn giữ nguyên, nhưng việc tính toán gr Lưu ý rằng phần bên trái nhất của tất cả các biểu thức này là giống nhau, và do đó chúng ta có thể tính toán hiệu quả các đạo hàm bắt đầu từ hàm mất mát và đi "ngược lại" qua đồ thị tính toán. Vì vậy, phương pháp huấn luyện perceptron đa tầng được gọi là **backpropagation**, hay 'backprop'. -compute graph +compute graph > TODO: trích dẫn hình ảnh diff --git a/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md index d33142ae..08807cbb 100644 --- a/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md @@ -1,12 +1,3 @@ - # Phân loại MNIST với Framework của chúng ta Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/README.md index 4ee7ab9f..59cb772b 100644 --- a/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/README.md @@ -1,12 +1,3 @@ - # Các Framework Mạng Neural Như chúng ta đã học, để có thể huấn luyện mạng neural một cách hiệu quả, chúng ta cần làm hai việc: diff --git a/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md index d521eb19..d7707e33 100644 --- a/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md @@ -1,12 +1,3 @@ - # Phân loại với PyTorch/TensorFlow Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/3-NeuralNetworks/README.md b/translations/vi/lessons/3-NeuralNetworks/README.md index a7f0e609..75b7eea9 100644 --- a/translations/vi/lessons/3-NeuralNetworks/README.md +++ b/translations/vi/lessons/3-NeuralNetworks/README.md @@ -1,12 +1,3 @@ - # Giới thiệu về Mạng Nơ-ron ![Tóm tắt nội dung Giới thiệu Mạng Nơ-ron trong một hình vẽ](../../../../translated_images/vi/ai-neuralnetworks.1c687ae40bc86e83.webp) diff --git a/translations/vi/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/vi/lessons/4-ComputerVision/06-IntroCV/README.md index ae9491e9..c3829984 100644 --- a/translations/vi/lessons/4-ComputerVision/06-IntroCV/README.md +++ b/translations/vi/lessons/4-ComputerVision/06-IntroCV/README.md @@ -1,12 +1,3 @@ - # Giới thiệu về Thị giác Máy tính [Thị giác Máy tính](https://wikipedia.org/wiki/Computer_vision) là một lĩnh vực nhằm giúp máy tính đạt được khả năng hiểu biết ở mức cao về hình ảnh kỹ thuật số. Đây là một định nghĩa khá rộng, bởi vì *hiểu biết* có thể mang nhiều ý nghĩa khác nhau, bao gồm việc tìm một đối tượng trong hình ảnh (**phát hiện đối tượng**), hiểu điều gì đang xảy ra (**phát hiện sự kiện**), mô tả hình ảnh bằng văn bản, hoặc tái tạo một cảnh trong không gian 3D. Ngoài ra còn có các nhiệm vụ đặc biệt liên quan đến hình ảnh con người: ước tính tuổi và cảm xúc, phát hiện và nhận diện khuôn mặt, và ước tính tư thế 3D, chỉ là một vài ví dụ. @@ -115,7 +106,7 @@ Xem [video này](https://docs.microsoft.com/shows/ai-show/ai-show--2021-opencv-a Trong bài thực hành này, bạn sẽ quay một video với các cử chỉ đơn giản, và mục tiêu của bạn là trích xuất các chuyển động lên/xuống/trái/phải bằng dòng quang học. -Khung hình chuyển động lòng bàn tay +Khung hình chuyển động lòng bàn tay --- diff --git a/translations/vi/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/vi/lessons/4-ComputerVision/06-IntroCV/lab/README.md index 5916cdb9..559b71a8 100644 --- a/translations/vi/lessons/4-ComputerVision/06-IntroCV/lab/README.md +++ b/translations/vi/lessons/4-ComputerVision/06-IntroCV/lab/README.md @@ -1,12 +1,3 @@ - # Phát Hiện Chuyển Động Sử Dụng Optical Flow Bài tập từ [Chương trình Học AI cho Người Mới Bắt Đầu](https://aka.ms/ai-beginners). diff --git a/translations/vi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/vi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md index 54ad820e..696d4198 100644 --- a/translations/vi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md +++ b/translations/vi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md @@ -1,12 +1,3 @@ - # Các Kiến Trúc CNN Nổi Tiếng ### VGG-16 @@ -25,7 +16,7 @@ Như bạn có thể thấy, VGG tuân theo kiến trúc hình kim tự tháp tr ResNet là một họ các mô hình được đề xuất bởi Microsoft Research vào năm 2015. Ý tưởng chính của ResNet là sử dụng **khối dư thừa**: - + > Hình ảnh từ [bài báo này](https://arxiv.org/pdf/1512.03385.pdf) @@ -37,7 +28,7 @@ Bạn cũng có thể nghĩ rằng mạng này có khả năng điều chỉnh Kiến trúc Google Inception đưa ý tưởng này tiến xa hơn, và xây dựng mỗi lớp mạng như một sự kết hợp của nhiều đường dẫn khác nhau: - + > Hình ảnh từ [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) diff --git a/translations/vi/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/vi/lessons/4-ComputerVision/07-ConvNets/README.md index c708605b..14c78682 100644 --- a/translations/vi/lessons/4-ComputerVision/07-ConvNets/README.md +++ b/translations/vi/lessons/4-ComputerVision/07-ConvNets/README.md @@ -1,12 +1,3 @@ - # Mạng Nơ-ron Tích Chập Chúng ta đã thấy trước đây rằng mạng nơ-ron rất tốt trong việc xử lý hình ảnh, và thậm chí một perceptron một lớp cũng có thể nhận diện chữ số viết tay từ tập dữ liệu MNIST với độ chính xác khá cao. Tuy nhiên, tập dữ liệu MNIST rất đặc biệt, vì tất cả các chữ số đều được căn giữa trong hình ảnh, điều này làm cho nhiệm vụ trở nên đơn giản hơn. @@ -24,7 +15,7 @@ Trong thực tế, chúng ta muốn có khả năng nhận diện các đối t Ví dụ, nếu chúng ta áp dụng các bộ lọc cạnh dọc và cạnh ngang 3x3 lên các chữ số MNIST, chúng ta có thể làm nổi bật (ví dụ: giá trị cao) những nơi có các cạnh dọc và ngang trong hình ảnh gốc. Do đó, hai bộ lọc này có thể được sử dụng để "tìm kiếm" các cạnh. Tương tự, chúng ta có thể thiết kế các bộ lọc khác để tìm kiếm các mẫu cấp thấp khác: - + > Hình ảnh của [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html) diff --git a/translations/vi/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/vi/lessons/4-ComputerVision/07-ConvNets/lab/README.md index 175a5204..f5e77429 100644 --- a/translations/vi/lessons/4-ComputerVision/07-ConvNets/lab/README.md +++ b/translations/vi/lessons/4-ComputerVision/07-ConvNets/lab/README.md @@ -1,12 +1,3 @@ - # Phân Loại Khuôn Mặt Thú Cưng Bài tập thực hành từ [Chương trình AI cho Người Mới Bắt Đầu](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/README.md index 2d59a6a2..3da99bb9 100644 --- a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/README.md +++ b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/README.md @@ -1,12 +1,3 @@ - # Mạng Được Huấn Luyện Sẵn và Học Chuyển Giao Huấn luyện CNN có thể mất rất nhiều thời gian và yêu cầu một lượng lớn dữ liệu. Tuy nhiên, phần lớn thời gian được dành để học các bộ lọc cấp thấp tốt nhất mà mạng có thể sử dụng để trích xuất các mẫu từ hình ảnh. Một câu hỏi tự nhiên được đặt ra - liệu chúng ta có thể sử dụng một mạng nơ-ron đã được huấn luyện trên một tập dữ liệu và điều chỉnh nó để phân loại các hình ảnh khác mà không cần một quá trình huấn luyện đầy đủ? diff --git a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md index 9757f986..95240b4e 100644 --- a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md +++ b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md @@ -1,12 +1,3 @@ - # Các Mẹo Huấn Luyện Deep Learning Khi mạng nơ-ron trở nên sâu hơn, quá trình huấn luyện chúng ngày càng trở nên thách thức hơn. Một vấn đề lớn là [gradient biến mất](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) hoặc [gradient bùng nổ](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Bài viết này](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) cung cấp một giới thiệu tốt về các vấn đề này. diff --git a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md index 89b0aeaa..0e9e3e77 100644 --- a/translations/vi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md +++ b/translations/vi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md @@ -1,12 +1,3 @@ - # Phân loại thú cưng Oxford bằng Transfer Learning Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/vi/lessons/4-ComputerVision/09-Autoencoders/README.md index 884c8c3f..e145a85a 100644 --- a/translations/vi/lessons/4-ComputerVision/09-Autoencoders/README.md +++ b/translations/vi/lessons/4-ComputerVision/09-Autoencoders/README.md @@ -1,12 +1,3 @@ - # Autoencoders Khi huấn luyện CNN, một trong những vấn đề là chúng ta cần rất nhiều dữ liệu được gắn nhãn. Trong trường hợp phân loại hình ảnh, chúng ta cần phân chia hình ảnh thành các lớp khác nhau, điều này đòi hỏi sự nỗ lực thủ công. @@ -46,7 +37,7 @@ Tóm lại: * Chúng ta lấy mẫu một vector `sample` từ phân phối N(zmean,exp(zlog\_sigma)) * Bộ giải mã cố gắng giải mã hình ảnh gốc bằng cách sử dụng `sample` làm vector đầu vào - + > Hình ảnh từ [bài viết blog này](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) của Isaak Dykeman @@ -57,13 +48,13 @@ Autoencoders biến thể sử dụng một hàm mất mát phức tạp bao g Một lợi thế quan trọng của VAEs là chúng cho phép chúng ta tạo ra hình ảnh mới một cách tương đối dễ dàng, vì chúng ta biết phân phối nào để lấy mẫu các vector tiềm ẩn. Ví dụ, nếu chúng ta huấn luyện VAE với vector tiềm ẩn 2D trên MNIST, chúng ta có thể thay đổi các thành phần của vector tiềm ẩn để tạo ra các chữ số khác nhau: -vaemnist +vaemnist > Hình ảnh bởi [Dmitry Soshnikov](http://soshnikov.com) Quan sát cách các hình ảnh hòa trộn vào nhau, khi chúng ta bắt đầu lấy các vector tiềm ẩn từ các phần khác nhau của không gian tham số tiềm ẩn. Chúng ta cũng có thể trực quan hóa không gian này trong 2D: -vaemnist cluster +vaemnist cluster > Hình ảnh bởi [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/vi/lessons/4-ComputerVision/10-GANs/README.md b/translations/vi/lessons/4-ComputerVision/10-GANs/README.md index 784bb278..a43d7375 100644 --- a/translations/vi/lessons/4-ComputerVision/10-GANs/README.md +++ b/translations/vi/lessons/4-ComputerVision/10-GANs/README.md @@ -1,12 +1,3 @@ - # Mạng Generative Adversarial (GAN) Trong phần trước, chúng ta đã tìm hiểu về **mô hình sinh**: các mô hình có thể tạo ra hình ảnh mới tương tự như những hình ảnh trong tập dữ liệu huấn luyện. VAE là một ví dụ điển hình của mô hình sinh. @@ -17,7 +8,7 @@ Tuy nhiên, nếu chúng ta cố gắng tạo ra thứ gì đó thực sự ý n Ý tưởng chính của GAN là có hai mạng nơ-ron được huấn luyện đối kháng lẫn nhau: - + > Hình ảnh bởi [Dmitry Soshnikov](http://soshnikov.com) @@ -41,7 +32,7 @@ Generator hơi phức tạp hơn một chút. Bạn có thể coi nó như là m > ✅ Vì lớp tích chập được triển khai như một bộ lọc tuyến tính quét qua hình ảnh, deconvolution về cơ bản tương tự như tích chập và có thể được triển khai bằng cùng logic lớp. - + > Hình ảnh bởi [Dmitry Soshnikov](http://soshnikov.com) diff --git a/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/README.md index a841aecc..3a4955b3 100644 --- a/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/README.md +++ b/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/README.md @@ -1,12 +1,3 @@ - # Phát Hiện Đối Tượng Các mô hình phân loại hình ảnh mà chúng ta đã làm việc trước đây nhận một hình ảnh và đưa ra kết quả phân loại, chẳng hạn như lớp 'số' trong bài toán MNIST. Tuy nhiên, trong nhiều trường hợp, chúng ta không chỉ muốn biết rằng một bức ảnh có chứa các đối tượng - mà còn muốn xác định vị trí chính xác của chúng. Đây chính là mục đích của **phát hiện đối tượng**. diff --git a/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md index 3629dd1c..1082f6dd 100644 --- a/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md +++ b/translations/vi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md @@ -1,12 +1,3 @@ - # Phát hiện đầu người sử dụng Hollywood Heads Dataset Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/vi/lessons/4-ComputerVision/12-Segmentation/README.md index 172fe762..9ab2b8c3 100644 --- a/translations/vi/lessons/4-ComputerVision/12-Segmentation/README.md +++ b/translations/vi/lessons/4-ComputerVision/12-Segmentation/README.md @@ -1,12 +1,3 @@ - # Phân đoạn Chúng ta đã học về Phát hiện Đối tượng, cho phép xác định vị trí các đối tượng trong hình ảnh bằng cách dự đoán *hộp giới hạn* của chúng. Tuy nhiên, đối với một số nhiệm vụ, chúng ta không chỉ cần hộp giới hạn mà còn cần định vị đối tượng chính xác hơn. Nhiệm vụ này được gọi là **phân đoạn**. @@ -20,7 +11,7 @@ Phân đoạn có thể được xem như **phân loại điểm ảnh**, trong Ví dụ, trong phân đoạn theo đối tượng, những con cừu này là các đối tượng khác nhau, nhưng trong phân đoạn ngữ nghĩa, tất cả các con cừu đều được biểu diễn bởi một lớp duy nhất. - + > Hình ảnh từ [bài viết này](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50) @@ -29,7 +20,7 @@ Có nhiều kiến trúc mạng thần kinh khác nhau cho phân đoạn, nhưng * **Encoder** trích xuất các đặc trưng từ hình ảnh đầu vào. * **Decoder** chuyển đổi các đặc trưng đó thành **hình ảnh mặt nạ**, với kích thước và số lượng kênh tương ứng với số lượng lớp. - + > Hình ảnh từ [ấn phẩm này](https://arxiv.org/pdf/2001.05566.pdf) @@ -43,7 +34,7 @@ Trong bài học này, chúng ta sẽ thấy phân đoạn hoạt động bằng > ✅ Kỹ thuật này đặc biệt phù hợp với loại hình ảnh y tế này, nhưng bạn có thể hình dung những ứng dụng thực tế nào khác? -navi +navi > Hình ảnh từ Cơ sở dữ liệu PH2 diff --git a/translations/vi/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/vi/lessons/4-ComputerVision/12-Segmentation/lab/README.md index dd5f7708..aed6e9ac 100644 --- a/translations/vi/lessons/4-ComputerVision/12-Segmentation/lab/README.md +++ b/translations/vi/lessons/4-ComputerVision/12-Segmentation/lab/README.md @@ -1,12 +1,3 @@ - # Phân Đoạn Cơ Thể Người Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/4-ComputerVision/README.md b/translations/vi/lessons/4-ComputerVision/README.md index b3681741..89573e68 100644 --- a/translations/vi/lessons/4-ComputerVision/README.md +++ b/translations/vi/lessons/4-ComputerVision/README.md @@ -1,12 +1,3 @@ - # Thị giác Máy tính ![Tóm tắt nội dung Thị giác Máy tính dưới dạng hình vẽ](../../../../translated_images/vi/ai-computervision.6506ebebac3fbf76.webp) diff --git a/translations/vi/lessons/5-NLP/13-TextRep/README.md b/translations/vi/lessons/5-NLP/13-TextRep/README.md index bd86438a..6648c729 100644 --- a/translations/vi/lessons/5-NLP/13-TextRep/README.md +++ b/translations/vi/lessons/5-NLP/13-TextRep/README.md @@ -1,12 +1,3 @@ - # Đại diện Văn bản dưới dạng Tensors ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/25) @@ -25,7 +16,7 @@ Mục tiêu của chúng ta là phân loại bài báo vào một trong các dan Nếu chúng ta muốn giải quyết các nhiệm vụ Xử lý Ngôn ngữ Tự nhiên (NLP) bằng mạng nơ-ron, chúng ta cần một cách để đại diện văn bản dưới dạng tensors. Máy tính đã đại diện các ký tự văn bản dưới dạng số, ánh xạ đến các phông chữ trên màn hình của bạn bằng các mã hóa như ASCII hoặc UTF-8. -Hình ảnh hiển thị sơ đồ ánh xạ một ký tự sang đại diện ASCII và nhị phân +Hình ảnh hiển thị sơ đồ ánh xạ một ký tự sang đại diện ASCII và nhị phân > [Nguồn hình ảnh](https://www.seobility.net/en/wiki/ASCII) @@ -48,7 +39,7 @@ Trong một số trường hợp, chúng ta có thể xem xét sử dụng tri-g Khi giải quyết các nhiệm vụ như phân loại văn bản, chúng ta cần có khả năng đại diện văn bản bằng một vector kích thước cố định, mà chúng ta sẽ sử dụng làm đầu vào cho bộ phân loại cuối cùng. Một trong những cách đơn giản nhất để làm điều đó là kết hợp tất cả các đại diện từ riêng lẻ, ví dụ bằng cách cộng chúng lại. Nếu chúng ta cộng các mã hóa one-hot của mỗi từ, chúng ta sẽ có một vector tần suất, cho thấy mỗi từ xuất hiện bao nhiêu lần trong văn bản. Cách đại diện văn bản này được gọi là **bag of words** (BoW). - + > Hình ảnh của tác giả diff --git a/translations/vi/lessons/5-NLP/13-TextRep/assignment.md b/translations/vi/lessons/5-NLP/13-TextRep/assignment.md index 35a32060..c851e19b 100644 --- a/translations/vi/lessons/5-NLP/13-TextRep/assignment.md +++ b/translations/vi/lessons/5-NLP/13-TextRep/assignment.md @@ -1,12 +1,3 @@ - # Bài tập: Sổ tay (Notebooks) Sử dụng các sổ tay liên quan đến bài học này (có thể là phiên bản PyTorch hoặc TensorFlow), chạy lại chúng với bộ dữ liệu của riêng bạn, có thể lấy từ Kaggle, và nhớ ghi nguồn. Viết lại sổ tay để làm nổi bật những phát hiện của bạn. Hãy thử sử dụng một số bộ dữ liệu sáng tạo có thể mang lại bất ngờ, chẳng hạn như [bộ dữ liệu về các lần nhìn thấy UFO này](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) từ NUFORC. diff --git a/translations/vi/lessons/5-NLP/14-Embeddings/README.md b/translations/vi/lessons/5-NLP/14-Embeddings/README.md index a75171a1..d4c005ab 100644 --- a/translations/vi/lessons/5-NLP/14-Embeddings/README.md +++ b/translations/vi/lessons/5-NLP/14-Embeddings/README.md @@ -1,12 +1,3 @@ - # Nhúng ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/27) diff --git a/translations/vi/lessons/5-NLP/14-Embeddings/assignment.md b/translations/vi/lessons/5-NLP/14-Embeddings/assignment.md index 05f5f003..2ddbb208 100644 --- a/translations/vi/lessons/5-NLP/14-Embeddings/assignment.md +++ b/translations/vi/lessons/5-NLP/14-Embeddings/assignment.md @@ -1,12 +1,3 @@ - # Bài tập: Sổ tay (Notebooks) Sử dụng các sổ tay liên quan đến bài học này (có thể là phiên bản PyTorch hoặc TensorFlow), chạy lại chúng với bộ dữ liệu của riêng bạn, có thể lấy từ Kaggle, và nhớ ghi nguồn. Viết lại sổ tay để làm nổi bật những phát hiện của bạn. Thử sử dụng một loại bộ dữ liệu khác và ghi lại những phát hiện của bạn, sử dụng văn bản như [lời bài hát của Beatles](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics). diff --git a/translations/vi/lessons/5-NLP/15-LanguageModeling/README.md b/translations/vi/lessons/5-NLP/15-LanguageModeling/README.md index 376da40d..d3153ea2 100644 --- a/translations/vi/lessons/5-NLP/15-LanguageModeling/README.md +++ b/translations/vi/lessons/5-NLP/15-LanguageModeling/README.md @@ -1,12 +1,3 @@ - # Mô hình Ngôn ngữ Các biểu diễn ngữ nghĩa, như Word2Vec và GloVe, thực chất là bước đầu tiên hướng tới **mô hình ngôn ngữ** - tạo ra các mô hình có thể *hiểu* (hoặc *biểu diễn*) bản chất của ngôn ngữ. diff --git a/translations/vi/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/vi/lessons/5-NLP/15-LanguageModeling/lab/README.md index d9cca107..49852787 100644 --- a/translations/vi/lessons/5-NLP/15-LanguageModeling/lab/README.md +++ b/translations/vi/lessons/5-NLP/15-LanguageModeling/lab/README.md @@ -1,12 +1,3 @@ - # Huấn Luyện Mô Hình Skip-Gram Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/5-NLP/16-RNN/README.md b/translations/vi/lessons/5-NLP/16-RNN/README.md index 66176d28..6e99e30f 100644 --- a/translations/vi/lessons/5-NLP/16-RNN/README.md +++ b/translations/vi/lessons/5-NLP/16-RNN/README.md @@ -1,12 +1,3 @@ - # Mạng Nơ-ron Tái Phục Hồi ## [Câu hỏi kiểm tra trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/31) @@ -31,7 +22,7 @@ Hãy xem cách một cell RNN đơn giản được tổ chức. Nó nhận tr Một cell RNN đơn giản có hai ma trận trọng số bên trong: một ma trận biến đổi một ký hiệu đầu vào (gọi là W), và một ma trận khác biến đổi một trạng thái đầu vào (H). Trong trường hợp này, đầu ra của mạng được tính bằng σ(W×Xi+H×Si-1+b), trong đó σ là hàm kích hoạt và b là bias bổ sung. -Cấu trúc RNN Cell +Cấu trúc RNN Cell > Hình ảnh của tác giả diff --git a/translations/vi/lessons/5-NLP/16-RNN/assignment.md b/translations/vi/lessons/5-NLP/16-RNN/assignment.md index 171e0641..ef9a33b4 100644 --- a/translations/vi/lessons/5-NLP/16-RNN/assignment.md +++ b/translations/vi/lessons/5-NLP/16-RNN/assignment.md @@ -1,12 +1,3 @@ - # Bài tập: Sổ tay (Notebooks) Sử dụng các sổ tay liên quan đến bài học này (có thể là phiên bản PyTorch hoặc TensorFlow), chạy lại chúng với bộ dữ liệu của riêng bạn, có thể lấy từ Kaggle, và nhớ ghi nguồn. Viết lại sổ tay để làm nổi bật những phát hiện của bạn. Thử sử dụng một loại bộ dữ liệu khác và ghi lại những phát hiện của bạn, ví dụ như sử dụng văn bản như [bộ dữ liệu cuộc thi Kaggle này về các tweet thời tiết](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv). diff --git a/translations/vi/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/vi/lessons/5-NLP/17-GenerativeNetworks/README.md index 8a6be17b..af4c8fc4 100644 --- a/translations/vi/lessons/5-NLP/17-GenerativeNetworks/README.md +++ b/translations/vi/lessons/5-NLP/17-GenerativeNetworks/README.md @@ -1,12 +1,3 @@ - # Mạng tạo sinh ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/33) @@ -36,7 +27,7 @@ Chúng ta sẽ huấn luyện RNN này để tạo văn bản từng bước. Khi tạo văn bản (trong quá trình suy luận), chúng ta bắt đầu với một **gợi ý**, được truyền qua các tế bào RNN để tạo trạng thái trung gian của nó, và sau đó từ trạng thái này bắt đầu quá trình tạo. Chúng ta tạo từng ký tự một, và truyền trạng thái cùng ký tự vừa tạo vào một tế bào RNN khác để tạo ký tự tiếp theo, cho đến khi tạo đủ số ký tự. - + > Hình ảnh của tác giả diff --git a/translations/vi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/vi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md index 58c93606..a9d472db 100644 --- a/translations/vi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md +++ b/translations/vi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md @@ -1,12 +1,3 @@ - # Tạo văn bản ở cấp độ từ bằng RNNs Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/5-NLP/18-Transformers/README.md b/translations/vi/lessons/5-NLP/18-Transformers/README.md index 4b7d9536..c1cfae2b 100644 --- a/translations/vi/lessons/5-NLP/18-Transformers/README.md +++ b/translations/vi/lessons/5-NLP/18-Transformers/README.md @@ -1,12 +1,3 @@ - # Cơ chế Attention và Transformers ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/35) @@ -56,7 +47,7 @@ Một trong những ý tưởng chính đằng sau transformers là tránh tính * Nhúng có thể huấn luyện, tương tự như nhúng token. Đây là cách tiếp cận chúng ta xem xét ở đây. Chúng ta áp dụng các lớp nhúng lên cả token và vị trí của chúng, tạo ra các vector nhúng có cùng kích thước, sau đó cộng chúng lại với nhau. * Hàm mã hóa vị trí cố định, như được đề xuất trong bài báo gốc. - + > Hình ảnh của tác giả diff --git a/translations/vi/lessons/5-NLP/18-Transformers/assignment.md b/translations/vi/lessons/5-NLP/18-Transformers/assignment.md index fa1bbe98..682c3930 100644 --- a/translations/vi/lessons/5-NLP/18-Transformers/assignment.md +++ b/translations/vi/lessons/5-NLP/18-Transformers/assignment.md @@ -1,12 +1,3 @@ - # Bài tập: Transformers Thử nghiệm với Transformers trên HuggingFace! Hãy thử một số script mà họ cung cấp để làm việc với các mô hình khác nhau có sẵn trên trang của họ: https://huggingface.co/docs/transformers/run_scripts. Thử một trong các bộ dữ liệu của họ, sau đó nhập một bộ dữ liệu của riêng bạn từ chương trình học này hoặc từ Kaggle và xem liệu bạn có thể tạo ra các văn bản thú vị không. Tạo một notebook với những phát hiện của bạn. diff --git a/translations/vi/lessons/5-NLP/19-NER/README.md b/translations/vi/lessons/5-NLP/19-NER/README.md index 151a13f8..c0ae0ef4 100644 --- a/translations/vi/lessons/5-NLP/19-NER/README.md +++ b/translations/vi/lessons/5-NLP/19-NER/README.md @@ -1,12 +1,3 @@ - # Nhận diện Thực thể Được đặt tên Cho đến nay, chúng ta chủ yếu tập trung vào một nhiệm vụ NLP - phân loại. Tuy nhiên, còn có nhiều nhiệm vụ NLP khác có thể được thực hiện bằng mạng nơ-ron. Một trong những nhiệm vụ đó là **[Nhận diện Thực thể Được đặt tên](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), nhiệm vụ này liên quan đến việc nhận diện các thực thể cụ thể trong văn bản, chẳng hạn như địa điểm, tên người, khoảng thời gian, công thức hóa học, và nhiều hơn nữa. @@ -17,7 +8,7 @@ Cho đến nay, chúng ta chủ yếu tập trung vào một nhiệm vụ NLP - Giả sử bạn muốn phát triển một chatbot ngôn ngữ tự nhiên, tương tự như Amazon Alexa hoặc Google Assistant. Cách các chatbot thông minh hoạt động là *hiểu* người dùng muốn gì bằng cách thực hiện phân loại văn bản trên câu đầu vào. Kết quả của việc phân loại này là cái gọi là **ý định**, xác định chatbot nên làm gì. -Bot NER +Bot NER > Hình ảnh của tác giả diff --git a/translations/vi/lessons/5-NLP/19-NER/lab/README.md b/translations/vi/lessons/5-NLP/19-NER/lab/README.md index 47f28a47..fc364b67 100644 --- a/translations/vi/lessons/5-NLP/19-NER/lab/README.md +++ b/translations/vi/lessons/5-NLP/19-NER/lab/README.md @@ -1,12 +1,3 @@ - # NER Bài tập thực hành từ [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners). diff --git a/translations/vi/lessons/5-NLP/20-LangModels/README.md b/translations/vi/lessons/5-NLP/20-LangModels/README.md index 8ce208b3..84b6ba28 100644 --- a/translations/vi/lessons/5-NLP/20-LangModels/README.md +++ b/translations/vi/lessons/5-NLP/20-LangModels/README.md @@ -1,12 +1,3 @@ - # Các Mô Hình Ngôn Ngữ Lớn Được Huấn Luyện Trước Trong tất cả các nhiệm vụ trước đây, chúng ta đã huấn luyện một mạng nơ-ron để thực hiện một nhiệm vụ cụ thể bằng cách sử dụng tập dữ liệu có nhãn. Với các mô hình transformer lớn, như BERT, chúng ta sử dụng mô hình ngôn ngữ theo cách tự giám sát để xây dựng một mô hình ngôn ngữ, sau đó được chuyên biệt hóa cho các nhiệm vụ cụ thể với việc huấn luyện thêm theo từng lĩnh vực. Tuy nhiên, đã có minh chứng rằng các mô hình ngôn ngữ lớn cũng có thể giải quyết nhiều nhiệm vụ mà KHÔNG cần huấn luyện theo từng lĩnh vực. Một nhóm các mô hình có khả năng làm điều này được gọi là **GPT**: Generative Pre-Trained Transformer. diff --git a/translations/vi/lessons/5-NLP/README.md b/translations/vi/lessons/5-NLP/README.md index aef06315..3d527d48 100644 --- a/translations/vi/lessons/5-NLP/README.md +++ b/translations/vi/lessons/5-NLP/README.md @@ -1,12 +1,3 @@ - # Xử lý Ngôn ngữ Tự nhiên ![Tóm tắt các nhiệm vụ NLP trong một hình vẽ](../../../../translated_images/vi/ai-nlp.b22dcb8ca4707cea.webp) diff --git a/translations/vi/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/vi/lessons/6-Other/21-GeneticAlgorithms/README.md index b6002e55..3d527b9f 100644 --- a/translations/vi/lessons/6-Other/21-GeneticAlgorithms/README.md +++ b/translations/vi/lessons/6-Other/21-GeneticAlgorithms/README.md @@ -1,12 +1,3 @@ - # Thuật toán Di truyền ## [Câu hỏi trước bài giảng](https://ff-quizzes.netlify.app/en/ai/quiz/41) diff --git a/translations/vi/lessons/6-Other/22-DeepRL/README.md b/translations/vi/lessons/6-Other/22-DeepRL/README.md index dc7a9a8e..b51681de 100644 --- a/translations/vi/lessons/6-Other/22-DeepRL/README.md +++ b/translations/vi/lessons/6-Other/22-DeepRL/README.md @@ -1,12 +1,3 @@ - # Học Tăng Cường Sâu Học tăng cường (Reinforcement Learning - RL) được xem là một trong những mô hình học máy cơ bản, bên cạnh học có giám sát và học không giám sát. Trong khi học có giám sát dựa vào tập dữ liệu với kết quả đã biết, RL lại dựa trên **học thông qua hành động**. Ví dụ, khi lần đầu chơi một trò chơi máy tính, chúng ta bắt đầu chơi mà không biết luật, và sau đó cải thiện kỹ năng chỉ bằng cách chơi và điều chỉnh hành vi. @@ -34,7 +25,7 @@ Chắc hẳn bạn đã từng thấy các thiết bị cân bằng hiện đạ Phiên bản đơn giản hóa của bài toán cân bằng được gọi là vấn đề **CartPole**. Trong thế giới CartPole, chúng ta có một thanh trượt ngang có thể di chuyển sang trái hoặc phải, và mục tiêu là cân bằng một cột thẳng đứng trên thanh trượt khi nó di chuyển. -a cartpole +a cartpole Để tạo và sử dụng môi trường này, chúng ta cần một vài dòng mã Python: diff --git a/translations/vi/lessons/6-Other/22-DeepRL/lab/README.md b/translations/vi/lessons/6-Other/22-DeepRL/lab/README.md index 42d7e113..29bcf78c 100644 --- a/translations/vi/lessons/6-Other/22-DeepRL/lab/README.md +++ b/translations/vi/lessons/6-Other/22-DeepRL/lab/README.md @@ -1,12 +1,3 @@ - ## Môi trường Môi trường Mountain Car bao gồm một chiếc xe bị mắc kẹt trong một thung lũng. Mục tiêu của bạn là nhảy ra khỏi thung lũng và đến được lá cờ. Các hành động bạn có thể thực hiện là tăng tốc sang trái, sang phải, hoặc không làm gì cả. Bạn có thể quan sát vị trí của xe dọc theo trục x và vận tốc. diff --git a/translations/vi/lessons/6-Other/23-MultiagentSystems/README.md b/translations/vi/lessons/6-Other/23-MultiagentSystems/README.md index 86a267b4..666ea298 100644 --- a/translations/vi/lessons/6-Other/23-MultiagentSystems/README.md +++ b/translations/vi/lessons/6-Other/23-MultiagentSystems/README.md @@ -1,12 +1,3 @@ - # Hệ Thống Đa Tác Nhân Một trong những cách để đạt được trí tuệ là phương pháp **nổi bật** (hoặc **tương hỗ**), dựa trên thực tế rằng hành vi kết hợp của nhiều tác nhân tương đối đơn giản có thể dẫn đến hành vi tổng thể phức tạp hơn (hoặc thông minh hơn) của hệ thống nói chung. Về lý thuyết, điều này dựa trên các nguyên tắc của [Trí tuệ Tập thể](https://en.wikipedia.org/wiki/Collective_intelligence), [Thuyết Nổi bật](https://en.wikipedia.org/wiki/Global_brain) và [Điều khiển học Tiến hóa](https://en.wikipedia.org/wiki/Global_brain), cho rằng các hệ thống cấp cao hơn đạt được một giá trị gia tăng nào đó khi được kết hợp đúng cách từ các hệ thống cấp thấp hơn (còn gọi là *nguyên tắc chuyển đổi siêu hệ thống*). @@ -60,7 +51,7 @@ Bạn có thể [tải xuống](https://ccl.northwestern.edu/netlogo/download.sh Một điều tuyệt vời về NetLogo là nó chứa một thư viện các mô hình hoạt động mà bạn có thể thử. Đi tới **File → Models Library**, và bạn có nhiều danh mục mô hình để lựa chọn. -Thư viện Mô Hình NetLogo +Thư viện Mô Hình NetLogo > Ảnh chụp màn hình thư viện mô hình của Dmitry Soshnikov diff --git a/translations/vi/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/vi/lessons/6-Other/23-MultiagentSystems/assignment.md index cf9abbc9..778de60e 100644 --- a/translations/vi/lessons/6-Other/23-MultiagentSystems/assignment.md +++ b/translations/vi/lessons/6-Other/23-MultiagentSystems/assignment.md @@ -1,12 +1,3 @@ - # Bài Tập NetLogo Hãy chọn một trong các mô hình trong thư viện của NetLogo và sử dụng nó để mô phỏng một tình huống thực tế một cách sát nhất có thể. Một ví dụ hay là điều chỉnh mô hình Virus trong thư mục Alternative Visualizations để cho thấy cách nó có thể được sử dụng để mô phỏng sự lây lan của COVID-19. Bạn có thể xây dựng một mô hình mô phỏng sự lây lan của virus trong thực tế không? diff --git a/translations/vi/lessons/7-Ethics/README.md b/translations/vi/lessons/7-Ethics/README.md index 8a0af618..a6455dc9 100644 --- a/translations/vi/lessons/7-Ethics/README.md +++ b/translations/vi/lessons/7-Ethics/README.md @@ -1,12 +1,3 @@ - # AI Đạo Đức và Trách Nhiệm Bạn đã gần hoàn thành khóa học này, và tôi hy vọng rằng đến thời điểm này bạn đã thấy rõ rằng AI dựa trên một số phương pháp toán học chính thức cho phép chúng ta tìm ra mối quan hệ trong dữ liệu và huấn luyện các mô hình để tái tạo một số khía cạnh của hành vi con người. Tại thời điểm lịch sử này, chúng ta coi AI là một công cụ rất mạnh mẽ để trích xuất các mẫu từ dữ liệu và áp dụng các mẫu đó để giải quyết các vấn đề mới. diff --git a/translations/vi/lessons/README.md b/translations/vi/lessons/README.md index 74a2dbdd..27a3b5b1 100644 --- a/translations/vi/lessons/README.md +++ b/translations/vi/lessons/README.md @@ -1,12 +1,3 @@ - # Tổng quan ![Tổng quan trong một hình vẽ minh họa](../../../translated_images/vi/ai-overview.0857791951d19500.webp) diff --git a/translations/vi/lessons/X-Extras/X1-MultiModal/README.md b/translations/vi/lessons/X-Extras/X1-MultiModal/README.md index e95ef145..650e186b 100644 --- a/translations/vi/lessons/X-Extras/X1-MultiModal/README.md +++ b/translations/vi/lessons/X-Extras/X1-MultiModal/README.md @@ -1,12 +1,3 @@ - # Mạng Đa Phương Thức Sau thành công của các mô hình transformer trong việc giải quyết các nhiệm vụ NLP, các kiến trúc tương tự đã được áp dụng cho các nhiệm vụ thị giác máy tính. Ngày càng có nhiều sự quan tâm đến việc xây dựng các mô hình có thể *kết hợp* khả năng xử lý hình ảnh và ngôn ngữ tự nhiên. Một trong những nỗ lực đó được thực hiện bởi OpenAI, được gọi là CLIP và DALL.E. diff --git a/translations/vi/lessons/sketchnotes/LICENSE.md b/translations/vi/lessons/sketchnotes/LICENSE.md index 921b0a31..3e0a78d2 100644 --- a/translations/vi/lessons/sketchnotes/LICENSE.md +++ b/translations/vi/lessons/sketchnotes/LICENSE.md @@ -1,12 +1,3 @@ - Quyền Chia Sẻ Tương Tự 4.0 Quốc Tế ======================================================================= diff --git a/translations/vi/lessons/sketchnotes/README.md b/translations/vi/lessons/sketchnotes/README.md index d550a601..d6b21602 100644 --- a/translations/vi/lessons/sketchnotes/README.md +++ b/translations/vi/lessons/sketchnotes/README.md @@ -1,12 +1,3 @@ - Tất cả các bản vẽ phác thảo của chương trình học có thể được tải xuống tại đây. 🎨 Tạo bởi: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac)) diff --git a/translations/vi/troubleshoot.md b/translations/vi/troubleshoot.md index 8e6e2050..984802d9 100644 --- a/translations/vi/troubleshoot.md +++ b/translations/vi/troubleshoot.md @@ -1,12 +1,3 @@ - # Hướng Dẫn Khắc Phục Sự Cố AI-For-Beginners Hướng dẫn này giúp bạn giải quyết các vấn đề thường gặp khi sử dụng hoặc đóng góp vào kho lưu trữ [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners). Mỗi vấn đề bao gồm thông tin nền, triệu chứng, giải thích và các bước giải quyết cụ thể.