chore(i18n): sync translations with latest source changes (chunk 1/1, 201 changes)
This commit is contained in:
localizeflow[bot]
parent
43c61babaf
commit
2cf3095b7a
|
|
@ -0,0 +1,398 @@
|
|||
{
|
||||
"AGENTS.md": {
|
||||
"original_hash": "6b11a37115944252ab3ed04e358d830d",
|
||||
"translation_date": "2025-10-03T09:30:38+00:00",
|
||||
"source_file": "AGENTS.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"README.md": {
|
||||
"original_hash": "1984fc89dd304a8a33ab5584691a99aa",
|
||||
"translation_date": "2026-01-30T02:40:01+00:00",
|
||||
"source_file": "README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"SECURITY.md": {
|
||||
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
|
||||
"translation_date": "2025-08-25T21:22:00+00:00",
|
||||
"source_file": "SECURITY.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/CODE_OF_CONDUCT.md": {
|
||||
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
|
||||
"translation_date": "2025-08-26T00:44:58+00:00",
|
||||
"source_file": "etc/CODE_OF_CONDUCT.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/CONTRIBUTING.md": {
|
||||
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
|
||||
"translation_date": "2025-08-26T00:47:59+00:00",
|
||||
"source_file": "etc/CONTRIBUTING.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/Mindmap.md": {
|
||||
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
|
||||
"translation_date": "2025-08-26T00:51:04+00:00",
|
||||
"source_file": "etc/Mindmap.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/SUPPORT.md": {
|
||||
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
|
||||
"translation_date": "2025-08-26T00:43:56+00:00",
|
||||
"source_file": "etc/SUPPORT.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/TRANSLATIONS.md": {
|
||||
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
|
||||
"translation_date": "2025-08-26T00:46:23+00:00",
|
||||
"source_file": "etc/TRANSLATIONS.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"etc/quiz-app/README.md": {
|
||||
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
|
||||
"translation_date": "2025-08-26T00:54:39+00:00",
|
||||
"source_file": "etc/quiz-app/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"examples/README.md": {
|
||||
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
|
||||
"translation_date": "2025-10-03T11:34:49+00:00",
|
||||
"source_file": "examples/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/0-course-setup/for-teachers.md": {
|
||||
"original_hash": "a094ef9927883de1cfcee51dbd143381",
|
||||
"translation_date": "2025-08-26T00:39:34+00:00",
|
||||
"source_file": "lessons/0-course-setup/for-teachers.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/0-course-setup/how-to-run.md": {
|
||||
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
|
||||
"translation_date": "2026-01-16T06:04:58+00:00",
|
||||
"source_file": "lessons/0-course-setup/how-to-run.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/0-course-setup/setup.md": {
|
||||
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
|
||||
"translation_date": "2025-12-12T20:20:45+00:00",
|
||||
"source_file": "lessons/0-course-setup/setup.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/1-Intro/README.md": {
|
||||
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
|
||||
"translation_date": "2025-11-18T22:08:05+00:00",
|
||||
"source_file": "lessons/1-Intro/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/1-Intro/assignment.md": {
|
||||
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
|
||||
"translation_date": "2025-11-18T22:09:17+00:00",
|
||||
"source_file": "lessons/1-Intro/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/2-Symbolic/README.md": {
|
||||
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
|
||||
"translation_date": "2026-01-16T06:05:20+00:00",
|
||||
"source_file": "lessons/2-Symbolic/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/2-Symbolic/assignment.md": {
|
||||
"original_hash": "a057a8604f3976c3e309884453f1fad0",
|
||||
"translation_date": "2025-08-26T00:34:18+00:00",
|
||||
"source_file": "lessons/2-Symbolic/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/03-Perceptron/README.md": {
|
||||
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
|
||||
"translation_date": "2025-09-23T14:56:42+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
|
||||
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
|
||||
"translation_date": "2025-08-30T07:06:15+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
|
||||
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
|
||||
"translation_date": "2025-09-23T14:56:13+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
|
||||
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
|
||||
"translation_date": "2025-08-25T23:49:22+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/05-Frameworks/README.md": {
|
||||
"original_hash": "ddd216f558a255260a9374008002c971",
|
||||
"translation_date": "2025-09-23T14:56:58+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
|
||||
"original_hash": "e452d897efb9a89700f41021834cf6e5",
|
||||
"translation_date": "2025-08-25T23:55:54+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/README.md": {
|
||||
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
|
||||
"translation_date": "2025-10-03T12:53:55+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/06-IntroCV/README.md": {
|
||||
"original_hash": "feeca98225cb420afc89415f24f63d92",
|
||||
"translation_date": "2025-09-23T14:51:44+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
|
||||
"original_hash": "3d53d6409f80970f7281a45dee35328a",
|
||||
"translation_date": "2025-08-25T23:05:52+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
|
||||
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
|
||||
"translation_date": "2025-09-23T14:51:00+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/README.md": {
|
||||
"original_hash": "a560d5b845962cf33dc102266e409568",
|
||||
"translation_date": "2025-09-23T14:50:40+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
|
||||
"original_hash": "b70fcf7fcee862990f848c679090943f",
|
||||
"translation_date": "2025-10-03T14:58:11+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/README.md": {
|
||||
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
|
||||
"translation_date": "2025-09-23T14:51:17+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
|
||||
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
|
||||
"translation_date": "2025-08-25T23:14:14+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
|
||||
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
|
||||
"translation_date": "2025-08-25T23:17:08+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/09-Autoencoders/README.md": {
|
||||
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
|
||||
"translation_date": "2025-09-23T14:52:43+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/10-GANs/README.md": {
|
||||
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
|
||||
"translation_date": "2025-09-23T14:53:28+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/11-ObjectDetection/README.md": {
|
||||
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
|
||||
"translation_date": "2025-09-23T14:52:10+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
|
||||
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
|
||||
"translation_date": "2025-08-25T22:50:29+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/12-Segmentation/README.md": {
|
||||
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
|
||||
"translation_date": "2025-09-23T14:53:13+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
|
||||
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
|
||||
"translation_date": "2025-08-25T22:37:34+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/4-ComputerVision/README.md": {
|
||||
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
|
||||
"translation_date": "2025-08-25T22:28:11+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/13-TextRep/README.md": {
|
||||
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
|
||||
"translation_date": "2025-09-23T15:00:14+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/13-TextRep/assignment.md": {
|
||||
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
|
||||
"translation_date": "2025-08-25T21:54:49+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/14-Embeddings/README.md": {
|
||||
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
|
||||
"translation_date": "2025-09-23T14:59:50+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/14-Embeddings/assignment.md": {
|
||||
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
|
||||
"translation_date": "2025-08-25T21:42:58+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/15-LanguageModeling/README.md": {
|
||||
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
|
||||
"translation_date": "2025-09-23T14:57:57+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/15-LanguageModeling/lab/README.md": {
|
||||
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
|
||||
"translation_date": "2025-08-25T21:58:39+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/16-RNN/README.md": {
|
||||
"original_hash": "e2273cc150380a5e191903cea858f021",
|
||||
"translation_date": "2025-09-23T14:59:20+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/16-RNN/assignment.md": {
|
||||
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
|
||||
"translation_date": "2025-08-25T21:37:31+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/17-GenerativeNetworks/README.md": {
|
||||
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
|
||||
"translation_date": "2025-09-23T14:57:29+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
|
||||
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
|
||||
"translation_date": "2025-08-25T21:48:43+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/18-Transformers/README.md": {
|
||||
"original_hash": "f335dfcb4a993920504c387973a36957",
|
||||
"translation_date": "2025-09-23T14:58:10+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/18-Transformers/assignment.md": {
|
||||
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
|
||||
"translation_date": "2025-08-25T22:05:33+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/19-NER/README.md": {
|
||||
"original_hash": "6522312ff835796ca34136a9462fafb2",
|
||||
"translation_date": "2025-09-23T14:59:00+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/19-NER/lab/README.md": {
|
||||
"original_hash": "032bda5068f543d6c1fcb30c34231461",
|
||||
"translation_date": "2025-08-25T22:15:11+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/20-LangModels/README.md": {
|
||||
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
|
||||
"translation_date": "2025-09-23T14:58:41+00:00",
|
||||
"source_file": "lessons/5-NLP/20-LangModels/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/5-NLP/README.md": {
|
||||
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
|
||||
"translation_date": "2025-08-25T21:29:43+00:00",
|
||||
"source_file": "lessons/5-NLP/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/6-Other/21-GeneticAlgorithms/README.md": {
|
||||
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
|
||||
"translation_date": "2025-09-23T14:49:11+00:00",
|
||||
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/6-Other/22-DeepRL/README.md": {
|
||||
"original_hash": "04395657fc01648f8f70484d0e55ab67",
|
||||
"translation_date": "2025-09-23T14:50:11+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/6-Other/22-DeepRL/lab/README.md": {
|
||||
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
|
||||
"translation_date": "2025-08-25T23:36:02+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/6-Other/23-MultiagentSystems/README.md": {
|
||||
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
|
||||
"translation_date": "2025-09-23T14:49:30+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/6-Other/23-MultiagentSystems/assignment.md": {
|
||||
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
|
||||
"translation_date": "2025-08-25T23:29:29+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/7-Ethics/README.md": {
|
||||
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
|
||||
"translation_date": "2025-08-25T21:25:49+00:00",
|
||||
"source_file": "lessons/7-Ethics/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/README.md": {
|
||||
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
|
||||
"translation_date": "2025-08-25T21:23:24+00:00",
|
||||
"source_file": "lessons/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/X-Extras/X1-MultiModal/README.md": {
|
||||
"original_hash": "9c592c26aca16ca085d268c732284187",
|
||||
"translation_date": "2025-08-25T23:39:49+00:00",
|
||||
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/sketchnotes/LICENSE.md": {
|
||||
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
|
||||
"translation_date": "2025-08-26T00:12:28+00:00",
|
||||
"source_file": "lessons/sketchnotes/LICENSE.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"lessons/sketchnotes/README.md": {
|
||||
"original_hash": "050b8bddebafba55b129414e6ab096ab",
|
||||
"translation_date": "2025-08-26T00:02:20+00:00",
|
||||
"source_file": "lessons/sketchnotes/README.md",
|
||||
"language_code": "hr"
|
||||
},
|
||||
"troubleshoot.md": {
|
||||
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
|
||||
"translation_date": "2025-10-03T09:52:37+00:00",
|
||||
"source_file": "troubleshoot.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
}
|
||||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "6b11a37115944252ab3ed04e358d830d",
|
||||
"translation_date": "2025-10-03T09:30:38+00:00",
|
||||
"source_file": "AGENTS.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# AGENTS.md
|
||||
|
||||
## Pregled projekta
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "85102ce4bfab31103e99dc8ca2e2f181",
|
||||
"translation_date": "2026-01-16T06:02:34+00:00",
|
||||
"source_file": "README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
|
||||
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
|
||||
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
|
||||
|
|
@ -23,210 +14,212 @@ CO_OP_TRANSLATOR_METADATA:
|
|||
|
||||
# Umjetna inteligencija za početnike - Kurikulum
|
||||
|
||||
||
|
||||
||
|
||||
|:---:|
|
||||
| AI za početnike - _Sketchnote od [@girlie_mac](https://twitter.com/girlie_mac)_ |
|
||||
| AI za početnike - _Sketchnote by [@girlie_mac](https://twitter.com/girlie_mac)_ |
|
||||
|
||||
Istražite svijet **Umjetne inteligencije** (UI) s našim 12-tjednim, 24-lekcijskim kurikulumom! Uključuje praktične lekcije, kvizove i laboratorijske vježbe. Kurikulum je prilagođen početnicima i pokriva alate poput TensorFlowa i PyTorcha, kao i etiku u UI
|
||||
|
||||
Istražite svijet **Umjetne inteligencije** (UI) s našim 12-tjednim, 24-lekcijskim kurikulumom! Uključuje praktične lekcije, kvizove i radionice. Kurikulum je prilagođen početnicima i obuhvaća alate poput TensorFlow i PyTorch, kao i etiku u UI.
|
||||
|
||||
### 🌐 Podrška za više jezika
|
||||
|
||||
#### Podržano putem GitHub akcije (Automatski i uvijek ažurno)
|
||||
#### Podržano preko GitHub Action (Automatski i uvijek ažurno)
|
||||
|
||||
<!-- CO-OP TRANSLATOR LANGUAGES TABLE START -->
|
||||
[arapski](../ar/README.md) | [bengalski](../bn/README.md) | [bugarski](../bg/README.md) | [birmanski (Myanmar)](../my/README.md) | [kineski (pojednostavljeni)](../zh/README.md) | [kineski (tradicionalni, Hong Kong)](../hk/README.md) | [kineski (tradicionalni, Macau)](../mo/README.md) | [kineski (tradicionalni, Tajvan)](../tw/README.md) | [hrvatski](./README.md) | [češki](../cs/README.md) | [danski](../da/README.md) | [nizozemski](../nl/README.md) | [estonski](../et/README.md) | [finski](../fi/README.md) | [francuski](../fr/README.md) | [njemački](../de/README.md) | [grčki](../el/README.md) | [hebrejski](../he/README.md) | [hindski](../hi/README.md) | [mađarski](../hu/README.md) | [indonezijski](../id/README.md) | [talijanski](../it/README.md) | [japanski](../ja/README.md) | [kanada](../kn/README.md) | [korejski](../ko/README.md) | [litavski](../lt/README.md) | [malajski](../ms/README.md) | [malajalamski](../ml/README.md) | [maratijski](../mr/README.md) | [nepalski](../ne/README.md) | [nigerijski pidgin](../pcm/README.md) | [norveški](../no/README.md) | [persijski (farsi)](../fa/README.md) | [poljski](../pl/README.md) | [portugalski (Brazil)](../br/README.md) | [portugalski (Portugal)](../pt/README.md) | [pandžapski (Gurmukhi)](../pa/README.md) | [rumunjski](../ro/README.md) | [ruski](../ru/README.md) | [srpski (ćirilica)](../sr/README.md) | [slovački](../sk/README.md) | [slovenski](../sl/README.md) | [španjolski](../es/README.md) | [svahili](../sw/README.md) | [švedski](../sv/README.md) | [tagalog (filipinski)](../tl/README.md) | [tamil](../ta/README.md) | [telugu](../te/README.md) | [tajlandski](../th/README.md) | [turski](../tr/README.md) | [ukrajinski](../uk/README.md) | [urdu](../ur/README.md) | [vijetnamski](../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](./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)](../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)
|
||||
|
||||
> **Želite li klonirati lokalno?**
|
||||
> **Preferirate klonirati lokalno?**
|
||||
|
||||
> Ovo spremište uključuje više od 50 prijevoda jezika što znatno povećava veličinu preuzimanja. Za kloniranje bez prijevoda, koristite sparse checkout:
|
||||
> Ovaj repozitorij sadrži više od 50 prijevoda jezika što značajno povećava veličinu preuzimanja. Za kloniranje bez prijevoda, koristite 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'
|
||||
> ```
|
||||
> Ovo vam daje sve što vam je potrebno za dovršetak tečaja znatno bržim preuzimanjem.
|
||||
> Ovo vam daje sve što vam treba za završetak tečaja s mnogo bržim preuzimanjem.
|
||||
<!-- CO-OP TRANSLATOR LANGUAGES TABLE END -->
|
||||
|
||||
**Ako želite dodatne podržane jezike za prijevod, pogledajte [ovdje](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
|
||||
**Ako želite dodatnu podršku za prevode, podržani jezici su navedeni [ovdje](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
|
||||
|
||||
## Pridružite se zajednici
|
||||
[](https://discord.gg/nTYy5BXMWG)
|
||||
|
||||
## Što ćete naučiti
|
||||
|
||||
**[Mentalna mapa tečaja](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
|
||||
**[Mapa uma tečaja](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
|
||||
|
||||
U ovom kurikulumu naučit ćete:
|
||||
|
||||
* Različite pristupe umjetnoj inteligenciji, uključujući "dobri stari" simbolički pristup s **Reprezentacijom znanja** i zaključivanjem ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
|
||||
* **Neuronske mreže** i **duboko učenje**, koji su srž moderne UI. Objasnit ćemo koncepte iza ovih važnih tema koristeći kod u dva od najpopularnijih okvira - [TensorFlow](http://Tensorflow.org) i [PyTorch](http://pytorch.org).
|
||||
* **Neuronske arhitekture** za rad sa slikama i tekstom. Pokrit ćemo nedavne modele, ali možda ćemo malo zaostajati za najnovijim dostignućima.
|
||||
* Rjeđe popularne pristupe u UI, poput **genetskih algoritama** i **sustava s više agenata**.
|
||||
* Različite pristupe umjetnoj inteligenciji, uključujući "dobar stari" simbolički pristup s **reprezentacijom znanja** i zaključivanjem ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
|
||||
* **Neuronske mreže** i **Duboko učenje**, koji su u središtu moderne UI. Koncepte iza ovih važnih tema prikazat ćemo pomoću koda u dva najpopularnija okvira - [TensorFlow](http://Tensorflow.org) i [PyTorch](http://pytorch.org).
|
||||
* **Neuronske arhitekture** za rad sa slikama i tekstom. Pokrit ćemo nedavne modele, iako možda neće biti u potpunosti u vrhu suvremenih dostignuća.
|
||||
* Manje popularne pristupe u UI, poput **genetskih algoritama** i **višekorisničkih sustava**.
|
||||
|
||||
Što nećemo pokriti u ovom kurikulumu:
|
||||
|
||||
> [Pronađite sve dodatne resurse za ovaj tečaj u našoj kolekciji Microsoft Learn](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
|
||||
> [Pronađite sve dodatne resurse za ovaj tečaj u našoj Microsoft Learn kolekciji](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
|
||||
|
||||
* Poslovne slučajeve korištenja **UI u poslovanju**. Razmislite o polaganju [Uvod u UI za poslovne korisnike](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) na Microsoft Learn, ili [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), razvijen u suradnji s [INSEAD](https://www.insead.edu/).
|
||||
* **Klasično strojno učenje**, koje je dobro opisano u našem [Kurikulumu za strojno učenje za početnike](http://github.com/Microsoft/ML-for-Beginners).
|
||||
* Praktične primjene UI izgrađene korištenjem **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Za to preporučujemo da započnete s Microsoft Learn modulima za [viziju](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [obradu prirodnog jezika](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[generativnu umjetnu inteligenciju uz Azure OpenAI servis](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** i druge.
|
||||
* Specifične okvire za ML u oblaku, poput [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) ili [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Razmislite o korištenju tečajeva [Izgradite i upravljajte ML rješenjima uz Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) i [Izgradite i upravljajte ML rješenjima s Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
|
||||
* **Conversational AI** i **chat botove**. Postoji zaseban tečaj [Kreirajte konverzacijske AI aplikacije](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), a možete se referirati i na [ovaj blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) za više detalja.
|
||||
* **Duboku matematiku** iza dubokog učenja. Za to preporučujemo [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) autora Iana Goodfellowa, Yoshua Bengioa i Aarona Courvillea, koji je također dostupan online na [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
|
||||
* Poslovne slučajeve korištenja **UI u poslovanju**. Razmotrite polaganje [Uvod u UI za poslovne korisnike](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) putem Microsoft Learn ili [AI poslovnu školu](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), razvijenu u suradnji s [INSEAD](https://www.insead.edu/).
|
||||
* **Klasično strojno učenje**, koje je dobro opisano u našem [Kurikulumu strojnog učenja za početnike](http://github.com/Microsoft/ML-for-Beginners).
|
||||
* Praktične AI aplikacije izgrađene koristeći **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Za njih preporučujemo da započnete s modulima Microsoft Learn za [vid](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [obradu prirodnog jezika](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativnu umjetnu inteligenciju uz Azure OpenAI uslugu](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** i druge.
|
||||
* Specifične ML **cloud okvire**, kao što su [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) ili [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Razmislite o korištenju [Gradite i upravljajte ML rješenjima uz Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) i [Gradite i upravljajte ML rješenjima s Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) učnih staza.
|
||||
* **Konverzacijski UI** i **chat botovi**. Postoji zasebna [Staza za stvaranje konverzacijskih AI rješenja](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), a možete pogledati i [ovaj blog post](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) za dodatne detalje.
|
||||
* **Duboku matematiku** iza dubokog učenja. Za to preporučujemo [Duboko učenje](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) autora Ian Goodfellow, Yoshua Bengio i Aaron Courville, koja je također dostupna online na [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
|
||||
|
||||
Za lagani uvod u teme _AI u oblaku_ možete uzeti u obzir tečaj [Počnite s umjetnom inteligencijom na Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
|
||||
Za lagani uvod u teme _UI u oblaku_ možete razmotriti polaganje [Započinjemo s umjetnom inteligencijom na Azureu](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) učne staze.
|
||||
|
||||
# Sadržaj
|
||||
|
||||
| | Poveznica na lekciju | PyTorch/Keras/TensorFlow | Laboratorijske vježbe |
|
||||
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------------------------------------------ |
|
||||
| 0 | [Postavljanje tečaja](./lessons/0-course-setup/setup.md) | [Postavite svoje razvojno okruženje](./lessons/0-course-setup/how-to-run.md) | |
|
||||
| I | [**Uvod u umjetnu inteligenciju**](./lessons/1-Intro/README.md) | | |
|
||||
| | Poveznica lekcije | PyTorch/Keras/TensorFlow | Laboratorij |
|
||||
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
|
||||
| 0 | [Postavljanje kursa](./lessons/0-course-setup/setup.md) | [Postavite svoje razvojno okruženje](./lessons/0-course-setup/how-to-run.md) | |
|
||||
| I | [**Uvod u UI**](./lessons/1-Intro/README.md) | | |
|
||||
| 01 | [Uvod i povijest UI](./lessons/1-Intro/README.md) | - | - |
|
||||
| II | **Simbolička umjetna inteligencija** |
|
||||
| 02 | [Reprezentacija znanja i ekspertni sustavi](./lessons/2-Symbolic/README.md) | [Ekspertni sustavi](./lessons/2-Symbolic/Animals.ipynb) / [Ontologija](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Graf pojmova](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
|
||||
| II | **Simbolička UI** |
|
||||
| 02 | [Reprezentacija znanja i ekspertni sustavi](./lessons/2-Symbolic/README.md) | [Ekspertni sustavi](./lessons/2-Symbolic/Animals.ipynb) / [Ontologija](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Graf koncepata](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
|
||||
| III | [**Uvod u neuronske mreže**](./lessons/3-NeuralNetworks/README.md) |||
|
||||
| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Bilježnica](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Laboratorij](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
|
||||
| 04 | [Višeslojni perceptron i stvaranje vlastitog okvira](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Bilježnica](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Laboratorij](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
|
||||
| 05 | [Uvod u okvire (PyTorch/TensorFlow) i prekomjerno uklapanje](./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) | [Laboratorij](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
|
||||
| IV | [**Računalni vid**](./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)| [Istraži računalni vid na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
|
||||
| 05 | [Uvod u okvire (PyTorch/TensorFlow) i prenaučenost](./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) | [Laboratorij](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
|
||||
| IV | [**Računalni vid**](./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) | [Istražite računalni vid na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
|
||||
| 06 | [Uvod u računalni vid. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Bilježnica](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Laboratorij](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
|
||||
| 07 | [Konvolucijske neuronske mreže](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Arhitekture CNN-a](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Laboratorij](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
|
||||
| 08 | [Unaprijed naučene mreže i transferno učenje](./lessons/4-ComputerVision/08-TransferLearning/README.md) i [Trikovi treniranja](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Laboratorij](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
|
||||
| 09 | [Autoenkoderi i VAE-ovi](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
|
||||
| 10 | [Generativne kontradiktorne mreže i prijenos umjetničkog stila](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
|
||||
| 07 | [Konvolucijske neuronske mreže](./lessons/4-ComputerVision/07-ConvNets/README.md) & [Arhitekture 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) | [Laboratorij](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
|
||||
| 08 | [Unaprijed trenirane mreže i transfer učenja](./lessons/4-ComputerVision/08-TransferLearning/README.md) i [Trikovi u treniranju](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Laboratorij](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
|
||||
| 09 | [Autoenkoderi i 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 | [Generativne suparničke mreže i prijenos umjetničkog stila](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
|
||||
| 11 | [Detekcija objekata](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Laboratorij](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
|
||||
| 12 | [Semantička segmentacija. 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 | [**Obrada prirodnog jezika**](./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) | [Istraži obradu prirodnog jezika na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
|
||||
| 13 | [Predstavljanje teksta. 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 | [Semantičke vektorske reprezentacije riječi. Word2Vec i GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
|
||||
| 15 | [Modeliranje jezika. Treniranje vlastitih ugrađenih modela](./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) | [Laboratorij](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
|
||||
| V | [**Obrada prirodnog jezika**](./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) | [Istražite obradu prirodnog jezika na Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
|
||||
| 13 | [Predstavljanje teksta. 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 | [Semantičke riječne ugrađenosti. Word2Vec i GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
|
||||
| 15 | [Modeliranje jezika. Treniranje vlastitih ugrađenosti](./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) | [Laboratorij](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
|
||||
| 16 | [Rekurentne neuronske mreže](./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 | [Generativne rekurentne mreže](./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) | [Laboratorij](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
|
||||
| 18 | [Transformeri. 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 | [Prepoznavanje imenovanih entiteta](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Laboratorij](./lessons/5-NLP/19-NER/lab/README.md) |
|
||||
| 20 | [Veliki jezični modeli, programiranje na zahtjev i zadaci s malo primjera](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
|
||||
| 20 | [Veliki jezični modeli, programiranje upita i zadaci s malo primjera](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
|
||||
| VI | **Ostale AI tehnike** || |
|
||||
| 21 | [Genetski algoritmi](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Bilježnica](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
|
||||
| 22 | [Duboko učenje s pojačanjem](./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) | [Laboratorij](./lessons/6-Other/22-DeepRL/lab/README.md) |
|
||||
| 22 | [Duboko učenje s potkrepljenjem](./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) | [Laboratorij](./lessons/6-Other/22-DeepRL/lab/README.md) |
|
||||
| 23 | [Sustavi s više agenata](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
|
||||
| VII | **Etika umjetne inteligencije** | | |
|
||||
| 24 | [Etika umjetne inteligencije i odgovorna AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Načela odgovorne AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
|
||||
| VII | **AI etika** | | |
|
||||
| 24 | [AI etika i odgovorni AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Principi odgovornog AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
|
||||
| IX | **Dodatno** | | |
|
||||
| 25 | [Višeslojne mreže, CLIP i VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Bilježnica](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
|
||||
| 25 | [Višemodalne mreže, CLIP i VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Bilježnica](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
|
||||
|
||||
## Svaka lekcija sadrži
|
||||
|
||||
* Materijal za pred-čitanje
|
||||
* Izvršljive Jupyter bilježnice, koje su često specifične za okvir (**PyTorch** ili **TensorFlow**). Izvršljiva bilježnica također sadrži mnogo teoretskog materijala, stoga da biste razumjeli temu potrebno je proći kroz barem jednu verziju bilježnice (bilo PyTorch ili TensorFlow).
|
||||
* **Laboratorije** dostupne za neke teme, koje vam pružaju priliku da isprobate primjenu naučenog materijala na određenom problemu.
|
||||
* Neki dijelovi sadrže poveznice na [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) module koji pokrivaju povezane teme.
|
||||
* Materijal za predčitanje
|
||||
* Izvršne Jupyter bilježnice, koje su često specifične za okvir (**PyTorch** ili **TensorFlow**). Izvršna bilježnica također sadrži mnogo teorijskog materijala, stoga za razumijevanje teme morate proći barem jednu verziju bilježnice (bilo PyTorch ili TensorFlow).
|
||||
* **Laboratorije** dostupne za neke teme, koje vam daju priliku da isprobate primjenu naučenog materijala na određenom problemu.
|
||||
* Neki odjeljci sadrže poveznice na module [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) koji pokrivaju povezane teme.
|
||||
|
||||
## Početak
|
||||
|
||||
### 🎯 Novi u AI? Počnite ovdje!
|
||||
|
||||
Ako ste potpuno novi u umjetnoj inteligenciji i želite brze, praktične primjere, pogledajte naše [**Primjerima prilagođene početnicima**](./examples/README.md)! Oni uključuju:
|
||||
Ako ste potpuno novi u AI i želite brze, praktične primjere, pogledajte naše [**Primjere prilagođene početnicima**](./examples/README.md)! Oni uključuju:
|
||||
|
||||
- 🌟 **Pozdrav AI svijete** - Vaš prvi AI program (prepoznavanje uzoraka)
|
||||
- 🧠 **Jednostavna neuronska mreža** - Izgradite neuronsku mrežu ispočetka
|
||||
- 🖼️ **Klasifikator slika** - Klasificirajte slike s detaljnim komentarima
|
||||
- 💬 **Sentiment teksta** - Analizirajte pozitivan/negativan tekst
|
||||
- 🌟 **Hello AI World** - Vaš prvi AI program (prepoznavanje uzoraka)
|
||||
- 🧠 **Jednostavna neuronska mreža** - Izgradite neuronsku mrežu od nule
|
||||
|
||||
Ovi primjeri osmišljeni su kako bi vam pomogli razumjeti AI koncepte prije nego započnete s cjelokupnim kurikulumom.
|
||||
- 🖼️ **Klasifikator slika** - Klasificirajte slike s detaljnim komentarima
|
||||
- 💬 **Sentiment teksta** - Analizirajte pozitivan/negativan tekst
|
||||
|
||||
Ovi primjeri osmišljeni su da vam pomognu razumjeti AI koncepte prije nego što započnete s cjelokupnim kurikulumom.
|
||||
|
||||
### 📚 Postavljanje cjelokupnog kurikuluma
|
||||
|
||||
- Napravili smo [lekciju za postavljanje](./lessons/0-course-setup/setup.md) kako bismo vam pomogli pri postavljanju vašeg razvojog okruženja. - Za edukatore smo također kreirali [lekciju za postavljanje kurikuluma](./lessons/0-course-setup/for-teachers.md)!
|
||||
- Kako [pokrenuti kod u VSCode-u ili Codespace-u](./lessons/0-course-setup/how-to-run.md)
|
||||
- Izradili smo [lekciju za postavljanje](./lessons/0-course-setup/setup.md) koja će vam pomoći pri postavljanju razvojnog okruženja. - Za nastavnike smo također izradili [lekciju za postavljanje kurikuluma](./lessons/0-course-setup/for-teachers.md)!
|
||||
- Kako [pokrenuti kod u VSCode ili Codespaceu](./lessons/0-course-setup/how-to-run.md)
|
||||
|
||||
Slijedite ove korake:
|
||||
|
||||
Forkajte repositorij: Kliknite na gumb "Fork" u gornjem desnom kutu ove stranice.
|
||||
Forkajte repozitorij: Kliknite na gumb "Fork" u gornjem desnom kutu ove stranice.
|
||||
|
||||
Klonirajte repositorij: `git clone https://github.com/microsoft/AI-For-Beginners.git`
|
||||
Klonirajte repozitorij: `git clone https://github.com/microsoft/AI-For-Beginners.git`
|
||||
|
||||
Ne zaboravite označiti (🌟) ovaj repozitorij kako biste ga lakše pronašli kasnije.
|
||||
Ne zaboravite označiti (🌟) ovaj repo da biste ga lakše pronašli kasnije.
|
||||
|
||||
## Upoznajte druge polaznike
|
||||
|
||||
Pridružite se našem [službenom AI Discord serveru](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) kako biste upoznali i povezali se s ostalim polaznicima ovog tečaja i dobili podršku.
|
||||
Pridružite se našem [službenom AI Discord serveru](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) kako biste upoznali i povezali se s drugim polaznicima ovog tečaja i dobili podršku.
|
||||
|
||||
Ako imate povratne informacije o proizvodu ili pitanja tijekom izrade, posjetite naš [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
|
||||
|
||||
## Kvizovi
|
||||
## Kvizevi
|
||||
|
||||
> **Napomena o kvizovima**: Svi kvizovi nalaze se u mapi Quiz-app u etc\quiz-app, ili [Online Ovdje](https://ff-quizzes.netlify.app/) Povezani su iz lekcija, kviz aplikacija se može pokrenuti lokalno ili implementirati na Azure; slijedite upute u mapi `quiz-app`. Postupno se lokaliziraju.
|
||||
> **Napomena o kvizovima**: Svi kvizovi nalaze se u mapi Quiz-app u etc\quiz-app, ili [online ovdje](https://ff-quizzes.netlify.app/) Povezani su kroz lekcije; aplikaciju kviza možete pokrenuti lokalno ili je distribuirati na Azure; slijedite upute u mapi `quiz-app`. Postupno se lokaliziraju.
|
||||
|
||||
## Tražimo pomoć
|
||||
## Traži se pomoć
|
||||
|
||||
Imate li prijedloge ili ste pronašli pravopisne ili kodne greške? Otvorite issue ili kreirajte pull request.
|
||||
Imate li prijedloge ili ste pronašli pravopisne ili programske pogreške? Otvorite issue ili napravite pull request.
|
||||
|
||||
## Posebne zahvale
|
||||
## Posebna zahvalnost
|
||||
|
||||
* **✍️ Glavni autor:** [Dmitry Soshnikov](http://soshnikov.com), PhD
|
||||
* **🔥 Urednik:** [Jen Looper](https://twitter.com/jenlooper), PhD
|
||||
* **🎨 Ilustrator skica:** [Tomomi Imura](https://twitter.com/girlie_mac)
|
||||
* **✅ Kreator kvizova:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
|
||||
* **🙏 Glavni suradnici:** [Evgenii Pishchik](https://github.com/Pe4enIks)
|
||||
* **✍️ Glavni autor:** [Dmitry Soshnikov](http://soshnikov.com), PhD
|
||||
* **🔥 Urednik:** [Jen Looper](https://twitter.com/jenlooper), PhD
|
||||
* **🎨 Ilustrator sketchnote bilješki:** [Tomomi Imura](https://twitter.com/girlie_mac)
|
||||
* **✅ Kreator kvizova:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
|
||||
* **🙏 Glavni suradnici:** [Evgenii Pishchik](https://github.com/Pe4enIks)
|
||||
|
||||
## Ostali kurikulumi
|
||||
|
||||
Naš tim proizvodi i druge kurikulume! Pogledajte:
|
||||
|
||||
<!-- CO-OP TRANSLATOR OTHER COURSES START -->
|
||||
### LangChain
|
||||
[](https://aka.ms/langchain4j-for-beginners)
|
||||
[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
|
||||
### LangChain
|
||||
[](https://aka.ms/langchain4j-for-beginners)
|
||||
[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
|
||||
|
||||
---
|
||||
|
||||
### Azure / Edge / MCP / Agent
|
||||
[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
### Azure / Edge / MCP / Agent
|
||||
[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
---
|
||||
|
||||
### Serija Generativnog AI
|
||||
[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
|
||||
[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
|
||||
[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
### Serija Generativnog AI-a
|
||||
[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
|
||||
[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
|
||||
[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
---
|
||||
|
||||
### Osnovno učenje
|
||||
[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
|
||||
[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
### Osnovno učenje
|
||||
[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
|
||||
[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
---
|
||||
|
||||
### Serija Copilot
|
||||
[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
### Serija Copilot
|
||||
[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
|
||||
[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
|
||||
<!-- CO-OP TRANSLATOR OTHER COURSES END -->
|
||||
|
||||
## Dobivanje pomoći
|
||||
|
||||
Ako zapnete ili imate pitanja o izradi AI aplikacija, pridružite se drugim polaznicima i iskusnim developerima u diskusijama o MCP-u. To je podržavajuća zajednica gdje su pitanja dobrodošla, a znanje se slobodno dijeli.
|
||||
Ako zapnete ili imate pitanja o izradi AI aplikacija, pridružite se kolegama polaznicima i iskusnim programerima u raspravama o MCP-u. To je podržavajuća zajednica u kojoj su pitanja dobrodošla i znanje se slobodno dijeli.
|
||||
|
||||
[](https://discord.gg/nTYy5BXMWG)
|
||||
|
||||
Ako imate povratne informacije o proizvodu ili greške tijekom izrade, posjetite:
|
||||
Ako imate povratne informacije o proizvodu ili primijetite pogreške tijekom izrade, posjetite:
|
||||
|
||||
[](https://aka.ms/foundry/forum)
|
||||
|
||||
---
|
||||
|
||||
<!-- CO-OP TRANSLATOR DISCLAIMER START -->
|
||||
**Izjava o odricanju odgovornosti**:
|
||||
Ovaj dokument je preveden korištenjem AI prevoditeljskog servisa [Co-op Translator](https://github.com/Azure/co-op-translator). Iako nastojimo osigurati točnost, imajte na umu da automatski prijevodi mogu sadržavati pogreške ili netočnosti. Izvorni dokument na izvornom jeziku treba smatrati autoritativnim izvorom. Za važne informacije preporučuje se profesionalni ljudski prijevod. Ne snosimo odgovornost za bilo kakve nesporazume ili pogrešna tumačenja nastala uporabom ovog prijevoda.
|
||||
**Odricanje od odgovornosti**:
|
||||
Ovaj dokument je preveden pomoću AI usluge za prevođenje [Co-op Translator](https://github.com/Azure/co-op-translator). Iako nastojimo osigurati točnost, imajte na umu da automatski prijevodi mogu sadržavati pogreške ili netočnosti. Izvorni dokument na izvornom jeziku smatra se službenim i autoritativnim izvorom. Za važne informacije preporučuje se profesionalni ljudski prijevod. Ne snosimo odgovornost za bilo kakve nesporazume ili pogrešna tumačenja proizašla iz korištenja ovog prijevoda.
|
||||
<!-- CO-OP TRANSLATOR DISCLAIMER END -->
|
||||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
|
||||
"translation_date": "2025-08-25T21:22:00+00:00",
|
||||
"source_file": "SECURITY.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
## Sigurnost
|
||||
|
||||
Microsoft ozbiljno pristupa sigurnosti svojih softverskih proizvoda i usluga, uključujući sve repozitorije izvornog koda kojima upravljamo putem naših GitHub organizacija, kao što su [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) i [naše GitHub organizacije](https://opensource.microsoft.com/).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
|
||||
"translation_date": "2025-08-26T00:44:58+00:00",
|
||||
"source_file": "etc/CODE_OF_CONDUCT.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Microsoftov Kodeks ponašanja za otvoreni izvor
|
||||
|
||||
Ovaj projekt je usvojio [Microsoftov Kodeks ponašanja za otvoreni izvor](https://opensource.microsoft.com/codeofconduct/).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
|
||||
"translation_date": "2025-08-26T00:47:59+00:00",
|
||||
"source_file": "etc/CONTRIBUTING.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Doprinose
|
||||
|
||||
Ovaj projekt pozdravlja doprinose i prijedloge. Većina doprinosa zahtijeva da se složite s Ugovorom o licenci za suradnike (CLA) kojim izjavljujete da imate pravo, i da zaista dajete, prava za korištenje vašeg doprinosa. Za detalje posjetite https://cla.microsoft.com.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
|
||||
"translation_date": "2025-08-26T00:51:04+00:00",
|
||||
"source_file": "etc/Mindmap.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# AI
|
||||
|
||||
## [Uvod u AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
|
||||
"translation_date": "2025-08-26T00:43:56+00:00",
|
||||
"source_file": "etc/SUPPORT.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Podrška
|
||||
|
||||
## Kako prijaviti probleme i dobiti pomoć
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
|
||||
"translation_date": "2025-08-26T00:46:23+00:00",
|
||||
"source_file": "etc/TRANSLATIONS.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Sudjelujte u prevođenju lekcija
|
||||
|
||||
Pozivamo vas da sudjelujete u prevođenju lekcija iz ovog kurikuluma!
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
|
||||
"translation_date": "2025-08-26T00:54:39+00:00",
|
||||
"source_file": "etc/quiz-app/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Kvizovi
|
||||
|
||||
Ovi kvizovi su uvodni i završni kvizovi za AI kurikulum na https://aka.ms/ai-beginners
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
|
||||
"translation_date": "2025-10-03T11:34:49+00:00",
|
||||
"source_file": "examples/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Primjeri umjetne inteligencije za početnike
|
||||
|
||||
Dobrodošli! Ovaj direktorij sadrži jednostavne, samostalne primjere koji će vam pomoći da započnete s umjetnom inteligencijom i strojnim učenjem. Svaki primjer je osmišljen tako da bude prilagođen početnicima, uz detaljne komentare i objašnjenja korak po korak.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a094ef9927883de1cfcee51dbd143381",
|
||||
"translation_date": "2025-08-26T00:39:34+00:00",
|
||||
"source_file": "lessons/0-course-setup/for-teachers.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Za edukatore
|
||||
|
||||
Želite li koristiti ovaj kurikulum u svojoj učionici? Slobodno ga koristite!
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
|
||||
"translation_date": "2026-01-16T06:04:58+00:00",
|
||||
"source_file": "lessons/0-course-setup/how-to-run.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Kako pokrenuti kod
|
||||
|
||||
Ovaj nastavni plan sadrži mnogo izvršnih primjera i laboratorijskih vježbi koje želite pokrenuti. Da biste to učinili, morate imati mogućnost izvršavanja Python koda u Jupyter bilježnicama koje su dio ovog nastavnog plana. Imate nekoliko opcija za pokretanje koda:
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
|
||||
"translation_date": "2025-12-12T20:20:45+00:00",
|
||||
"source_file": "lessons/0-course-setup/setup.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Početak s ovim kurikulumom
|
||||
|
||||
## Jeste li student?
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
|
||||
"translation_date": "2025-11-18T22:08:05+00:00",
|
||||
"source_file": "lessons/1-Intro/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Uvod u AI
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
|
||||
"translation_date": "2025-11-18T22:09:17+00:00",
|
||||
"source_file": "lessons/1-Intro/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Game Jam
|
||||
|
||||
Igre su područje koje je snažno pod utjecajem razvoja umjetne inteligencije (AI) i strojnog učenja (ML). U ovom zadatku napišite kratki rad o igri koja vam se sviđa, a koja je bila pod utjecajem evolucije AI-a. Trebala bi biti dovoljno stara da je bila pod utjecajem različitih vrsta računalnih sustava. Dobar primjer su šah ili Go, ali također razmotrite videoigre poput Ponga ili Pac-Mana. Napišite esej koji raspravlja o prošlosti, sadašnjosti i budućnosti igre u kontekstu AI-a.
|
||||
|
|
|
|||
|
|
@ -1,15 +1,6 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
|
||||
"translation_date": "2026-01-16T06:05:20+00:00",
|
||||
"source_file": "lessons/2-Symbolic/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Predstavljanje znanja i stručni sustavi
|
||||
|
||||
|
||||
|
||||
|
||||
> Sketchnote autora [Tomomi Imura](https://twitter.com/girlie_mac)
|
||||
|
||||
|
|
@ -41,7 +32,7 @@ Najčešće ne definiramo strogo znanje, već ga usklađujemo s drugim povezanim
|
|||
|
||||
Dakle, problem **predstavljanja znanja** je pronaći neki učinkovit način predstavljanja znanja unutar računala u obliku podataka kako bi bilo automatski upotrebljivo. To se može promatrati kao spektar:
|
||||
|
||||
|
||||
|
||||
|
||||
> Slika autora [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
|
|
@ -94,7 +85,7 @@ Sintaksa bloka | Indent | | |
|
|||
|
||||
Jedan od ranih uspjeha simboličke AI bili su tzv. **stručni sustavi** - računalni sustavi dizajnirani da djeluju kao stručnjak u nekom ograničenom području problema. Temeljili su se na **bazi znanja** izvučenoj od jednog ili više ljudskih stručnjaka i sadržavali su **zaključni stroj** koji je vršio zaključivanje na temelju nje.
|
||||
|
||||
 | 
|
||||
 | 
|
||||
---------------------------------------------|------------------------------------------------
|
||||
Pojednostavljena struktura ljudskog živčanog sustava | Arhitektura sustava temeljenog na znanju
|
||||
|
||||
|
|
@ -106,7 +97,7 @@ Stručni sustavi se grade poput ljudskog sustava zaključivanja, koji sadrži **
|
|||
|
||||
Kao primjer, razmotrimo sljedeći stručni sustav za određivanje životinje na temelju fizičkih karakteristika:
|
||||
|
||||
|
||||
|
||||
|
||||
> Slika autora [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a057a8604f3976c3e309884453f1fad0",
|
||||
"translation_date": "2025-08-26T00:34:18+00:00",
|
||||
"source_file": "lessons/2-Symbolic/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Izgradnja ontologije
|
||||
|
||||
Izgradnja baze znanja temelji se na kategorizaciji modela koji predstavlja činjenice o nekoj temi. Odaberite temu - poput osobe, mjesta ili stvari - i zatim izradite model te teme. Koristite neke od tehnika i strategija izgradnje modela opisane u ovoj lekciji. Primjer bi bio stvaranje ontologije dnevne sobe s namještajem, rasvjetom i slično. Kako se dnevna soba razlikuje od kuhinje? Kupaonice? Kako znate da je to dnevna soba, a ne blagovaonica? Koristite [Protégé](https://protege.stanford.edu/) za izradu svoje ontologije.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
|
||||
"translation_date": "2025-09-23T14:56:42+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Uvod u neuronske mreže: Perceptron
|
||||
|
||||
## [Kviz prije predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/5)
|
||||
|
|
@ -15,7 +6,7 @@ Jedan od prvih pokušaja implementacije nečega sličnog modernoj neuronskoj mre
|
|||
|
||||
| | |
|
||||
|--------------|-----------|
|
||||
|<img src='images/Rosenblatt-wikipedia.jpg' alt='Frank Rosenblatt'/> | <img src='images/Mark_I_perceptron_wikipedia.jpg' alt='The Mark 1 Perceptron' />|
|
||||
|<img src='../../../../../translated_images/hr/Rosenblatt-wikipedia.294821b285ac796d.webp' alt='Frank Rosenblatt'/> | <img src='../../../../../translated_images/hr/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp' alt='The Mark 1 Perceptron' />|
|
||||
|
||||
> Slike [s Wikipedije](https://en.wikipedia.org/wiki/Perceptron)
|
||||
|
||||
|
|
@ -34,7 +25,7 @@ y(x) = f(w<sup>T</sup>x)
|
|||
gdje je f funkcija aktivacije koraka
|
||||
|
||||
<!-- img src="http://www.sciweavers.org/tex2img.php?eq=f%28x%29%20%3D%20%5Cbegin%7Bcases%7D%0A%20%20%20%20%20%20%20%20%20%2B1%20%26%20x%20%5Cgeq%200%20%5C%5C%0A%20%20%20%20%20%20%20%20%20-1%20%26%20x%20%3C%200%0A%20%20%20%20%20%20%20%5Cend%7Bcases%7D%20%5C%5C%0A&bc=White&fc=Black&im=jpg&fs=12&ff=arev&edit=0" align="center" border="0" alt="f(x) = \begin{cases} +1 & x \geq 0 \\ -1 & x < 0 \end{cases} \\" width="154" height="50" / -->
|
||||
<img src="images/activation-func.png"/>
|
||||
<img src="../../../../../translated_images/hr/activation-func.b4924007c7ce7764.webp"/>
|
||||
|
||||
## Treniranje perceptrona
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
|
||||
"translation_date": "2025-08-30T07:06:15+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Višeklasna klasifikacija s perceptronom
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
|
||||
"translation_date": "2025-09-23T14:56:13+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Uvod u neuronske mreže. Višeslojni perceptron
|
||||
|
||||
U prethodnom dijelu naučili ste o najjednostavnijem modelu neuronske mreže - jednoslojnom perceptronu, linearnom modelu za klasifikaciju s dvije klase.
|
||||
|
|
@ -65,7 +56,7 @@ Algoritam gradijentnog spuštanja ostaje isti, ali postaje teže izračunati gra
|
|||
|
||||
Primijetite da je lijevi dio svih tih izraza isti, i stoga možemo učinkovito izračunavati derivacije počevši od funkcije gubitka i idući "unatrag" kroz računski graf. Stoga se metoda treniranja višeslojnog perceptrona naziva **povratna propagacija**, ili 'backprop'.
|
||||
|
||||
<img alt="računski graf" src="images/ComputeGraphGrad.png"/>
|
||||
<img alt="računski graf" src="../../../../../translated_images/hr/ComputeGraphGrad.4626252c0de03507.webp"/>
|
||||
|
||||
> TODO: citiranje slike
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
|
||||
"translation_date": "2025-08-25T23:49:22+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Klasifikacija MNIST-a s Našim Okvirom
|
||||
|
||||
Laboratorijska vježba iz [AI za Početnike Kurikulum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ddd216f558a255260a9374008002c971",
|
||||
"translation_date": "2025-09-23T14:56:58+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Okviri za neuronske mreže
|
||||
|
||||
Kao što smo već naučili, da bismo učinkovito trenirali neuronske mreže, moramo učiniti dvije stvari:
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "e452d897efb9a89700f41021834cf6e5",
|
||||
"translation_date": "2025-08-25T23:55:54+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Klasifikacija s PyTorch/TensorFlow
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
|
||||
"translation_date": "2025-10-03T12:53:55+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Uvod u neuronske mreže
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "feeca98225cb420afc89415f24f63d92",
|
||||
"translation_date": "2025-09-23T14:51:44+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Uvod u računalni vid
|
||||
|
||||
[Računalni vid](https://wikipedia.org/wiki/Computer_vision) je disciplina čiji je cilj omogućiti računalima da steknu visok nivo razumijevanja digitalnih slika. Ovo je prilično široka definicija jer *razumijevanje* može značiti mnogo različitih stvari, uključujući pronalaženje objekta na slici (**detekcija objekata**), razumijevanje što se događa (**detekcija događaja**), opisivanje slike tekstom ili rekonstrukciju scene u 3D. Postoje i posebni zadaci vezani uz slike ljudi: procjena dobi i emocija, detekcija i identifikacija lica te procjena 3D poze, da spomenemo samo neke.
|
||||
|
|
@ -115,7 +106,7 @@ Pročitajte više o optičkom toku [u ovom odličnom vodiču](https://learnopenc
|
|||
|
||||
U ovom laboratoriju snimit ćete video s jednostavnim gestama, a vaš cilj je izdvojiti pokrete gore/dolje/lijevo/desno pomoću optičkog toka.
|
||||
|
||||
<img src="images/palm-movement.png" width="30%" alt="Okvir pokreta dlana"/>
|
||||
<img src="../../../../../translated_images/hr/palm-movement.341495f0e9c47da3.webp" width="30%" alt="Okvir pokreta dlana"/>
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "3d53d6409f80970f7281a45dee35328a",
|
||||
"translation_date": "2025-08-25T23:05:52+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Otkrivanje pokreta pomoću optičkog toka
|
||||
|
||||
Laboratorijska vježba iz [AI za početnike kurikuluma](https://aka.ms/ai-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
|
||||
"translation_date": "2025-09-23T14:51:00+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Dobro poznate CNN arhitekture
|
||||
|
||||
### VGG-16
|
||||
|
|
@ -25,7 +16,7 @@ Kao što možete vidjeti, VGG slijedi tradicionalnu piramidalnu arhitekturu, koj
|
|||
|
||||
ResNet je obitelj modela koju je predložio Microsoft Research 2015. godine. Glavna ideja ResNet-a je korištenje **rezidualnih blokova**:
|
||||
|
||||
<img src="images/resnet-block.png" width="300"/>
|
||||
<img src="../../../../../translated_images/hr/resnet-block.aba4ccbcc0944434.webp" width="300"/>
|
||||
|
||||
> Slika preuzeta iz [ovog rada](https://arxiv.org/pdf/1512.03385.pdf)
|
||||
|
||||
|
|
@ -37,7 +28,7 @@ Ovu mrežu možete zamisliti i kao mrežu koja prilagođava svoju složenost dat
|
|||
|
||||
Google Inception arhitektura ide korak dalje i gradi svaki sloj mreže kao kombinaciju nekoliko različitih putova:
|
||||
|
||||
<img src="images/inception.png" width="400"/>
|
||||
<img src="../../../../../translated_images/hr/inception.a6605b85bcbc6f52.webp" width="400"/>
|
||||
|
||||
> Slika preuzeta s [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a560d5b845962cf33dc102266e409568",
|
||||
"translation_date": "2025-09-23T14:50:40+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Konvolucijske neuronske mreže
|
||||
|
||||
Već smo vidjeli da su neuronske mreže prilično dobre u obradi slika, pa čak i perceptron s jednim slojem može prepoznati rukom pisane znamenke iz MNIST skupa podataka s razumnom točnošću. Međutim, MNIST skup podataka je vrlo specifičan, jer su sve znamenke centrirane unutar slike, što zadatak čini jednostavnijim.
|
||||
|
|
@ -24,7 +15,7 @@ Za izdvajanje uzoraka koristit ćemo pojam **konvolucijskih filtera**. Kao što
|
|||
|
||||
Na primjer, ako primijenimo 3x3 vertikalni i horizontalni rubni filter na znamenke iz MNIST skupa podataka, možemo dobiti istaknute dijelove (npr. visoke vrijednosti) gdje postoje vertikalni i horizontalni rubovi u našoj originalnoj slici. Tako se ta dva filtera mogu koristiti za "traženje" rubova. Slično tome, možemo dizajnirati različite filtere za traženje drugih niskorazinskih uzoraka:
|
||||
|
||||
<img src="images/lmfilters.jpg" width="500" align="center"/>
|
||||
<img src="../../../../../translated_images/hr/lmfilters.ea9e4868a82cf74c.webp" width="500" align="center"/>
|
||||
|
||||
> Slika: [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "b70fcf7fcee862990f848c679090943f",
|
||||
"translation_date": "2025-10-03T14:58:11+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Klasifikacija lica kućnih ljubimaca
|
||||
|
||||
Laboratorijska vježba iz [AI za početnike](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
|
||||
"translation_date": "2025-09-23T14:51:17+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Pretrenirane mreže i prijenos učenja
|
||||
|
||||
Treniranje CNN-a može zahtijevati puno vremena, a za taj zadatak potrebno je mnogo podataka. Međutim, velik dio vremena troši se na učenje najboljih niskorazinskih filtera koje mreža može koristiti za izdvajanje uzoraka iz slika. Postavlja se prirodno pitanje - možemo li koristiti neuronsku mrežu treniranu na jednom skupu podataka i prilagoditi je za klasifikaciju različitih slika bez potrebe za potpunim procesom treniranja?
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
|
||||
"translation_date": "2025-08-25T23:14:14+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Trikovi za treniranje dubokog učenja
|
||||
|
||||
Kako neuronske mreže postaju dublje, proces njihovog treniranja postaje sve izazovniji. Jedan od glavnih problema su takozvani [nestajući gradijenti](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) ili [eksplodirajući gradijenti](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Ovaj članak](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) pruža dobar uvod u te probleme.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
|
||||
"translation_date": "2025-08-25T23:17:08+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Klasifikacija Oxford kućnih ljubimaca koristeći prijenosno učenje
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
|
||||
"translation_date": "2025-09-23T14:52:43+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Autoenkoderi
|
||||
|
||||
Kod treniranja CNN-a, jedan od problema je potreba za velikom količinom označenih podataka. U slučaju klasifikacije slika, potrebno je razvrstati slike u različite klase, što zahtijeva ručni rad.
|
||||
|
|
@ -46,7 +37,7 @@ Ukratko:
|
|||
* Uzorkujemo vektor `sample` iz distribucije N(z<sub>mean</sub>,exp(z<sub>log\_sigma</sub>))
|
||||
* Dekoder pokušava dekodirati originalnu sliku koristeći `sample` kao ulazni vektor
|
||||
|
||||
<img src="images/vae.png" width="50%">
|
||||
<img src="../../../../../translated_images/hr/vae.464c465a5b6a9e25.webp" width="50%">
|
||||
|
||||
> Slika iz [ovog blog posta](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) autora Isaaka Dykemana
|
||||
|
||||
|
|
@ -57,13 +48,13 @@ Varijacijski autoenkoderi koriste složenu funkciju gubitka koja se sastoji od d
|
|||
|
||||
Jedna važna prednost VAE-a je da nam omogućuju relativno lako generiranje novih slika, jer znamo iz koje distribucije uzorkovati latentne vektore. Na primjer, ako treniramo VAE s 2D latentnim vektorom na MNIST datasetu, možemo zatim mijenjati komponente latentnog vektora kako bismo dobili različite brojeve:
|
||||
|
||||
<img alt="vaemnist" src="images/vaemnist.png" width="50%"/>
|
||||
<img alt="vaemnist" src="../../../../../translated_images/hr/vaemnist.cab9e602dc08dc50.webp" width="50%"/>
|
||||
|
||||
> Slika autora [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
Primijetite kako se slike stapaju jedna u drugu, dok počinjemo dobivati latentne vektore iz različitih dijelova latentnog prostora parametara. Također možemo vizualizirati ovaj prostor u 2D:
|
||||
|
||||
<img alt="vaemnist cluster" src="images/vaemnist-diag.png" width="50%"/>
|
||||
<img alt="vaemnist cluster" src="../../../../../translated_images/hr/vaemnist-diag.694315f775d5d666.webp" width="50%"/>
|
||||
|
||||
> Slika autora [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
|
||||
"translation_date": "2025-09-23T14:53:28+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Generativne suparničke mreže
|
||||
|
||||
U prethodnom dijelu naučili smo o **generativnim modelima**: modelima koji mogu generirati nove slike slične onima iz skupa za treniranje. VAE je bio dobar primjer generativnog modela.
|
||||
|
|
@ -17,7 +8,7 @@ Međutim, ako pokušamo generirati nešto zaista značajno, poput slike visoke r
|
|||
|
||||
Glavna ideja GAN-a je imati dvije neuronske mreže koje se treniraju jedna protiv druge:
|
||||
|
||||
<img src="images/gan_architecture.png" width="70%"/>
|
||||
<img src="../../../../../translated_images/hr/gan_architecture.8f3a5ab62b8d5d69.webp" width="70%"/>
|
||||
|
||||
> Slika: [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
|
|
@ -41,7 +32,7 @@ Generator je malo složeniji. Možete ga smatrati obrnutim diskriminatorom. Poč
|
|||
|
||||
> ✅ Budući da je konvolucijski sloj implementiran kao linearni filter koji prolazi kroz sliku, dekonvolucija je u suštini slična konvoluciji i može se implementirati koristeći istu logiku sloja.
|
||||
|
||||
<img src="images/gan_arch_detail.png" width="70%"/>
|
||||
<img src="../../../../../translated_images/hr/gan_arch_detail.46b95fd366f8e543.webp" width="70%"/>
|
||||
|
||||
> Slika: [Dmitry Soshnikov](http://soshnikov.com)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
|
||||
"translation_date": "2025-09-23T14:52:10+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Detekcija objekata
|
||||
|
||||
Modeli za klasifikaciju slika s kojima smo se dosad susretali uzimaju sliku i proizvode kategorijski rezultat, poput klase 'broj' u MNIST problemu. Međutim, u mnogim slučajevima ne želimo samo znati da slika prikazuje objekte – želimo odrediti njihovu točnu lokaciju. Upravo to je cilj **detekcije objekata**.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
|
||||
"translation_date": "2025-08-25T22:50:29+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Detekcija glava koristeći Hollywood Heads Dataset
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
|
||||
"translation_date": "2025-09-23T14:53:13+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Segmentacija
|
||||
|
||||
Ranije smo učili o Detekciji objekata, koja nam omogućuje lociranje objekata na slici predviđanjem njihovih *bounding boxova*. Međutim, za neke zadatke ne trebamo samo bounding boxove, već i precizniju lokalizaciju objekata. Taj zadatak zove se **segmentacija**.
|
||||
|
|
@ -20,7 +11,7 @@ Segmentacija se može promatrati kao **klasifikacija piksela**, gdje za **svaki*
|
|||
|
||||
Kod segmentacije instanci, ove ovce su različiti objekti, dok kod semantičke segmentacije sve ovce pripadaju jednoj klasi.
|
||||
|
||||
<img src="images/instance_vs_semantic.jpeg" width="50%">
|
||||
<img src="../../../../../translated_images/hr/instance_vs_semantic.eee9812bebf8cd45.webp" width="50%">
|
||||
|
||||
> Slika iz [ovog blog posta](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
|
||||
|
||||
|
|
@ -29,7 +20,7 @@ Postoje različite neuronske arhitekture za segmentaciju, ali sve imaju istu str
|
|||
* **Encoder** izvlači značajke iz ulazne slike.
|
||||
* **Decoder** transformira te značajke u **masku slike**, iste veličine i s brojem kanala koji odgovara broju klasa.
|
||||
|
||||
<img src="images/segm.png" width="80%">
|
||||
<img src="../../../../../translated_images/hr/segm.92442f2cb42ff4fa.webp" width="80%">
|
||||
|
||||
> Slika iz [ove publikacije](https://arxiv.org/pdf/2001.05566.pdf)
|
||||
|
||||
|
|
@ -43,7 +34,7 @@ U ovoj lekciji vidjet ćemo segmentaciju u praksi treniranjem mreže za prepozna
|
|||
|
||||
> ✅ Ova tehnika je posebno prikladna za ovu vrstu medicinskog snimanja, ali koje druge stvarne primjene možete zamisliti?
|
||||
|
||||
<img alt="navi" src="images/navi.png"/>
|
||||
<img alt="navi" src="../../../../../translated_images/hr/navi.2f20b727910110ea.webp"/>
|
||||
|
||||
> Slika iz PH<sup>2</sup> baze podataka
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
|
||||
"translation_date": "2025-08-25T22:37:34+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Segmentacija ljudskog tijela
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
|
||||
"translation_date": "2025-08-25T22:28:11+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Računalni vid
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
|
||||
"translation_date": "2025-09-23T15:00:14+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Predstavljanje teksta kao tenzora
|
||||
|
||||
## [Kviz prije predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/25)
|
||||
|
|
@ -25,7 +16,7 @@ Naš cilj bit će klasificirati vijest u jednu od kategorija na temelju teksta.
|
|||
|
||||
Ako želimo rješavati zadatke obrade prirodnog jezika (NLP) pomoću neuronskih mreža, trebamo način za predstavljanje teksta kao tenzora. Računala već predstavljaju tekstualne znakove kao brojeve koji se mapiraju na fontove na vašem ekranu koristeći kodiranja poput ASCII ili UTF-8.
|
||||
|
||||
<img alt="Slika koja prikazuje dijagram mapiranja znaka na ASCII i binarnu reprezentaciju" src="images/ascii-character-map.png" width="50%"/>
|
||||
<img alt="Slika koja prikazuje dijagram mapiranja znaka na ASCII i binarnu reprezentaciju" src="../../../../../translated_images/hr/ascii-character-map.18ed6aa7f3b0a7ff.webp" width="50%"/>
|
||||
|
||||
> [Izvor slike](https://www.seobility.net/en/wiki/ASCII)
|
||||
|
||||
|
|
@ -48,7 +39,7 @@ U nekim slučajevima možemo razmotriti korištenje tri-grama -- kombinacija tri
|
|||
|
||||
Kod rješavanja zadataka poput klasifikacije teksta, trebamo biti u mogućnosti predstaviti tekst jednim vektorom fiksne veličine, koji ćemo koristiti kao ulaz za završni gusti klasifikator. Jedan od najjednostavnijih načina za to je kombiniranje svih pojedinačnih reprezentacija riječi, npr. njihovim zbrajanjem. Ako zbrojimo one-hot kodiranja svake riječi, dobit ćemo vektor frekvencija, koji pokazuje koliko se puta svaka riječ pojavljuje unutar teksta. Takva reprezentacija teksta naziva se **bag-of-words** (BoW).
|
||||
|
||||
<img src="images/bow.png" width="90%"/>
|
||||
<img src="../../../../../translated_images/hr/bow.3811869cff59368d.webp" width="90%"/>
|
||||
|
||||
> Slika autora
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
|
||||
"translation_date": "2025-08-25T21:54:49+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Zadatak: Bilježnice
|
||||
|
||||
Koristeći bilježnice povezane s ovom lekcijom (bilo PyTorch ili TensorFlow verziju), ponovno ih pokrenite koristeći vlastiti skup podataka, možda neki s Kagglea, uz odgovarajuće navođenje izvora. Prepravite bilježnicu kako biste istaknuli vlastite zaključke. Isprobajte neke inovativne skupove podataka koji bi mogli biti iznenađujući, poput [ovog o viđenjima NLO-a](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) od NUFORC-a.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
|
||||
"translation_date": "2025-09-23T14:59:50+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Ugrađivanja
|
||||
|
||||
## [Pre-lecture kviz](https://ff-quizzes.netlify.app/en/ai/quiz/27)
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
|
||||
"translation_date": "2025-08-25T21:42:58+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Zadatak: Bilježnice
|
||||
|
||||
Koristeći bilježnice povezane s ovom lekcijom (bilo PyTorch ili TensorFlow verziju), ponovno ih pokrenite koristeći vlastiti skup podataka, možda neki s Kagglea, uz odgovarajuće navođenje izvora. Prepravite bilježnicu kako biste istaknuli vlastite zaključke. Isprobajte drugačiju vrstu skupa podataka i dokumentirajte svoja otkrića, koristeći tekst poput [ovih stihova Beatlesa](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
|
||||
"translation_date": "2025-09-23T14:57:57+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Modeliranje jezika
|
||||
|
||||
Semantičke ugrađene reprezentacije, poput Word2Vec i GloVe, zapravo su prvi korak prema **modeliranju jezika** - stvaranju modela koji na neki način *razumiju* (ili *predstavljaju*) prirodu jezika.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
|
||||
"translation_date": "2025-08-25T21:58:39+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Treniranje Skip-Gram modela
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "e2273cc150380a5e191903cea858f021",
|
||||
"translation_date": "2025-09-23T14:59:20+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Rekurentne neuronske mreže
|
||||
|
||||
## [Kviz prije predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/31)
|
||||
|
|
@ -31,7 +22,7 @@ Pogledajmo kako je organizirana jednostavna RNN ćelija. Ona prihvaća prethodno
|
|||
|
||||
Jednostavna RNN ćelija ima dvije matrice težina unutar sebe: jedna transformira ulazni simbol (nazovimo je W), a druga transformira ulazno stanje (H). U ovom slučaju izlaz mreže se računa kao σ(W×X<sub>i</sub>+H×S<sub>i-1</sub>+b), gdje je σ funkcija aktivacije, a b dodatna pristranost.
|
||||
|
||||
<img alt="Anatomija RNN ćelije" src="images/rnn-anatomy.png" width="50%"/>
|
||||
<img alt="Anatomija RNN ćelije" src="../../../../../translated_images/hr/rnn-anatomy.79ee3f3920b3294b.webp" width="50%"/>
|
||||
|
||||
> Slika autora
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
|
||||
"translation_date": "2025-08-25T21:37:31+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Zadatak: Bilježnice
|
||||
|
||||
Koristeći bilježnice povezane s ovom lekcijom (bilo PyTorch ili TensorFlow verziju), ponovno ih pokrenite koristeći vlastiti skup podataka, možda jedan s Kagglea, uz odgovarajuće navođenje izvora. Prepravite bilježnicu kako biste istaknuli vlastite zaključke. Isprobajte drugačiju vrstu skupa podataka i dokumentirajte svoja otkrića, koristeći tekst poput [ovog Kaggle natjecateljskog skupa podataka o vremenskim tweetovima](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
|
||||
"translation_date": "2025-09-23T14:57:29+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Generativne mreže
|
||||
|
||||
## [Kviz prije predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/33)
|
||||
|
|
@ -36,7 +27,7 @@ Trenirat ćemo ovaj RNN da generira tekst korak po korak. Na svakom koraku uzet
|
|||
|
||||
Tijekom generiranja teksta (tijekom inferencije), počinjemo s nekim **poticajem**, koji se prosljeđuje kroz RNN ćelije kako bi se generiralo njegovo međustanje, a zatim iz tog stanja počinje generiranje. Generiramo jedan znak po jedan, prosljeđujemo stanje i generirani znak sljedećoj RNN ćeliji kako bismo generirali sljedeći znak, sve dok ne generiramo dovoljno znakova.
|
||||
|
||||
<img src="images/rnn-generate-inf.png" width="60%"/>
|
||||
<img src="../../../../../translated_images/hr/rnn-generate-inf.5168dc65e0370eea.webp" width="60%"/>
|
||||
|
||||
> Slika autora
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
|
||||
"translation_date": "2025-08-25T21:48:43+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Generiranje teksta na razini riječi pomoću RNN-a
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f335dfcb4a993920504c387973a36957",
|
||||
"translation_date": "2025-09-23T14:58:10+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Mehanizmi pažnje i transformeri
|
||||
|
||||
## [Pre-kviz predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/35)
|
||||
|
|
@ -56,7 +47,7 @@ Ideja pozicijskog kodiranja je sljedeća.
|
|||
* Ugrađivanje koje se trenira, slično ugrađivanju tokena. Ovo je pristup koji ovdje razmatramo. Primjenjujemo slojeve ugrađivanja na tokene i njihove pozicije, što rezultira vektorima ugrađivanja iste dimenzije, koje zatim zbrajamo.
|
||||
* Fiksna funkcija pozicijskog kodiranja, kako je predloženo u originalnom radu.
|
||||
|
||||
<img src="images/pos-embedding.png" width="50%"/>
|
||||
<img src="../../../../../translated_images/hr/pos-embedding.e41ce9b6cf6078af.webp" width="50%"/>
|
||||
|
||||
> Slika autora
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
|
||||
"translation_date": "2025-08-25T22:05:33+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Zadatak: Transformeri
|
||||
|
||||
Eksperimentirajte s Transformerima na HuggingFace! Isprobajte neke od skripti koje pružaju za rad s raznim modelima dostupnim na njihovoj stranici: https://huggingface.co/docs/transformers/run_scripts. Isprobajte jedan od njihovih skupova podataka, a zatim uvezite jedan svoj iz ovog kurikuluma ili s Kagglea i provjerite možete li generirati zanimljive tekstove. Izradite bilježnicu s vašim rezultatima.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "6522312ff835796ca34136a9462fafb2",
|
||||
"translation_date": "2025-09-23T14:59:00+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Prepoznavanje imenovanih entiteta
|
||||
|
||||
Do sada smo se uglavnom fokusirali na jedan NLP zadatak - klasifikaciju. Međutim, postoje i drugi NLP zadaci koji se mogu ostvariti pomoću neuronskih mreža. Jedan od tih zadataka je **[Prepoznavanje imenovanih entiteta](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), koji se bavi prepoznavanjem specifičnih entiteta unutar teksta, poput mjesta, imena osoba, vremenskih intervala, kemijskih formula i slično.
|
||||
|
|
@ -17,7 +8,7 @@ Do sada smo se uglavnom fokusirali na jedan NLP zadatak - klasifikaciju. Međuti
|
|||
|
||||
Pretpostavimo da želite razviti chatbot za prirodni jezik, sličan Amazon Alexi ili Google Asistentu. Inteligentni chatboti funkcioniraju tako da *razumiju* što korisnik želi, koristeći klasifikaciju teksta na ulaznoj rečenici. Rezultat te klasifikacije je takozvani **intencija**, koja određuje što chatbot treba učiniti.
|
||||
|
||||
<img alt="Bot NER" src="images/bot-ner.png" width="50%"/>
|
||||
<img alt="Bot NER" src="../../../../../translated_images/hr/bot-ner.4b09235dbb0ad275.webp" width="50%"/>
|
||||
|
||||
> Slika autora
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "032bda5068f543d6c1fcb30c34231461",
|
||||
"translation_date": "2025-08-25T22:15:11+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# NER
|
||||
|
||||
Laboratorijska vježba iz [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
|
||||
"translation_date": "2025-09-23T14:58:41+00:00",
|
||||
"source_file": "lessons/5-NLP/20-LangModels/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Pre-Trained Large Language Models
|
||||
|
||||
U svim našim prethodnim zadacima trenirali smo neuronsku mrežu da obavlja određeni zadatak koristeći označene skupove podataka. Kod velikih transformacijskih modela, poput BERT-a, koristimo jezično modeliranje u samonadziranom načinu rada kako bismo izgradili jezični model, koji se zatim specijalizira za specifične zadatke uz dodatnu obuku prilagođenu domeni. Međutim, pokazalo se da veliki jezični modeli mogu riješiti mnoge zadatke i bez IKAKVE obuke prilagođene domeni. Obitelj modela sposobnih za to naziva se **GPT**: Generativni unaprijed trenirani transformator.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
|
||||
"translation_date": "2025-08-25T21:29:43+00:00",
|
||||
"source_file": "lessons/5-NLP/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Obrada Prirodnog Jezika
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
|
||||
"translation_date": "2025-09-23T14:49:11+00:00",
|
||||
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Genetski algoritmi
|
||||
|
||||
## [Pre-kviz predavanja](https://ff-quizzes.netlify.app/en/ai/quiz/41)
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "04395657fc01648f8f70484d0e55ab67",
|
||||
"translation_date": "2025-09-23T14:50:11+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Duboko pojačano učenje
|
||||
|
||||
Pojačano učenje (RL) smatra se jednim od osnovnih paradigmi strojnog učenja, uz nadzirano učenje i nenadzirano učenje. Dok se u nadziranom učenju oslanjamo na skup podataka s poznatim ishodima, RL se temelji na **učenju kroz rad**. Na primjer, kada prvi put vidimo računalnu igru, počinjemo igrati, čak i bez poznavanja pravila, i ubrzo poboljšavamo svoje vještine samo kroz proces igranja i prilagođavanja ponašanja.
|
||||
|
|
@ -34,7 +25,7 @@ Vjerojatno ste svi vidjeli moderne uređaje za balansiranje poput *Segwaya* ili
|
|||
|
||||
Pojednostavljena verzija balansiranja poznata je kao problem **CartPole**. U svijetu CartPole-a imamo horizontalni klizač koji se može kretati lijevo ili desno, a cilj je balansirati vertikalni štap na vrhu klizača dok se kreće.
|
||||
|
||||
<img alt="cartpole" src="images/cartpole.png" width="200"/>
|
||||
<img alt="cartpole" src="../../../../../translated_images/hr/cartpole.f52a67f27e058170.webp" width="200"/>
|
||||
|
||||
Za stvaranje i korištenje ovog okruženja potrebno je nekoliko linija Python koda:
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
|
||||
"translation_date": "2025-08-25T23:36:02+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
## Okruženje
|
||||
|
||||
Okruženje Mountain Car sastoji se od automobila zarobljenog u dolini. Vaš cilj je iskočiti iz doline i doseći zastavu. Akcije koje možete poduzeti su ubrzavanje ulijevo, udesno ili ne raditi ništa. Možete promatrati položaj automobila duž x-osi i brzinu.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
|
||||
"translation_date": "2025-09-23T14:49:30+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Višeagentski sustavi
|
||||
|
||||
Jedan od mogućih načina postizanja inteligencije je takozvani **emergentni** (ili **sinergijski**) pristup, koji se temelji na činjenici da kombinirano ponašanje mnogih relativno jednostavnih agenata može rezultirati ukupno složenijim (ili inteligentnijim) ponašanjem sustava u cjelini. Teoretski, ovo se temelji na principima [kolektivne inteligencije](https://en.wikipedia.org/wiki/Collective_intelligence), [emergentizma](https://en.wikipedia.org/wiki/Global_brain) i [evolucijske kibernetike](https://en.wikipedia.org/wiki/Global_brain), koji tvrde da sustavi višeg nivoa dobivaju neku vrstu dodane vrijednosti kada se pravilno kombiniraju iz sustava nižeg nivoa (tzv. *princip prijelaza metasustava*).
|
||||
|
|
@ -60,7 +51,7 @@ Možete [preuzeti](https://ccl.northwestern.edu/netlogo/download.shtml) i instal
|
|||
|
||||
Sjajna stvar kod NetLoga je da sadrži biblioteku radnih modela koje možete isprobati. Idite na **File → Models Library**, i imate mnogo kategorija modela za odabir.
|
||||
|
||||
<img alt="NetLogo Models Library" src="images/NetLogo-ModelLib.png" width="60%"/>
|
||||
<img alt="NetLogo Models Library" src="../../../../../translated_images/hr/NetLogo-ModelLib.efe023afb4763c05.webp" width="60%"/>
|
||||
|
||||
> Snimka zaslona biblioteke modela Dmitryja Soshnikova
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
|
||||
"translation_date": "2025-08-25T23:29:29+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Zadatak za NetLogo
|
||||
|
||||
Odaberite jedan od modela iz NetLogo biblioteke i upotrijebite ga za simulaciju stvarne životne situacije što je moguće preciznije. Dobar primjer bio bi prilagoditi model Virus iz mape Alternative Visualizations kako bi pokazao kako se može koristiti za modeliranje širenja COVID-19. Možete li izraditi model koji oponaša stvarno širenje virusa?
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
|
||||
"translation_date": "2025-08-25T21:25:49+00:00",
|
||||
"source_file": "lessons/7-Ethics/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Etička i odgovorna umjetna inteligencija
|
||||
|
||||
Skoro ste završili ovaj tečaj i nadam se da sada jasno vidite da se umjetna inteligencija temelji na nizu formalnih matematičkih metoda koje nam omogućuju pronalaženje odnosa u podacima i treniranje modela za repliciranje nekih aspekata ljudskog ponašanja. U ovom trenutku povijesti smatramo umjetnu inteligenciju vrlo moćnim alatom za izdvajanje uzoraka iz podataka i primjenu tih uzoraka za rješavanje novih problema.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
|
||||
"translation_date": "2025-08-25T21:23:24+00:00",
|
||||
"source_file": "lessons/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Pregled
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "9c592c26aca16ca085d268c732284187",
|
||||
"translation_date": "2025-08-25T23:39:49+00:00",
|
||||
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# Multi-modalne mreže
|
||||
|
||||
Nakon uspjeha transformera u rješavanju zadataka obrade prirodnog jezika (NLP), iste ili slične arhitekture primijenjene su na zadatke računalnog vida. Sve je veći interes za izgradnju modela koji bi *kombinirali* sposobnosti vida i prirodnog jezika. Jedan od takvih pokušaja napravio je OpenAI, a naziva se CLIP i DALL.E.
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
|
||||
"translation_date": "2025-08-26T00:12:28+00:00",
|
||||
"source_file": "lessons/sketchnotes/LICENSE.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
Priznanje-Dijeljenje pod istim uvjetima 4.0 Međunarodna
|
||||
|
||||
=======================================================================
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "050b8bddebafba55b129414e6ab096ab",
|
||||
"translation_date": "2025-08-26T00:02:20+00:00",
|
||||
"source_file": "lessons/sketchnotes/README.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
Sve sketchnoteovi kurikuluma mogu se preuzeti ovdje.
|
||||
|
||||
🎨 Autor: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
|
||||
"translation_date": "2025-10-03T09:52:37+00:00",
|
||||
"source_file": "troubleshoot.md",
|
||||
"language_code": "hr"
|
||||
}
|
||||
-->
|
||||
# AI-For-Beginners Vodič za rješavanje problema
|
||||
|
||||
Ovaj vodič pomaže u rješavanju uobičajenih problema koji se javljaju prilikom korištenja ili doprinosa [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners) repozitoriju. Svaki problem uključuje pozadinu, simptome, objašnjenja i korak-po-korak rješenja.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,398 @@
|
|||
{
|
||||
"AGENTS.md": {
|
||||
"original_hash": "6b11a37115944252ab3ed04e358d830d",
|
||||
"translation_date": "2025-10-03T09:31:39+00:00",
|
||||
"source_file": "AGENTS.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"README.md": {
|
||||
"original_hash": "1984fc89dd304a8a33ab5584691a99aa",
|
||||
"translation_date": "2026-01-30T02:44:01+00:00",
|
||||
"source_file": "README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"SECURITY.md": {
|
||||
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
|
||||
"translation_date": "2025-08-25T21:22:35+00:00",
|
||||
"source_file": "SECURITY.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/CODE_OF_CONDUCT.md": {
|
||||
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
|
||||
"translation_date": "2025-08-26T00:45:17+00:00",
|
||||
"source_file": "etc/CODE_OF_CONDUCT.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/CONTRIBUTING.md": {
|
||||
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
|
||||
"translation_date": "2025-08-26T00:48:26+00:00",
|
||||
"source_file": "etc/CONTRIBUTING.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/Mindmap.md": {
|
||||
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
|
||||
"translation_date": "2025-08-26T00:52:27+00:00",
|
||||
"source_file": "etc/Mindmap.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/SUPPORT.md": {
|
||||
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
|
||||
"translation_date": "2025-08-26T00:44:14+00:00",
|
||||
"source_file": "etc/SUPPORT.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/TRANSLATIONS.md": {
|
||||
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
|
||||
"translation_date": "2025-08-26T00:46:49+00:00",
|
||||
"source_file": "etc/TRANSLATIONS.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"etc/quiz-app/README.md": {
|
||||
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
|
||||
"translation_date": "2025-08-26T00:55:41+00:00",
|
||||
"source_file": "etc/quiz-app/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"examples/README.md": {
|
||||
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
|
||||
"translation_date": "2025-10-03T11:35:15+00:00",
|
||||
"source_file": "examples/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/0-course-setup/for-teachers.md": {
|
||||
"original_hash": "a094ef9927883de1cfcee51dbd143381",
|
||||
"translation_date": "2025-08-26T00:40:07+00:00",
|
||||
"source_file": "lessons/0-course-setup/for-teachers.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/0-course-setup/how-to-run.md": {
|
||||
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
|
||||
"translation_date": "2026-01-16T06:16:07+00:00",
|
||||
"source_file": "lessons/0-course-setup/how-to-run.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/0-course-setup/setup.md": {
|
||||
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
|
||||
"translation_date": "2025-12-12T20:25:12+00:00",
|
||||
"source_file": "lessons/0-course-setup/setup.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/1-Intro/README.md": {
|
||||
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
|
||||
"translation_date": "2025-11-18T22:13:19+00:00",
|
||||
"source_file": "lessons/1-Intro/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/1-Intro/assignment.md": {
|
||||
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
|
||||
"translation_date": "2025-11-18T22:14:28+00:00",
|
||||
"source_file": "lessons/1-Intro/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/2-Symbolic/README.md": {
|
||||
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
|
||||
"translation_date": "2026-01-16T06:18:19+00:00",
|
||||
"source_file": "lessons/2-Symbolic/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/2-Symbolic/assignment.md": {
|
||||
"original_hash": "a057a8604f3976c3e309884453f1fad0",
|
||||
"translation_date": "2025-08-26T00:34:40+00:00",
|
||||
"source_file": "lessons/2-Symbolic/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/03-Perceptron/README.md": {
|
||||
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
|
||||
"translation_date": "2025-09-23T15:22:42+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
|
||||
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
|
||||
"translation_date": "2025-08-30T08:46:51+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
|
||||
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
|
||||
"translation_date": "2025-09-23T15:22:12+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
|
||||
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
|
||||
"translation_date": "2025-08-25T23:49:41+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/05-Frameworks/README.md": {
|
||||
"original_hash": "ddd216f558a255260a9374008002c971",
|
||||
"translation_date": "2025-09-23T15:23:03+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
|
||||
"original_hash": "e452d897efb9a89700f41021834cf6e5",
|
||||
"translation_date": "2025-08-25T23:56:22+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/3-NeuralNetworks/README.md": {
|
||||
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
|
||||
"translation_date": "2025-10-03T12:54:28+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/06-IntroCV/README.md": {
|
||||
"original_hash": "feeca98225cb420afc89415f24f63d92",
|
||||
"translation_date": "2025-09-23T15:15:24+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
|
||||
"original_hash": "3d53d6409f80970f7281a45dee35328a",
|
||||
"translation_date": "2025-08-25T23:06:15+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
|
||||
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
|
||||
"translation_date": "2025-09-23T15:14:34+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/README.md": {
|
||||
"original_hash": "a560d5b845962cf33dc102266e409568",
|
||||
"translation_date": "2025-09-23T15:14:13+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
|
||||
"original_hash": "b70fcf7fcee862990f848c679090943f",
|
||||
"translation_date": "2025-10-03T14:58:29+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/README.md": {
|
||||
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
|
||||
"translation_date": "2025-09-23T15:14:56+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
|
||||
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
|
||||
"translation_date": "2025-08-25T23:15:43+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
|
||||
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
|
||||
"translation_date": "2025-08-25T23:17:32+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/09-Autoencoders/README.md": {
|
||||
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
|
||||
"translation_date": "2025-09-23T15:17:12+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/10-GANs/README.md": {
|
||||
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
|
||||
"translation_date": "2025-09-23T15:18:19+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/11-ObjectDetection/README.md": {
|
||||
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
|
||||
"translation_date": "2025-09-23T15:16:34+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
|
||||
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
|
||||
"translation_date": "2025-08-25T22:51:01+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/12-Segmentation/README.md": {
|
||||
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
|
||||
"translation_date": "2025-09-23T15:17:51+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
|
||||
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
|
||||
"translation_date": "2025-08-25T22:38:00+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/4-ComputerVision/README.md": {
|
||||
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
|
||||
"translation_date": "2025-08-25T22:28:30+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/13-TextRep/README.md": {
|
||||
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
|
||||
"translation_date": "2025-09-23T15:26:49+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/13-TextRep/assignment.md": {
|
||||
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
|
||||
"translation_date": "2025-08-25T21:55:08+00:00",
|
||||
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/14-Embeddings/README.md": {
|
||||
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
|
||||
"translation_date": "2025-09-23T15:26:21+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/14-Embeddings/assignment.md": {
|
||||
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
|
||||
"translation_date": "2025-08-25T21:43:16+00:00",
|
||||
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/15-LanguageModeling/README.md": {
|
||||
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
|
||||
"translation_date": "2025-09-23T15:24:05+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/15-LanguageModeling/lab/README.md": {
|
||||
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
|
||||
"translation_date": "2025-08-25T21:59:05+00:00",
|
||||
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/16-RNN/README.md": {
|
||||
"original_hash": "e2273cc150380a5e191903cea858f021",
|
||||
"translation_date": "2025-09-23T15:25:46+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/16-RNN/assignment.md": {
|
||||
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
|
||||
"translation_date": "2025-08-25T21:37:49+00:00",
|
||||
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/17-GenerativeNetworks/README.md": {
|
||||
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
|
||||
"translation_date": "2025-09-23T15:23:40+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
|
||||
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
|
||||
"translation_date": "2025-08-25T21:49:02+00:00",
|
||||
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/18-Transformers/README.md": {
|
||||
"original_hash": "f335dfcb4a993920504c387973a36957",
|
||||
"translation_date": "2025-09-23T15:24:18+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/18-Transformers/assignment.md": {
|
||||
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
|
||||
"translation_date": "2025-08-25T22:05:50+00:00",
|
||||
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/19-NER/README.md": {
|
||||
"original_hash": "6522312ff835796ca34136a9462fafb2",
|
||||
"translation_date": "2025-09-23T15:25:20+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/19-NER/lab/README.md": {
|
||||
"original_hash": "032bda5068f543d6c1fcb30c34231461",
|
||||
"translation_date": "2025-08-25T22:15:56+00:00",
|
||||
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/20-LangModels/README.md": {
|
||||
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
|
||||
"translation_date": "2025-09-23T15:24:55+00:00",
|
||||
"source_file": "lessons/5-NLP/20-LangModels/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/5-NLP/README.md": {
|
||||
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
|
||||
"translation_date": "2025-08-25T21:31:03+00:00",
|
||||
"source_file": "lessons/5-NLP/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/6-Other/21-GeneticAlgorithms/README.md": {
|
||||
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
|
||||
"translation_date": "2025-09-23T15:12:25+00:00",
|
||||
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/6-Other/22-DeepRL/README.md": {
|
||||
"original_hash": "04395657fc01648f8f70484d0e55ab67",
|
||||
"translation_date": "2025-09-23T15:13:39+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/6-Other/22-DeepRL/lab/README.md": {
|
||||
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
|
||||
"translation_date": "2025-08-25T23:36:21+00:00",
|
||||
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/6-Other/23-MultiagentSystems/README.md": {
|
||||
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
|
||||
"translation_date": "2025-09-23T15:12:50+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/6-Other/23-MultiagentSystems/assignment.md": {
|
||||
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
|
||||
"translation_date": "2025-08-25T23:29:46+00:00",
|
||||
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/7-Ethics/README.md": {
|
||||
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
|
||||
"translation_date": "2025-08-25T21:26:48+00:00",
|
||||
"source_file": "lessons/7-Ethics/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/README.md": {
|
||||
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
|
||||
"translation_date": "2025-08-25T21:23:39+00:00",
|
||||
"source_file": "lessons/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/X-Extras/X1-MultiModal/README.md": {
|
||||
"original_hash": "9c592c26aca16ca085d268c732284187",
|
||||
"translation_date": "2025-08-25T23:41:01+00:00",
|
||||
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/sketchnotes/LICENSE.md": {
|
||||
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
|
||||
"translation_date": "2025-08-26T00:18:10+00:00",
|
||||
"source_file": "lessons/sketchnotes/LICENSE.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"lessons/sketchnotes/README.md": {
|
||||
"original_hash": "050b8bddebafba55b129414e6ab096ab",
|
||||
"translation_date": "2025-08-26T00:02:36+00:00",
|
||||
"source_file": "lessons/sketchnotes/README.md",
|
||||
"language_code": "my"
|
||||
},
|
||||
"troubleshoot.md": {
|
||||
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
|
||||
"translation_date": "2025-10-03T09:53:41+00:00",
|
||||
"source_file": "troubleshoot.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
}
|
||||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "6b11a37115944252ab3ed04e358d830d",
|
||||
"translation_date": "2025-10-03T09:31:39+00:00",
|
||||
"source_file": "AGENTS.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# AGENTS.md
|
||||
|
||||
## ပရောဂျက်အကျဉ်းချုပ်
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "85102ce4bfab31103e99dc8ca2e2f181",
|
||||
"translation_date": "2026-01-16T06:13:22+00:00",
|
||||
"source_file": "README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
|
||||
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
|
||||
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
|
||||
|
|
@ -21,158 +12,162 @@ CO_OP_TRANSLATOR_METADATA:
|
|||
|
||||
[](https://discord.gg/nTYy5BXMWG)
|
||||
|
||||
# စတင်လေ့လာသူများအတွက် အတုယူမှုအင်တဲလီဂျင့် - သင်ရိုးညွှန်းတမ်း
|
||||
# လူသစ်များအတွက် အတုယူစက်ရုပ် - ပညာသင်အစီအစဉ်
|
||||
|
||||
||
|
||||
||
|
||||
|:---:|
|
||||
| စတင်လေ့လာသူများအတွက် အတုယူမှုအင်တဲလီဂျင့် - _Sketchnote များကို [@girlie_mac](https://twitter.com/girlie_mac) မှဖန်တီးသည်_ |
|
||||
| လူသစ်များအတွက် AI - _Sketchnote by [@girlie_mac](https://twitter.com/girlie_mac)_ |
|
||||
|
||||
ကျွန်ုပ်တို့ရဲ့ ၁၂ ပတ်၊ ၂၄ မိနစ် သင်ရိုးညွှန်းတမ်းဖြင့် **အတုယူမှုအင်တဲလီဂျင့်** (AI) ကမ္ဘာကြီးကို လေ့လာလိုက်ပါ! ၎င်းတွင် လက်တွေ့သင်ခန်းစာများ၊ စစ်တမ်းများနှင့် ဂုဏ်ရည်ခန်းများပါဝင်သည်။ သင်ရိုးညွှန်းတမ်းသည် စတင်လေ့လာသောသူများအတွက်လိုက်ဖက်ပြီး TensorFlow နဲ့ PyTorch ကဲ့သို့သော ကိရိယာများနှင့် AI ကျင့်ဝတ်များကိုလည်း ဖုံးကွယ်ပြသထားပါသည်။
|
||||
**အတုယူစက်ရုပ်** (AI) ၏ ကမ္ဘာကြီးကို ကျွန်ုပ်တို့၏ ၁၂ ပတ်၊ ၂၄ သင်ခန်းစာ ပညာသင်အစီအစဉ်ဖြင့် စူးစမ်းလေ့လာပါ! ၎င်းတွင် လက်တွေ့သင်ခန်းစာများ၊ စမ်းသပ်မေးခွန်းများနှင့် ပရိုဇက်များ ပါဝင်သည်။ ဒီအစီအစဉ်သည် လူသစ်များအတွက် လွယ်ကူစွာနားလည်နိုင်ပြီး TensorFlow နှင့် PyTorch ကဲ့သို့သော ကိရိယာများနှင့် AI တွင် ရိုးသားမှုအချက်များကိုလည်း ပါဝင်ပါသည်။
|
||||
|
||||
### 🌐 ဘာသာစကားပေါင်းစုံ ထောက်ပံ့မှု
|
||||
|
||||
#### GitHub Action မှတဆင့် ထောက်ပံ့မှုရှိသည် (အလိုအလျောက်နှင့် အမြဲပြင်ဆင်ထား)
|
||||
### 🌐 ဘာသာစကားစုံအထောက်အပံ့
|
||||
|
||||
#### GitHub Action မှတဆင့်ထောက်ပံ့ထားသည် (အလိုအလျောက် နှင့် အမြဲနောက်ဆုံးဗားရှင်း)
|
||||
|
||||
<!-- CO-OP TRANSLATOR LANGUAGES TABLE START -->
|
||||
[အာရပ်](../ar/README.md) | [ဘင်္ဂါလီ](../bn/README.md) | [ဘူလ်ဂေးရီးယား](../bg/README.md) | [မြန်မာ (မြန်မာ)](./README.md) | [တရုတ် (ရိုးရိုး)](../zh/README.md) | [တရုတ် (ရိုးရိုး, ဟောင်ကောင်)](../hk/README.md) | [တရုတ် (ရိုးရိုး, မာစူ)](../mo/README.md) | [တရုတ် (ရိုးရိုး, တိုင်ဝမ်)](../tw/README.md) | [ခရိုက်ရှားဒီယား](../hr/README.md) | [ချက်](../cs/README.md) | [ဒိန်းမတ်](../da/README.md) | [ဒတ်ချ်](../nl/README.md) | [အက်စ်တိုးနီးယား](../et/README.md) | [ဖင်နစ်](../fi/README.md) | [ပြင်သစ်](../fr/README.md) | [ဂျာမာန်](../de/README.md) | [ဂရိ](../el/README.md) | [ဟီဘရူး](../he/README.md) | [ဟင်းဒီ](../hi/README.md) | [ဟန်ဂေရီးယား](../hu/README.md) | [အင်ဒိုနီးရှား](../id/README.md) | [အီတလီ](../it/README.md) | [ဂျပန်](../ja/README.md) | [ကနေဒါ](../kn/README.md) | [ကိုရီးယား](../ko/README.md) | [လစ္သူနီးယား](../lt/README.md) | [မလေး](../ms/README.md) | [မလေးလာမ်](../ml/README.md) | [မာရသီ](../mr/README.md) | [နီပေါလီ](../ne/README.md) | [နိုင်ဂျီးရီးယား ပစ်ဂင်](../pcm/README.md) | [နော်ဝေ](../no/README.md) | [ပါရှန် (ဖာဆီ)](../fa/README.md) | [ပိုလန်](../pl/README.md) | [ပေါ်တူဂီ (ဘရဇီးလ်)](../br/README.md) | [ပေါ်တူဂီ (ပေါ်ချီဂျီ)](../pt/README.md) | [ပန်ဇာဘီ (ဂျာမူခီ)](../pa/README.md) | [ရိုမေးနီးယား](../ro/README.md) | [ရုရှား](../ru/README.md) | [ဆားဘီးယား (စာရိုလစ်လစ်)](../sr/README.md) | [စလိုဗက်](../sk/README.md) | [စလိုဗေးနီးယား](../sl/README.md) | [စပိန်](../es/README.md) | [ဆွာဟီလီ](../sw/README.md) | [ဆွီဒင်](../sv/README.md) | [တာဂလိုဂ် (ဖိလစ်ပိုင်)](../tl/README.md) | [တမီးလ်](../ta/README.md) | [တယ်လူဂူ](../te/README.md) | [ထိုင်း](../th/README.md) | [တူရ်ကီ](../tr/README.md) | [ယူကရိန်း](../uk/README.md) | [ဥာဒူ](../ur/README.md) | [ဗီယက်နမ်](../vi/README.md)
|
||||
[အာရဗီ](../ar/README.md) | [ဘင်္ဂါလီ](../bn/README.md) | [ဘူල්ဂေးရီးယား](../bg/README.md) | [မြန်မာ](./README.md) | [တရုတ် (ရိုးရိုး)](../zh-CN/README.md) | [တရုတ် (ရိုးရိုး, ဟောင်ကောင်)](../zh-HK/README.md) | [တရုတ် (ရိုးရိုး, မကာဝူ)](../zh-MO/README.md) | [တရုတ် (ရိုးရိုး, တိုင်ဝမ်)](../zh-TW/README.md) | [ခရို့ရှီးယား](../hr/README.md) | [ချက်](../cs/README.md) | [ဒိန်းမားခ်](../da/README.md) | [ဒါချ်](../nl/README.md) | [အက်စတိုနီးယား](../et/README.md) | [ဖင်နစ်](../fi/README.md) | [ပြင်သစ်](../fr/README.md) | [ဂျာမနီ](../de/README.md) | [ဂရိ](../el/README.md) | [ဟေဘရွူး](../he/README.md) | [ဟိန္ဒီ](../hi/README.md) | [ဟန်ဂေရီ](../hu/README.md) | [အင်ဒိုနီးရှား](../id/README.md) | [အီတလီ](../it/README.md) | [ဂျပန်](../ja/README.md) | [ကန်နာဒါ](../kn/README.md) | [ကိုရီးယား](../ko/README.md) | [လစ်သူဝေးနီးယား](../lt/README.md) | [မာလေး](../ms/README.md) | [မာလာရမ်](../ml/README.md) | [မာရသိ](../mr/README.md) | [နီပေါလီ](../ne/README.md) | [နိုင်ဂျီးရီးယား ပစ္ဂင်](../pcm/README.md) | [နော်ဝေ](../no/README.md) | [ပါရှန် (ဖာ ရ်စီ)](../fa/README.md) | [ပိုလန်](../pl/README.md) | [ပေါ်တူဂီ (ဘရာဇီးလ်)](../pt-BR/README.md) | [ပေါ်တူဂီ (ပိုတူဂီ)](../pt-PT/README.md) | [ပန်ဂျာဘီ (ဂူရူမူခီ)](../pa/README.md) | [ရိုမေးနီးယား](../ro/README.md) | [ရုရှား](../ru/README.md) | [ဆားဘီးယား (စီရီးလစ်)](../sr/README.md) | [စလိုဗက်](../sk/README.md) | [စလိုဗေးနီးယား](../sl/README.md) | [စပိန်](../es/README.md) | [ဆွာဟီလီ](../sw/README.md) | [ဆွီဒင်](../sv/README.md) | [တာဂလိုဂ် (ဖိလစ်ပိုင်)](../tl/README.md) | [တမီးလ်](../ta/README.md) | [တာလူဂူ](../te/README.md) | [ថៃ](../th/README.md) | [တူရကီ](../tr/README.md) | [ယူကရိန်း](../uk/README.md) | [ဥာဒူး](../ur/README.md) | [ဗီယက်နမ်](../vi/README.md)
|
||||
|
||||
> **ဒေသတွင်းမှာ Clone လုပ်ချင်ပါသလား?**
|
||||
> **ဒေသတွင်း များကူးယူချင်ပါသလား?**
|
||||
|
||||
> ဤ repository တွင် ဘာသာစကား ၅၀ ကျော်သော ဘာသာပြန်ချက်များပါရှိပြီး ဒါကြောင့် ဒေါင်းလုတ်အရွယ်အစား အများကြီးတိုးပွားပါသည်။ ဘာသာပြန်ချက် မပါမှုဖြင့် clone လုပ်လိုပါက sparse checkout ကို အသုံးပြုပါ:
|
||||
> ဒီ repository မှာ ဘာသာစကား ၅၀ ကျော် စာနဲ့အတူ ပါဝင်တဲ့ အတွက် ဒေါင်းလုဒ် အရွယ်အစား ကြီးတယ်။ ဘာသာစကားများမပါဘဲ ကူးယူချင်ရင် sparse checkout ကို အသုံးပြုပါ:
|
||||
> ```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'
|
||||
> ```
|
||||
> ဒါက သင်အတန်းလေ့လာပြီးမြန်ဆန်စွာ ဒေါင်းလုတ်လုပ်နိုင်မှာ ဖြစ်ပါတယ်။
|
||||
> ဒါကြောင့် သင်သင်ယူဖို့ လိုအပ်သမျှ အားလုံးကို ပိုမြန်တဲ့ ဒေါင်းလုဒ်နဲ့ ရနိုင်ပါပြီ။
|
||||
<!-- CO-OP TRANSLATOR LANGUAGES TABLE END -->
|
||||
|
||||
**ထပ်မံဘာသာပြန်စကားများ ထောက်ပံ့လိုပါက [ဒီနေရာ](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) တွင်စာရင်းပြထားပါသည်။**
|
||||
**အခြား ဘာသာစကားများ ထောက်ပံ့လိုပါက၊ ဤနေရာတွင် စာရင်းပြုထားသည် [here](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
|
||||
|
||||
## အသိုင်းအဝိုင်းတွင် ပူးပေါင်းပါ
|
||||
|
||||
## အသိုင်းအဝိုင်းတွင် ပါဝင်ပါ
|
||||
[](https://discord.gg/nTYy5BXMWG)
|
||||
|
||||
## သင်တတ်မည့်အရာများ
|
||||
## သင်ယူမည့်အချက်များ
|
||||
|
||||
**[သင်တန်း၏ စိတ်ကူးမြေပုံ](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
|
||||
|
||||
ဤသင်ရိုးညွှန်းတမ်းတွင် သင်သည် လေ့လာမည်မှာ –
|
||||
ဒီအစီအစဉ်တွင် သင်တန်းသားများ အောက်ဖော်ပြပါအချက်များကို သင်ယူမည်ဖြစ်ပါသည်-
|
||||
|
||||
* အတုယူမှုအင်တဲလီဂျင့် (AI) ဆိုင်ရာ မတူကွဲပြားသောနည်းလမ်းများ၊ ပုံမှန်ရိုးရာ "အဟောင်း" သင်္ကေတနည်းလမ်းနှင့် **အကြောင်းအရာ ဖော်ပြချက်** နဲ့ သဘောထားခြင်း ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)) ပါဝင်သည်။
|
||||
* ခေတ်မီ AI ၏ အဓိကဖြစ်သော **နာယူးရယ်ကွန်ရက်များ** နှင့် **နက်ကြီးသင်ယူခြင်း**။ မူလတန်းအတွက် များသောအားဖြင့် အဓိက သဘောတရားများကို ပရိုဂရမ်ကို အသုံးပြု၍ ထုတ်ပြသမယ် – နာမည်ကြီးသော Framework နှစ်ခု ဖြစ်သည့် [TensorFlow](http://Tensorflow.org) နှင့် [PyTorch](http://pytorch.org) တွင်ဖြစ်သည်။
|
||||
* ပုံရိပ်နှင့် စာသားများကို ကိုင်တွယ်သုံးစွဲနိုင်ဖို့ **နာယူးရယ်ဖွဲ့စည်းမှုများ**။ နောက်ဆုံးပေါ်မော်ဒယ်များကို ပါဝင်ကာ ပြီးမြောက်မှု လောက်မရှိသော်လည်း ပါဝင်သည်။
|
||||
* နည်းနည်း နာမည်ကျော် မဟုတ်သော AI နည်းလမ်းများကဲ့သို့ **ဂျီနက်တစ် အယ်လ်ဂိုရစ်သမ်များ** နှင့် **Multi-Agent Systems** လည်း ပါဝင်သည်။
|
||||
* အတုယူစက်ရုပ်၏ ကွဲပြားသောနည်းလမ်းများ၊ အထူးသဖြင့် အမှတ်အသားပြ နည်းလမ်းဖြစ်သော **အသိအမှတ်ပြုမှု** နှင့် စဉ်းစားခြင်း ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence))။
|
||||
* ခေတ်မှီ AI ၏ အခြေခံတည်နေရာဖြစ်သော **နွယ်နက်၀ါးများ** နှင့် **နက်ရှိုင်းသင်ယူမှု**။ ထိုဂိမ်းဝိုင်းကို ပိုမိုနားလည်ရလွယ်ကူစေရန် အဓိက framework ၂ ခုဖြစ်သော [TensorFlow](http://Tensorflow.org) နှင့် [PyTorch](http://pytorch.org) တွင် ကုဒ်များဖြင့် ရှင်းလင်းပြသမည်။
|
||||
* ပုံနှင့် စာသားကို လုပ်ဆောင်ရာ၌ အသုံးပြုသော **နွယ်နက် ပုံစံများ**။ မကြာသေးမီက မော်ဒယ်များကို ရှင်းလင်းထားသော်လည်း နောက်ဆုံးနည်းပညာအတိုင်းမဖြစ်နိုင်သေးပါ။
|
||||
* အနည်းသော အသုံးပြုမှုရှိသော AI နည်းလမ်းများဖြစ်သော **ဗီဇဆိုင်ရာ အယ်လဂေါရီသမ်များ** နှင့် **အဖွဲ့ဝင်စနစ်များ**။
|
||||
|
||||
ဤသင်ရိုးညွှန်းတမ်းတွင် မပါဝင်သည့် အရာများက
|
||||
ဒီအစီအစဉ်တွင် မပါဝင်မည့် အကြောင်းအရာများ-
|
||||
|
||||
> [ဤသင်တန်း၏ အပိုဆောင်း အရင်းအမြစ်များအား Microsoft Learn စုစည်းမှုတွင် ရှာဖွေပါ](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
|
||||
> [ဒီသင်တန်းနှင့် ပတ်သက်သော အပိုဆောင်းအရင်းအမြစ်များကို မြန်မာ Microsoft Learn စုစည်းမှုတွင် ရှာဖွေပါ](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
|
||||
|
||||
* **AI ကို စီးပွားရေးထဲတွင် အသုံးပြုခြင်း** စီးပွားရေးဆိုင်ရာကိစ္စများ။ Microsoft Learn မှ [စီးပွားရေးအသုံးပြုသူများအတွက် AI မိတ်ဆက်](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) သင်ကြားမှုလမ်းကြောင်း သို့မဟုတ် [AI စီးပွားရေးကျောင်း](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum) ကို [INSEAD](https://www.insead.edu/) နှင့် ပူးပေါင်းဖန်တီးထားသည်။
|
||||
* ပထမအဆင့် မော်ကွန်းသင်ယူမှု **စတင်ခြင်း** အား အောက်ပါ [Machine Learning for Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners) တွင် ပြည့်စုံစွာ ဖော်ပြထားသည်။
|
||||
* **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** အသုံးပြု၍ တည်ဆောက်ထားသော လက်တွေ့ AI လျှောက်လွှာများ။ ဤအတွက် Microsoft Learn တွင် [မြင်ကွင်း](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [သဘာဝဘာသာစကား သီးခြားစီစစ်ခြင်း](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Azure OpenAI ဝန်ဆောင်မှုဖြင့် စိတ်မဖြစ်သော AI ဖန်တီးခြင်း](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** နှင့် အခြား ဒါမှမဟုတ် မော်ဂျူးများကို စတင်လေ့လာရန် အကြံပြုပါသည်။
|
||||
* အထူးပြု ML **Cloud Frameworks** များကဲ့သို့ [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), သို့မဟုတ် [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum) တို့ပါဝင်သည်။ [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) နှင့် [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) သင်ကြားပေးမှု လမ်းကြောင်းများကို အသုံးပြုဖို့ တိုက်တွန်းပါသည်။
|
||||
* **စကားပြော AI** နှင့် **စကားပြော ဘော့များ**။ ပါဝင်သင်ကြားမှု ပြုသည့် [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) ကိုသင်ယူနိုင်ပြီး၊ အသေးစိတ်အတွက် [ဒီဘလော့ဂ်စာတမ်း](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) ကိုလည်း အကြံပြုပါသည်။
|
||||
* နက်ကြီးသင်ယူမှုအတွက် ကျယ်ပြန့်သော **ဂဏန်းဆိုင်ရာ သင်္ချာများ**။ ဤအတွက် Ian Goodfellow, Yoshua Bengio နှင့် Aaron Courville ၏ [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) စာအုပ်ကို အကြံပြုလို 있으며၊ အွန်လိုင်းတွင် [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) မှလည်း ရနိုင်ပါသည်။
|
||||
* **စီးပွားရေးသုံး AI** ၏ စီးပွားရေးကိစ္စများ။ Microsoft Learn တွင် ပါဝင်သော [စီးပွားရေးသုံး AI ကို မိတ်ဆက်ခြင်း](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) သင်ကြားမှုလမ်းကြောင်း သို့မဟုတ် [AI စီးပွားရေးကျောင်း](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum) ကို INSEAD နှင့် ပူးပေါင်းတီထွင်ထားသည်ကို သင်ယူပါ။
|
||||
* ကျွန်ုပ်တို့၏ [လူသစ်များအတွက် စက်သင်ယူမှု](http://github.com/Microsoft/ML-for-Beginners) တွင် အသေးစားနည်းလမ်းဖြစ်သည့် **စက်သင်ယူမှု ပုံမှန်နည်းလမ်း** မပါဝင်။
|
||||
* **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** အသုံးပြုပြီး တီထွင်ထားသော လက်တွေ့ AI အက်ပလီကေးရှင်းများ။ ဤအတွက် Microsoft Learn တွင် [မြင်ကွင်း](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum)၊ [သဘာဝဘာသာစကား ပြုလုပ်မှု](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum)၊ **[Azure OpenAI Service ဖြင့် ဂျီနရေးတစ် AI](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** နှင့် အခြားများ စသော မော်ဂျူးများဖြင့် စတင်ရန် တိုက်တွန်းပါသည်။
|
||||
* အထူးသတ်မှတ်ထားသော ML **Cloud Frameworks**, ဥပမာ [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), သို့မဟုတ် [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum)။ သင်ယူရန် [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) နှင့် [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) သင်ယူမှုလမ်းကြောင်းများကို အသုံးပြုပါ။
|
||||
* **စကားပြော AI** နှင့် **စကားပြော Bot များ**။ သီးခြား [စကားပြော AI ဖြေရှင်းချက်များ ဖန်တီးခြင်း](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) သင်ကြားမှု လမ်းကြောင်းရှိပြီး၊ ပိုပြီး အသေးစိတ်အတွက် [ဤ ဘလော့ဂ်ပို့စ်](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) ကိုလည်း ပြန်လည်ကြည့်ရှုနိုင်သည်။
|
||||
* နက်ရှိုင်းသင်ယူမှုတွင် ပါဝင်သော **နက်ရှိုင်းသင်ယူမှု သင်္ချာကိန်းဂဏန်းများ**। ဤအတွက် Ian Goodfellow, Yoshua Bengio နှင့် Aaron Courville ရေးသားသော [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) ဝတ္ထုကို လမ်းညွှန်အဖြစ် အသုံးပြုရန် ညိတ်ဆက်ထားပြီး [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/) တွင် အွန်လိုင်းလည်း ရရှိနိုင်ပါသည်။
|
||||
|
||||
_cloud_ အတွင်းရှိ _AI_ အကြောင်းအရာများကို မျက်လုံးပိတ်ကာ အနည်းငယ် မိတ်ဆက်ကြည့်လိုလျှင် [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) သင်ကြားမှုလမ်းကြောင်းကို ဆင်ခြင်ကြည့်ရှုနိုင်ပါသည်။
|
||||
_Cloud တွင် AI_ အကြောင်း လွယ်ကူစွာ မိတ်ဆက်ရန်အတွက် [Azure ပေါ်တွင် အတုယူစက်ရုပ်ဖြင့် စတင်ရန်](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) သင်ကြားမှု လမ်းကြောင်းကို အကြံပြုပါသည်။
|
||||
|
||||
# အကြောင်းအရာများ
|
||||
# အကြောင်းအရာ
|
||||
|
||||
| | သင်ခန်းစာ လင့်ခ် | PyTorch/Keras/TensorFlow | ဂုဏ်ရည်ခန်း |
|
||||
| | သင်ခန်းစာ လင့်ခ် | PyTorch/Keras/TensorFlow | လေ့ကျင့်ခန်း |
|
||||
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
|
||||
| 0 | [သင်တန်း စတင်ခြင်း](./lessons/0-course-setup/setup.md) | [သင့် ဖွံ့ဖြိုးတိုးတက်မှု ပတ်ဝန်းကျင် စတင်ဆောင်ရွက်ခြင်း](./lessons/0-course-setup/how-to-run.md) | |
|
||||
| 0 | [သင်တန်း စတင်ခြင်း](./lessons/0-course-setup/setup.md) | [ဖန်တီးမှု ပတ်ဝန်းကျင် ပြင်ဆင်ခြင်း](./lessons/0-course-setup/how-to-run.md) | |
|
||||
| I | [**AI မိတ်ဆက်**](./lessons/1-Intro/README.md) | | |
|
||||
| 01 | [AI ၏ မိတ်ဆက်နှင့် သမိုင်း](./lessons/1-Intro/README.md) | - | - |
|
||||
| 01 | [AI မိတ်ဆက်နှင့် သမိုင်း](./lessons/1-Intro/README.md) | - | - |
|
||||
| II | **သင်္ကေတ AI** |
|
||||
| 02 | [အကြောင်းအရာ ဖော်ပြခြင်းနှင့် ကျွမ်းကျင်သူ စနစ်များ](./lessons/2-Symbolic/README.md) | [ကျွမ်းကျင်သူ စနစ်များ](./lessons/2-Symbolic/Animals.ipynb) / [အောင့်တောလီ](./lessons/2-Symbolic/FamilyOntology.ipynb) /[အယူအဆဇယား](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
|
||||
| III | [**နာယူးရယ်ကွန်ရက် မိတ်ဆက်**](./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 and Creating our own Framework](./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 to Frameworks (PyTorch/TensorFlow) and 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 | [**ကွန်ပျူတာဗွေရှင်း**](./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)| [Explore Computer Vision on Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
|
||||
| 06 | [ကွန်ပျူတာဗွေရှင်းနဲ့နိဒါန်း။ 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) & [CNN Architectures](./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 | [Pre-trained Networks and Transfer Learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) and [Training Tricks](./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 and 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 & Artistic Style Transfer](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
|
||||
| 11 | [Object Detection](./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 | [Semantic Segmentation. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
|
||||
| V | [**သဘာဝဘာသာစကားကုမန့်ဆုံးခြင်း**](./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) | [Explore Natural Language Processing on Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
|
||||
| 13 | [စာသားဖော်ပြချက်။ 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 | [အဓိပ္ပါယ်အရ စကားလုံးထိုးသွင်းပါတယ်။ Word2Vec နဲ့ 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 | [ဘာသာစကားပုံစံ။ ကိုယ်ပိုင်အပ်ဒိတ်ထိုးသွင်းခြင်းလေ့ကျင့်ခြင်း](./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) |
|
||||
| 02 | [အသိအမှတ်ပြုမှုနှင့် ကျွမ်းကျင်မှု စနစ်များ](./lessons/2-Symbolic/README.md) | [ကျွမ်းကျင်မှု စနစ်များ](./lessons/2-Symbolic/Animals.ipynb) / [ဇာတိတော်အခြေခံ စနစ်](./lessons/2-Symbolic/FamilyOntology.ipynb) /[အယူအဆ အကြောင်းပြု ရုပ်ပုံ](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
|
||||
| III | [**နယူးရယ်ကွန်ယက်များသို့နိဒါန်း**](./lessons/3-NeuralNetworks/README.md) |||
|
||||
| 03 | [ပာစက်ထရွန်](./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 | [အလွယ်တကူအဆင့်များပါ ပာစက်ထရွန်နှင့် ကျွန်ုပ်တို့၏ကိုယ့်စိတ်ကြိုက် Framework တည်ဆောက်ခြင်း](./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 | [Framework များသို့နိဒါန်း (PyTorch/TensorFlow) နှင့် အလွန်တက်မှု](./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 | [**ကွန်ပျူတာမြင်ကွင်း**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Microsoft Azure တွင် ကွန်ပျူတာမြင်ကွင်း စမ်းသပ်ရန်](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
|
||||
| 06 | [ကွန်ပျူတာမြင်ကွင်းနှင့် မိတ်ဆက်ခြင်း။ 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 | [ကွန်ဗောလုရှင်းနယူးရယ်ကွန်ယက်များ](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN စက်ဆောက်ပုံများ](./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 | [ကြိုတင်လေ့လာပြီးသောကွန်ယက်များနှင့် ကူးပြောင်းသင်ယူခြင်း](./lessons/4-ComputerVision/08-TransferLearning/README.md) နှင့် [လေ့ကျင့်ရေးနည်းပညာများ](./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 | [အော်တိုအင်ကိုးဒါများနှင့် VAE များ](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
|
||||
| 10 | [ဖန်တီးမှုဆန်ဆန် အပြိုင်တန်းကွန်ယက်များနှင့် အနုပညာစတိုင်ကူးပြောင်းခြင်း](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
|
||||
| 11 | [အရာဝတ္ထုစမ်းသပ်ခြင်း](./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 | [သိပ္ပံဘာသာဖြင့် Segmentation။ U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
|
||||
| V | [**ဘာသာစကားသဘာဝလုပ်ငန်းဆောင်တာ**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Microsoft Azure တွင် ဘာသာစကားသဘာဝလုပ်ငန်းဆောင်တာ စူးစမ်းခြင်း](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
|
||||
| 13 | [စာသားကို ကိုယ်စားပြုခြင်း။ 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 | [စာလုံး၏အဓိပ္ပာယ်အရသွင်ပြင်ဆက်စပ်မှု။ Word2Vec နှင့် 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 | [ဘာသာစကားမော်ဒယ်ရေးခြင်း။ ကိုယ့်ကိုယ်ကို embedding များလေ့ကျင့်ခြင်း](./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 | [ပြန်လည်ဖြတ်သန်းမှုနယူးရယ်ကွန်ယက်များ](./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 | [ဖန်တီးရေးပြန်လည်ဖြတ်သန်းမှုကွန်ယက်များ](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
|
||||
| 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
|
||||
| 19 | [အမည်ရှိနယ်မြေအသိအမှတ်ပြုခြင်း](./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 | [ကြီးမားသောဘာသာစကားပုံစံများ၊ ကမ်းလှမ်းချက်ပရိုဂရမ်းမင်းနှင့် အနည်းငယ်-သွားတာလှုပ်ရှားမှုများ](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
|
||||
| 19 | [အမည်သတ်မှတ်ထားသောအဖွဲ့အစည်း အသိအမှတ်ပြုခြင်း](./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 | [အကြီးစားဘာသာစကားမော်ဒယ်များ၊ Prompt Programming နှင့် နည်းနည်းသင်ကြားမှုလုပ်ငန်းဆောင်တာများ](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
|
||||
| VI | **အခြား AI နည်းပညာများ** || |
|
||||
| 21 | [ဂျင်နက်တစ် အယ်လ်ဂိုရီသမ်များ](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
|
||||
| 22 | [နက်ရှိုင်းသော အားပေးသင်ကြားမှု လေ့လာမှု](./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 | [အများပြည်သူအေဂျင့်စနစ်များ](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
|
||||
| VII | **AI သမာဓိ** | | |
|
||||
| 24 | [AI သမာဓိနှင့် တာဝန်ခံ AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Responsible AI Principles](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
|
||||
| IX | **အပိုဆောင်းများ** | | |
|
||||
| 25 | [မူလတန်းစုံကွန်ရက်များ၊ CLIP နှင့် VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
|
||||
| 21 | [ဂျင်နိုက် အယ်လဂိုရီသမ်များ](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
|
||||
| 22 | [နက်ရှိုက် အခြေခံတဲ့ ပြန်လည်အားဖြည့်မှုသင်ယူခြင်း](./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 | [Multi-Agent Systems](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
|
||||
| VII | **AI မြင်ကွင်းများနှင့် သမာဓိ** | | |
|
||||
| 24 | [AI မြင်ကွင်းများနှင့် တာဝန်ရှိမှု AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: တာဝန်ရှိသော AI 원칙များ](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
|
||||
| IX | **ထပ်ဆောင်းအကြောင်းအရာများ** | | |
|
||||
| 25 | [Multi-Modal Networks, CLIP နှင့် VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
|
||||
|
||||
## သင်ခန်းစာတိုင်းတွင်ပါဝင်သောအရာများ
|
||||
## လက်တွေ့သင်ခန်းစာတိုင်းတွင် ပါဝင်သည်များ
|
||||
|
||||
* မင်္ဂလာဆောင်စာအုပ်ပုံစံစာမျက်နှာများ
|
||||
* စနစ်အသီးသီးအတွက် အထူးသီးသန့်ဖြစ်သော Jupyter Notebooks များ (**PyTorch** သို့မဟုတ် **TensorFlow** ဖြစ်ကြောင်း) ပါဝင်သည်။ ကိုယ့်ဘာသာ အကြောင်းအရာကိုနားလည်ရန်အတွက် နောက်ထပ်အနည်းဆုံးတစ်ခုခု Notebook (PyTorch သို့မဟုတ် TensorFlow) ကို ဖတ်ပါ။
|
||||
* အချို့သောခေါင်းစဉ်များအတွက် **Labs** များ ရရှိနိုင်ပြီး သင်လေ့လာထားသော အကြောင်းအရာများကို အကောင်အထည်ဖော်ရန်အခွင့်အရေးပေးသည်။
|
||||
* အချို့သောအပိုင်းများတွင် သက်ဆိုင်ရာခေါင်းစဉ်များကို ဖုံးကွယ်ထားသည့် [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) modules များသို့ ချိတ်ဆက်ထားသည်။
|
||||
* ကြိုတင်ဖတ်ရှုရန် စာရင်း
|
||||
* လုပ်ဆောင်နိုင်သော Jupyter Notebooks များ၊ မကြာခဏ Framework အရောက်ကျသည့် (**PyTorch** သို့မဟုတ် **TensorFlow**) ဖြစ်သည်။ လုပ်ဆောင်နိုင်သော notebook တွင် သဘောတရားဆိုင်ရာများလည်းပါရှိသည့်အတွက် မည်သူမဆို ခေါင်းစဉ်နားလည်ရန် သာမန်အားဖြင့် notebook တစ်ခုခု (PyTorch သို့ TensorFlow) ကို ကြည့်ရှုရန် လိုအပ်သည်။
|
||||
* အချို့ခေါင်းစဉ်များအတွက် သင်တန်းပြန်လည်လုပ်ဆောင်နိုင်သော **Labs** များ၊ သင်သင်ယူခဲ့သော ကိစ္စအကြောင်းအရာကို တိကျသောပြဿနာတစ်ခုတွင် အသုံးပြု၍ ကြိုးစားလေ့လာနိုင်သောအခွင့်အလမ်းပေးသည်။
|
||||
* အပိုင်းတချို့တွင် [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) မိုဒျူးများသို့ ချိတ်ဆက်ထားသည်။
|
||||
|
||||
## စတင်လုပ်ဆောင်ခြင်း
|
||||
## စတင်ရန်
|
||||
|
||||
### 🎯 AI အသစ်လား? ဒီမှာစပါ!
|
||||
### 🎯 AI အသစ်တက်သူများအတွက်! ဒီနေရာကနေ စတင်ပါ။
|
||||
|
||||
သင် AI ကိုမပြည့်စုံသော အသစ်တစ်ယောက်ဖြစ်ပြီး လွယ်ကူမြန်ဆန်သော လက်တွေ့နမူနာများလိုလျှင် ကျွန်ုပ်တို့ရဲ့ [**စတင်ရန်အဆင်ပြေသောနမူနာများ**](./examples/README.md) ကို ကြည့်ပါ! ၎င်းတွင်ပါဝင်သည်မှာ-
|
||||
AI အသစ်တက်သူများအတွက် လျင်မြန်သေချာသော လက်တွေ့ ဥပမာများကို ကျွန်ုပ်တို့၏ [**စိတ်ကြိုက်အကြီးအကျယ် ဥပမာများ**](./examples/README.md) တွင် စူးစမ်းနိုင်ပါသည်။ ထည့်သွင်းထားသည်မှာ -
|
||||
|
||||
- 🌟 **မင်္ဂလာပါ AI ကမ္ဘာ** - သင့်ရဲ့ ပထမဆုံး AI ပရိုဂရမ်း (ပုံစံသိရှိခြင်း)
|
||||
- 🧠 **ရိုးရှင်းသောနည်းလမ်း Networks** - စတင်ဖန်တီးသော နယူးရယ်နက်ဝက်
|
||||
- 🖼️ **ပုံရိပ်စာတန်းသတ်မှတ်စက်** - အသေးစိတ် မှတ်ချက်များဖြင့် ပုံရိပ်များ သတ်မှတ်ခြင်း
|
||||
- 💬 **စာသားခံစားချက်** - ဂရုတစိုက်/မဂြိုဟ် စာသားကိုစစ်ဆေးပါ
|
||||
- 🌟 **Hello AI World** - သင်၏ပထမဆုံး AI ပရိုဂရမ် (ပုံစံအသိအမှတ်ပြုခြင်း)
|
||||
- 🧠 **ရိုးရှင်းသောနယူးရယ်ကွန်ယက်** - နယူးရယ်ကွန်ယက်ကို အစကနေတည်ဆောက်ခြင်း
|
||||
|
||||
ဤဥပမာများသည် သင်အား AI အတွေးအခေါ်များကို နားလည်စေရန်နှင့် အပြည့်အစုံ သင်ရိုးအစီအစဉ်ထဲ ဝင်ရောက်ရန်အတွက် အထောက်အကူပြုရန် ရည်ရွယ်ပါသည်။
|
||||
- 🖼️ **ပုံခွဲခြားစနစ်** - အဒီၤပုံများကို အသေးစိတ် မှတ်ချက်များနှင့် ခွဲခြားခြင်း
|
||||
- 💬 **စာသားခံစားချက်** - အပြု/အမပြု စာသားများကို ခွဲခြမ်းစိတ်ဖြာခြင်း
|
||||
|
||||
### 📚 အပြည့်အစုံ သင်ရိုးအစီအစဉ် တပ်ဆင်ခြင်း
|
||||
ဤဥပမာများကို သင်၏ AI မှတ်ယူချက်များကို နားလည်ရန်အတွက် ဖန်တီးထားပြီး မိမိတို့လေ့လာရေးအစီအစဉ်ကို စတင်လေ့လာရန် ပြင်ဆင်ပေးထားသည်။
|
||||
|
||||
- သင်၏ ဖွံ့ဖြိုးရေး ပတ်ဝန်းကျင်ကို တပ်ဆင်ရာတွင် ကူညီရန် အတွက် [တပ်ဆင်ခြင်းသင်ခန်းစာ](./lessons/0-course-setup/setup.md) တစ်ခု ပြုလုပ်ထားပါသည်။ - ပညာသင်ကြားသူများအတွက်လည်း သင့်အတွက် [သင်ရိုးစီစဉ်ခြင်း သင်ခန်းစာ](./lessons/0-course-setup/for-teachers.md) တစ်ခု ပြုလုပ်ထားပါသည်။
|
||||
- VSCode သို့မဟုတ် Codespace တွင် [ကုဒ်မှတ်တမ်းများကို အကောင်အထည်ဖော်နည်း](./lessons/0-course-setup/how-to-run.md)
|
||||
### 📚 အပြည့်အစုံ သင်ရိုးညွှန်းတမ်း ပြင်ဆင်ခြင်း
|
||||
|
||||
အောက်ပါအဆင့်များကို လိုက်နာပါ။
|
||||
- ဖန်တီးထားသည့် [setup lesson](./lessons/0-course-setup/setup.md) မှတဆင့် သင်၏ ဖွံဖြိုးတိုးတက်မှု ပတ်ဝန်းကျင်ကို ပြင်ဆင်နိုင်ပါသည်။
|
||||
- အတန်းအတွက် သင်ကြားသူများအတွက်လည်း [curricula setup lesson](./lessons/0-course-setup/for-teachers.md) ဖန်တီးထားသည်။
|
||||
- [VSCode သို့မဟုတ် Codespace တွင် အကောင်အထည်ဖော်နည်း](./lessons/0-course-setup/how-to-run.md)
|
||||
|
||||
Repository ကို Fork လုပ်ပါ- ဤ စာမျက်နှာ၏ ညာဘက်ထိပ်ရှိ "Fork" ခလုတ်ကို နှိပ်ပါ။
|
||||
အောက်ပါ အဆင့်များကို လိုက်နာပါ -
|
||||
|
||||
Repository ကို Clone လုပ်ပါ- `git clone https://github.com/microsoft/AI-For-Beginners.git`
|
||||
Repository ကို ဖောက်သည် - ဤစာမျက်နှာ၏ ညာဘက်အပေါ်တွင်ရှိသည့် "Fork" ခလုတ်ကို နှိပ်ပါ။
|
||||
|
||||
နောက်မှရှာဖွေရန်အဆင်ပြေသည့်အတွက် ဤ repo ကို စတား (🌟) ခြင်းမမေ့ပါနှင့်။
|
||||
Repository ကို clone လုပ်ပါ - `git clone https://github.com/microsoft/AI-For-Beginners.git`
|
||||
|
||||
## အခြား သင်ယူသူများနှင့် တွေ့ဆုံခြင်း
|
||||
ပြီးလျှင် repo ကို စတား (🌟) ပေးပါ။ ရှာဖွေဖို့ လွယ်ကူစေပါမည်။
|
||||
|
||||
ဤ သင်တန်းကို လေ့လာနေသူများနှင့် တွေ့ဆုံ၍ ပူးပေါင်းဆွေးနွေးနိုင်ရန်အတွက် ကျွန်ုပ်တို့၏ [တရားဝင် AI Discord ဆာဗာ](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) တက်ရောက်ပါ။
|
||||
## အခြားလေ့လာသူများနှင့် တွေ့ဆုံခြင်း
|
||||
|
||||
ထုတ်ကုန်ဆိုင်ရာ အကြံပြုချက်များ သို့မဟုတ် မေးခွန်းများ ရှိပါက ကျွန်ုပ်တို့၏ [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) မှာ လည်းလာဆွေးနွေးနိုင်ပါသည်။
|
||||
ဒီသင်ကြားမှုကို လေ့လာနေသူများနှင့် တွေ့ဆုံပြီး ဆွေးနွေးရန် ကျွန်ုပ်တို့ရဲ့ [တရားဝင် AI Discord server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) ကို ဝင်ရောက်ပါ။
|
||||
|
||||
## စမ်းသပ်မေးခွန်းများ
|
||||
ထပ်မံ ဒီဇိုင်းဆောက်လုပ်စဉ် တွေ့ရှိလာသော ထုတ်ကုန်မေးမြန်းချက်များ သို့မဟုတ် အကြံပြုချက်များရှိပါက ကျွန်ုပ်တို့ရဲ့ [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum) သို့ သွားရောက်ပါ။
|
||||
|
||||
> **စမ်းသပ်မေးခွန်းများအကြောင်း မှတ်ချက်**: စမ်းသပ်မေးခွန်းအားလုံးကို Quiz-app ဖိုလ်ဒါတွင်း etc\quiz-app မှာပါရှိပြီး [ဤနေရာတွင် အွန်လိုင်း](https://ff-quizzes.netlify.app/) မှာလည်း ကြည့်ရှုနိုင်ပါသည်။ စမ်းသပ်မေးခွန်း app ကို ဒေသတွင်းတွင် အကောင်အထည်ဖော်နိုင်ပြီး Azure သို့ deployment လုပ်နိုင်ပါသည်။ `quiz-app` ဖိုလ်ဒါအတွင်း လမ်းညွှန်ချက်များကို လိုက်နာပါ။ အစီအစဉ်များကို တဖြည်းဖြည်း ဘာသာပြန်ဆောင်ရွက်နေပါသည်။
|
||||
## စမ်းသပ်စစ်ဆေးမှုများ (Quizzes)
|
||||
|
||||
## ကူညီလိုသူ
|
||||
> **Quiz များအကြောင်း မှတ်ချက်**: All quizzes are contained in the Quiz-app folder in etc\quiz-app, or [Online Here](https://ff-quizzes.netlify.app/) သင်ခန်းစာအတွင်းပိုင်းမှ ချိတ်ဆက်ထားပါသည်။ Quiz App ကို ဒေသခံတွင် သို့မဟုတ် Azure သို့ တပ်ဆင်အသုံးပြုနိုင်ပါသည်။ `quiz-app` ဖိုလ်ဒါအတွင်းရှိပြသနာများကို လိုက်နာပါ။ Quiz များကို မြန်မြန်ဆန်ဆန် ပြည်တွင်းဘာသာဖြင့် ပြင်ဆင်နေပါသည်။
|
||||
|
||||
အကြံပြုချက်များရှိပါသလား၊ လက်လွတ်စကားလုံးများ သို့မဟုတ် ကုဒ်အမှားများကို တွေ့ရှိပါသလား? ပြဿနာတင်ပါ သို့မဟုတ် pull request တင်ပါ။
|
||||
## အကူအညီလိုအပ်ပါသည်
|
||||
|
||||
## အထူးကျေးဇူးတင်၏
|
||||
အကြံပြုချက်များရှိပါသလား သို့မဟုတ် စာလုံးပေါင်း ချွတ်ယွင်းမှု သို့မဟုတ် ကုဒ်အမှားများတွေ့ရှိပါသလား? ပြဿနာတင်ရန် သို့မဟုတ် pull request တင်ရန် ဆောင်ရွက်ပါ။
|
||||
|
||||
* **✍️ အဓိကရေးသားသူ**: [Dmitry Soshnikov](http://soshnikov.com), PhD
|
||||
* **🔥 တည်းဖြတ်သူ**: [Jen Looper](https://twitter.com/jenlooper), PhD
|
||||
* **🎨 အမှတ်အသားပုံဆွဲသူ**: [Tomomi Imura](https://twitter.com/girlie_mac)
|
||||
* **✅ စမ်းသပ်မေးခွန်း ဖန်တီးသူ**: [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
|
||||
* **🙏 အဓိက ပံ့ပိုးသူများ**: [Evgenii Pishchik](https://github.com/Pe4enIks)
|
||||
## အထူးကျေးဇူးတင်ခြင်း
|
||||
|
||||
## အခြား သင်ရိုးအစီအစဉ်များ
|
||||
* **✍️ အဓိကရေးသားသူ:** [Dmitry Soshnikov](http://soshnikov.com), PhD
|
||||
* **🔥 အယ်ဒီတာ:** [Jen Looper](https://twitter.com/jenlooper), PhD
|
||||
* **🎨 Sketchnote ပန်းချီဆရာ:** [Tomomi Imura](https://twitter.com/girlie_mac)
|
||||
* **✅ စမ်းသပ်မှု ဖန်တီးသူ:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
|
||||
* **🙏 အဓိက ပါဝင်ဆောင်ရွက်သူများ:** [Evgenii Pishchik](https://github.com/Pe4enIks)
|
||||
|
||||
ကျွန်ုပ်တို့၏အဖွဲ့သည် အခြား သင်ရိုးအစီအစဉ်များကို လည်း ထုတ်လုပ်ပါသည်။ ကြည့်ရှုပါ။
|
||||
## အခြား သင်ရိုးညွှန်းတမ်းများ
|
||||
|
||||
ကျွန်ုပ်တို့အသင်းအဖွဲ့သည် အခြားသင်ရိုးညွှန်းတမ်းများကို ထုတ်လုပ်သည်။ ဖော်ပြပါကိုကြည့်ရှုပါ -
|
||||
|
||||
<!-- CO-OP TRANSLATOR OTHER COURSES START -->
|
||||
### LangChain
|
||||
|
|
@ -214,19 +209,19 @@ Repository ကို Clone လုပ်ပါ- `git clone https://github.com/mic
|
|||
[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
|
||||
<!-- CO-OP TRANSLATOR OTHER COURSES END -->
|
||||
|
||||
## ကူညီမှု ရယူခြင်း
|
||||
## အကူအညီရယူနည်း
|
||||
|
||||
AI apps ဖန်တီးရာတွင် ပိတ်ဆို့မှုရှိပါက သို့မဟုတ် မေးခွန်းများရှိပါက MCP အကြောင်း ဆွေးနွေးရန်အတွက် အခြား သင်ယူသူများနှင့် အတွေ့အကြုံရှိ ဖွံ့ဖြိုးသူများနှင့် ပူးပေါင်းဆွေးနွေးနိုင်ပါသည်။ ဒီသည် မေးခွန်းများကို ကြိုဆိုပြီး အသိပညာကို လွတ်လပ်စွာ မျှဝေနိုင်သော ပံ့ပိုးကူညီမှုရှိသော အသိုင်းအဝိုင်းဖြစ်ပါသည်။
|
||||
AI အက်ပ်များ ဖန်တီးရာတွင် အခက်အခဲရှိပါက MCP အတွင်း လေ့လာသူများနှင့် အတွေ့အကြုံရှိသူများနှင့် ဆွေးနွေးနိုင်ပါသည်။ မေးခွန်းများသာမက ပညာအကြောင်းအရာများကိုလည်း မျှဝေကြသည့် ပံ့ပိုးမှုအဖွဲ့အစည်းဖြစ်ပါသည်။
|
||||
|
||||
[](https://discord.gg/nTYy5BXMWG)
|
||||
|
||||
ထုတ်ကုန်ဆိုင်ရာ တုံ့ပြန်ချက်များ သို့မဟုတ် ပြဿနာများ ရှိပါက လည်းလေ့လာရန်:
|
||||
ထုတ်ကုန်ပြန်လည်တုံ့ပြန်ချက် သို့မဟုတ် ဖန်တီးရာတွင် အမှားများရိှပါက သွားရောက်စစ်ဆေးပါ -
|
||||
|
||||
[](https://aka.ms/foundry/forum)
|
||||
|
||||
---
|
||||
|
||||
<!-- CO-OP TRANSLATOR DISCLAIMER START -->
|
||||
**အကြောင်းကြားချက်**
|
||||
ဤစာတမ်းကို AI ဘာသာပြန်ဝန်ဆောင်မှုဖြစ်သော [Co-op Translator](https://github.com/Azure/co-op-translator) အသုံးပြု၍ ဘာသာပြန်ထားပါသည်။ ကျွန်ုပ်တို့သည် မှန်ကန်မှုအတွက် ကြိုးစားတတ်သော်လည်း၊ အလိုအလျှောက် ဘာသာပြန်ခြင်းသည် အမှားများ သို့မဟုတ် မှားယွင်းမှုများ ပါရှိနိုင်ကြောင်း ကျေးဇူးပြု၍ သိရှိထားပေးပါရန် တိုက်တွန်းအပ်ပါသည်။ ဆက်စပ်ဘာသာစကားဖြင့် မူရင်းစာတမ်းကို စွဲဆိုနိုင်သော အတည်ပြုရရှိသော အရင်းအမြစ်အဖြစ် သတ်မှတ်စဉ်းစားသင့်ပါသည်။ အရေးကြီးသော သတင်းအချက်အလက်များအတွက်တော့ ပရော်ဖက်ရှင်နယ် လူသားဘာသာပြန်ခြင်းကို အကြံပြုအပ်ပါသည်။ ဤ ဘာသာပြန်ချက်ကို အသုံးပြုရာမှ ဖြစ်ပေါ်နိုင်သော နားမလည်မှုများ သို့မဟုတ် မှားယွင်းဖတ်ရှုမှုများအတွက် ကျွန်ုပ်တို့ အာမခံချက် မရှိပါ။
|
||||
**အဆိုပြုချက်**
|
||||
ဤစာတမ်းကို AI ဘာသာပြန်ဆဲဝစ်စ် [Co-op Translator](https://github.com/Azure/co-op-translator) ဖြင့် ဘာသာပြန်ထားပါသည်။ ကျွန်ုပ်တို့သည် မှန်ကန်မှုအတွက် ကြိုးပမ်းပါသော်လည်း အလိုအလျှောက် ဘာသာပြန်ချက်များတွင် အမှားလည်း ရှိနိုင်မှုကို သတိပြုပါရန် မေတ္တာရပ်ခံအပ်ပါသည်။ မူရင်းစာတမ်းကို မိမိဘာသာစကားဖြင့် ထုတ်ပြန်ထားသည့်ပုံစံကို တရားဝင်သော အရင်းအမြစ်အဖြစ် သတ်မှတ်စဉ်းစားသင့်ပါသည်။ အရေးကြီးသော အချက်အလက်များအတွက် သက်ဆိုင်ရာ ပညာရှင် လူသား ဘာသာပြန်ခြင်းကို အကြံပြုပါသည်။ ဤဘာသာပြန်ချက်ကို အသုံးပြုသည့်နေရာများမှ ဖြစ်ပေါ်နိုင်သော နားမလည်မှုများ သို့မဟုတ် မမှန်ကန်စွာ ခွဲခြားနားလည်မှုများအတွက် ကျွန်ုပ်တို့ တာဝန်မယူပါ။
|
||||
<!-- CO-OP TRANSLATOR DISCLAIMER END -->
|
||||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
|
||||
"translation_date": "2025-08-25T21:22:35+00:00",
|
||||
"source_file": "SECURITY.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
## လုံခြုံရေး
|
||||
|
||||
Microsoft သည် ၎င်း၏ ဆော့ဖ်ဝဲထုတ်ကုန်များနှင့် ဝန်ဆောင်မှုများ၏ လုံခြုံရေးကို အလေးထားဆောင်ရွက်ပြီး၊ ၎င်းတွင် [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) နှင့် [ကျွန်ုပ်တို့၏ GitHub အဖွဲ့အစည်းများ](https://opensource.microsoft.com/) အပါအဝင် GitHub အဖွဲ့အစည်းများမှ စီမံခန့်ခွဲထားသော အရင်းအမြစ်ကုဒ်ရုံများအားလုံး ပါဝင်သည်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
|
||||
"translation_date": "2025-08-26T00:45:17+00:00",
|
||||
"source_file": "etc/CODE_OF_CONDUCT.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Microsoft Open Source Code of Conduct
|
||||
|
||||
ဒီပရောဂျက်သည် [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/) ကို လက်ခံထားပါသည်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
|
||||
"translation_date": "2025-08-26T00:48:26+00:00",
|
||||
"source_file": "etc/CONTRIBUTING.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အထောက်အပံ့ပေးခြင်း
|
||||
|
||||
ဒီပရောဂျက်ဟာ အထောက်အပံ့ပေးမှုနဲ့ အကြံပြုချက်တွေကို ကြိုဆိုပါတယ်။ အများစုသော အထောက်အပံ့ပေးမှုတွေဟာ Contributor License Agreement (CLA) ကို သဘောတူဖို့ လိုအပ်ပါတယ်။ ဒါဟာ သင့်အနေဖြင့် သင့်အထောက်အပံ့ကို အသုံးပြုခွင့်ပေးဖို့ အခွင့်အရေးရှိတယ်၊ အမှန်တကယ်ပေးတယ်ဆိုတာကို ကြေညာတဲ့ အချက်လက်စာချုပ်တစ်ခုဖြစ်ပါတယ်။ အသေးစိတ်အချက်အလက်များကို https://cla.microsoft.com မှာ ကြည့်ရှုနိုင်ပါတယ်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
|
||||
"translation_date": "2025-08-26T00:52:27+00:00",
|
||||
"source_file": "etc/Mindmap.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# AI
|
||||
|
||||
## [AI အကြောင်းအရာမိတ်ဆက်](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
|
||||
"translation_date": "2025-08-26T00:44:14+00:00",
|
||||
"source_file": "etc/SUPPORT.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အထောက်အပံ့
|
||||
|
||||
## ပြဿနာများကို တင်ပြခြင်းနှင့် အကူအညီရယူရန်
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
|
||||
"translation_date": "2025-08-26T00:46:49+00:00",
|
||||
"source_file": "etc/TRANSLATIONS.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# သင်ခန်းစာများကို ဘာသာပြန်ခြင်းဖြင့် အထောက်အကူပြုပါ
|
||||
|
||||
ဒီသင်ခန်းစာများအတွက် ဘာသာပြန်မှုများကို ကြိုဆိုပါသည်!
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
|
||||
"translation_date": "2025-08-26T00:55:41+00:00",
|
||||
"source_file": "etc/quiz-app/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# မေးခွန်းများ
|
||||
|
||||
ဒီမေးခွန်းများဟာ AI သင်ခန်းစာများအတွက် [!NOTE] သင်ခန်းစာမတိုင်မီနှင့်ပြီးနောက် မေးခွန်းများဖြစ်ပါတယ်။ https://aka.ms/ai-beginners မှာတွေ့နိုင်ပါတယ်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
|
||||
"translation_date": "2025-10-03T11:35:15+00:00",
|
||||
"source_file": "examples/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# AI စတင်လေ့လာသူများအတွက် နမူနာများ
|
||||
|
||||
ကြိုဆိုပါတယ်! ဒီ directory မှာ AI နဲ့ machine learning ကို စတင်လေ့လာဖို့အတွက် လွယ်ကူပြီး တစ်ခုချင်းစီ standalone နမူနာများ ပါဝင်ပါတယ်။ နမူနာတစ်ခုချင်းစီကို စတင်လေ့လာသူများအတွက် သက်သာစေဖို့ အကြောင်းအရာများကို အသေးစိတ် ရှင်းပြထားပြီး အဆင့်ဆင့် လမ်းညွှန်ချက်များ ပါဝင်ပါတယ်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a094ef9927883de1cfcee51dbd143381",
|
||||
"translation_date": "2025-08-26T00:40:07+00:00",
|
||||
"source_file": "lessons/0-course-setup/for-teachers.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# ဆရာများအတွက်
|
||||
|
||||
ဒီသင်ရိုးကို သင့်အတန်းထဲမှာ အသုံးပြုချင်ပါသလား? ကျေးဇူးပြု၍ အသုံးပြုလိုက်ပါ။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
|
||||
"translation_date": "2026-01-16T06:16:07+00:00",
|
||||
"source_file": "lessons/0-course-setup/how-to-run.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# နည်းလမ်း အတိုင်း ကုတ်ကို လည်ပတ်ရန်
|
||||
|
||||
ဒီ သင်ခန်းစာဟာ အလုပ်လုပ်နိုင်တဲ့ ဥပမာတွေ နဲ့ လက်တွေ့လေ့ကျင့်ခန်းတွေ များစွာ ပါဝင်ပြီး သင် လည်ပတ်ချင်မယ်။ ဒါကို လုပ်ဖို့ သင် လိုအပ်တာက ဒီသင်ခန်းစာ၏ အစိတ်အပိုင်းတစ်ခုအနေဖြင့် ပေးထားတဲ့ Jupyter Notebooks ထဲမှာ Python ကုတ်ကို လည်ပတ်နိုင်စွမ်းရှိဖို့ ဖြစ်ပါတယ်။ ကုတ်ကို လည်ပတ်ဖို့ အနည်းငယ် ရွေးချယ်စရာရှိပါတယ်-
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
|
||||
"translation_date": "2025-12-12T20:25:12+00:00",
|
||||
"source_file": "lessons/0-course-setup/setup.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# ဒီသင်ရိုးကို စတင်အသုံးပြုခြင်း
|
||||
|
||||
## သင်ကျောင်းသားလား?
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
|
||||
"translation_date": "2025-11-18T22:13:19+00:00",
|
||||
"source_file": "lessons/1-Intro/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# AI အကြောင်းအကျဉ်း
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
|
||||
"translation_date": "2025-11-18T22:14:28+00:00",
|
||||
"source_file": "lessons/1-Intro/assignment.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Game Jam
|
||||
|
||||
ဂိမ်းများသည် AI နှင့် ML တိုးတက်မှုများ၏ သက်ရောက်မှုကို အလွန်ရရှိထားသော နယ်ပယ်တစ်ခုဖြစ်သည်။ ဤအလုပ်မှာ သင်နှစ်သက်သော ဂိမ်းတစ်ခုကို AI တိုးတက်မှုများ၏ သက်ရောက်မှုကြောင့် အကျိုးသက်ရောက်မှုရှိခဲ့သော ဂိမ်းအကြောင်းကို အတိုချုံးစာတမ်းရေးပါ။ ဂိမ်းသည် ကွန်ပျူတာလုပ်ဆောင်မှုစနစ်အမျိုးမျိုး၏ သက်ရောက်မှုကို ရရှိခဲ့သော ရှေးဟောင်းဂိမ်းတစ်ခုဖြစ်ရမည်။ ကောင်းသော ဥပမာများမှာ Chess သို့မဟုတ် Go ဖြစ်ပြီး pong သို့မဟုတ် Pac-Man ကဲ့သို့သော ဗီဒီယိုဂိမ်းများကိုလည်း ကြည့်ပါ။ ဂိမ်း၏ အတိတ်၊ ပစ္စုပ္ပန်နှင့် AI အနာဂတ်ကို ဆွေးနွေးသော စာတမ်းရေးပါ။
|
||||
|
|
|
|||
|
|
@ -1,15 +1,6 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
|
||||
"translation_date": "2026-01-16T06:18:19+00:00",
|
||||
"source_file": "lessons/2-Symbolic/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အသိပညာ ကိုယ်စားပြုခြင်းနှင့် ကျွမ်းကျင်သူ စနစ်များ
|
||||
|
||||
|
||||
|
||||
|
||||
> Sketchnote ကို [Tomomi Imura](https://twitter.com/girlie_mac) က ဖန်တီးထားသည်။
|
||||
|
||||
|
|
@ -42,7 +33,7 @@ Symbolic AI တွင် အရေးကြီးသော အယူအဆတစ
|
|||
|
||||
ထို့ကြောင့် **အသိပညာ ကိုယ်စားပြုခြင်း** ပြဿနာမှာ ကွန်ပျူတာထဲတွင် ဒေတာ ပုံစံဖြင့် အသိပညာကို ထိရောက်စွာ ကိုယ်စားပြုနိုင်ရန် နည်းလမ်းတစ်ခု ရှာဖွေခြင်း ဖြစ်သည်။ ၎င်းကို အောက်ပါအတိုင်း အမျိုးအစားများဖြင့် ဖော်ပြနိုင်သည် -
|
||||
|
||||
|
||||
|
||||
|
||||
> ပုံကို [Dmitry Soshnikov](http://soshnikov.com) ဖန်တီးသည်
|
||||
|
||||
|
|
@ -95,7 +86,7 @@ Block သဘောစနစ် | Indent | | |
|
|||
|
||||
Symbolic AI ၏ အစောပိုင်း အောင်မြင်မှုတစ်ခုမှာ **ကျွမ်းကျင်သူစနစ်များ** ဖြစ်သည် - အခြေအနေ တစ်ခုပေါ်တွင် ကျွမ်းကျင်သူတစ်ယောက်ကဲ့သို့ အလုပ်လုပ်နိုင်သော ကွန်ပျူတာစနစ်များ ဖြစ်သည်။ ၎င်းတို့သည် လူကြီးကျွမ်းကျင်သူတစ်ဦး သို့မဟုတ် ရှုပ်ထွေးမှုတစ်ခုပေါ်အခြေခံ၍ နှစ်ဆစ်စုထားခြင်းဖြစ်သော **သိမြင်မှု ဘဏ် (knowledge base)** ပါဝင်ပြီး၊ ၎င်း အပေါ်တွင် အချို့ ထုတ်ဖော်စဉ်းစားမှု လုပ်ဆောင်သော **inference engine** ပါဝင်သည်။
|
||||
|
||||
 | 
|
||||
 | 
|
||||
---------------------------------------------|------------------------------------------------
|
||||
လူမျိုးနာရးစနစ်၏ ရိုးရှင်းသည့် ဖွဲ့စည်းမှု | အသိပညာ အခြေပြုစနစ်၏ ဖွဲ့စည်းမှု
|
||||
|
||||
|
|
@ -107,7 +98,7 @@ Symbolic AI ၏ အစောပိုင်း အောင်မြင်မှ
|
|||
|
||||
ဥပမာ အဖြစ်၊ တိရစ္ဆာန်ကို ထူးခြားသော ရုပ်ပိုင်းဆိုင်ရာလက္ခဏာများအရ သတ်မှတ်ရန် ဤအောက်ပါ ကျွမ်းကျင်သူစနစ်ကို တွေးကြည့်ပါ -
|
||||
|
||||
|
||||
|
||||
|
||||
> ပုံကို [Dmitry Soshnikov](http://soshnikov.com) ဖန်တီးသည်
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a057a8604f3976c3e309884453f1fad0",
|
||||
"translation_date": "2025-08-26T00:34:40+00:00",
|
||||
"source_file": "lessons/2-Symbolic/assignment.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အွန်တိုလိုဂျီ တည်ဆောက်ခြင်း
|
||||
|
||||
အသိပညာအခြေခံကို တည်ဆောက်ခြင်းသည် တစ်ခုသော ခေါင်းစဉ်နှင့် ပတ်သက်သော အချက်အလက်များကို ကိုယ်စားပြုထားသော မော်ဒယ်ကို အမျိုးအစားခွဲခြင်းနှင့် ဆိုင်သည်။ လူတစ်ဦး၊ နေရာတစ်ခု သို့မဟုတ် အရာဝတ္ထုတစ်ခုကဲ့သို့သော ခေါင်းစဉ်တစ်ခုကို ရွေးချယ်ပြီး ထိုခေါင်းစဉ်၏ မော်ဒယ်ကို တည်ဆောက်ပါ။ ဒီသင်ခန်းစာတွင် ဖော်ပြထားသော နည်းလမ်းများနှင့် မော်ဒယ်တည်ဆောက်မှု မဟာဗျူဟာများကို အသုံးပြုပါ။ ဥပမာအားဖြင့်၊ ပရိဘောဂများ၊ မီးအလင်းများ စသဖြင့် ပါဝင်သော ဧည့်ခန်းတစ်ခန်း၏ အွန်တိုလိုဂျီတစ်ခုကို ဖန်တီးခြင်းဖြစ်နိုင်သည်။ ဧည့်ခန်းသည် မီးဖိုချောင်နှင့် ဘယ်လိုကွာခြားသလဲ။ ရေချိုးခန်းနဲ့ရော? ဧည့်ခန်းဟာ ဘာကြောင့် ထမင်းစားခန်းမဟုတ်ဘူးလို့ သိနိုင်သလဲ? သင့်အွန်တိုလိုဂျီကို တည်ဆောက်ရန် [Protégé](https://protege.stanford.edu/) ကို အသုံးပြုပါ။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
|
||||
"translation_date": "2025-09-23T15:22:42+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# နယူးရယ်နက်ဝက်များအကြောင်း: Perceptron
|
||||
|
||||
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/5)
|
||||
|
|
@ -15,7 +6,7 @@ CO_OP_TRANSLATOR_METADATA:
|
|||
|
||||
| | |
|
||||
|--------------|-----------|
|
||||
|<img src='images/Rosenblatt-wikipedia.jpg' alt='Frank Rosenblatt'/> | <img src='images/Mark_I_perceptron_wikipedia.jpg' alt='The Mark 1 Perceptron' />|
|
||||
|<img src='../../../../../translated_images/my/Rosenblatt-wikipedia.294821b285ac796d.webp' alt='Frank Rosenblatt'/> | <img src='../../../../../translated_images/my/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp' alt='The Mark 1 Perceptron' />|
|
||||
|
||||
> ပုံများ [Wikipedia မှ](https://en.wikipedia.org/wiki/Perceptron)
|
||||
|
||||
|
|
@ -34,7 +25,7 @@ y(x) = f(w<sup>T</sup>x)
|
|||
f ဟာ step activation function ဖြစ်ပါတယ်။
|
||||
|
||||
<!-- img src="http://www.sciweavers.org/tex2img.php?eq=f%28x%29%20%3D%20%5Cbegin%7Bcases%7D%0A%20%20%20%20%20%20%20%20%20%2B1%20%26%20x%20%5Cgeq%200%20%5C%5C%0A%20%20%20%20%20%20%20%20%20-1%20%26%20x%20%3C%200%0A%20%20%20%20%20%20%20%5Cend%7Bcases%7D%20%5C%5C%0A&bc=White&fc=Black&im=jpg&fs=12&ff=arev&edit=0" align="center" border="0" alt="f(x) = \begin{cases} +1 & x \geq 0 \\ -1 & x < 0 \end{cases} \\" width="154" height="50" / -->
|
||||
<img src="images/activation-func.png"/>
|
||||
<img src="../../../../../translated_images/my/activation-func.b4924007c7ce7764.webp"/>
|
||||
|
||||
## Perceptron ကို Training လုပ်ခြင်း
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
|
||||
"translation_date": "2025-08-30T08:46:51+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Multi-Class Classification with Perceptron
|
||||
|
||||
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
|
||||
"translation_date": "2025-09-23T15:22:12+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# နယူးရယ်နက်ဝါ့ခ်များကို မိတ်ဆက်ခြင်း။ Multi-Layered Perceptron
|
||||
|
||||
ယခင်အပိုင်းတွင် သင်သည် အလွယ်ဆုံး နယူးရယ်နက်ဝါ့ခ် မော်ဒယ် - တစ်လွှာတည်းရှိသော perceptron, linear two-class classification မော်ဒယ်ကို လေ့လာခဲ့ပါသည်။
|
||||
|
|
@ -66,7 +57,7 @@ Gradient descent algorithm သည် အတူတူပင်ဖြစ်သေ
|
|||
|
||||
ဤ expression များ၏ ဘယ်ဘက်ဆုံးအပိုင်းသည် အတူတူဖြစ်ပြီး loss function မှ စတင်၍ computational graph ကို "နောက်ပြန်" သွားသောအတိုင်း derivatives တွက်ချက်နိုင်သည်။ ထို့ကြောင့် multi-layered perceptron training နည်းလမ်းကို **backpropagation** သို့မဟုတ် 'backprop' ဟုခေါ်သည်။
|
||||
|
||||
<img alt="compute graph" src="images/ComputeGraphGrad.png"/>
|
||||
<img alt="compute graph" src="../../../../../translated_images/my/ComputeGraphGrad.4626252c0de03507.webp"/>
|
||||
|
||||
> TODO: image citation
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
|
||||
"translation_date": "2025-08-25T23:49:41+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# MNIST ကိုယ်တိုင်ဖွဲ့စည်းထားသော Framework ဖြင့် ခွဲခြားခြင်း
|
||||
|
||||
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ddd216f558a255260a9374008002c971",
|
||||
"translation_date": "2025-09-23T15:23:03+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Neural Network Frameworks
|
||||
|
||||
ကျွန်ုပ်တို့သိရှိပြီးသားအတိုင်း၊ နယူးရယ်နက်ဝက်များကို ထိရောက်စွာလေ့ကျင့်နိုင်ရန်အတွက် အောက်ပါအရာနှစ်ခုကို လုပ်ဆောင်ရမည်ဖြစ်သည်-
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "e452d897efb9a89700f41021834cf6e5",
|
||||
"translation_date": "2025-08-25T23:56:22+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# PyTorch/TensorFlow ဖြင့် အမျိုးအစားခွဲခြားခြင်း
|
||||
|
||||
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
|
||||
"translation_date": "2025-10-03T12:54:28+00:00",
|
||||
"source_file": "lessons/3-NeuralNetworks/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# နယူးရယ်နက်ဝါ့ခ်များအကြောင်း အကျဉ်းချုပ်
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "feeca98225cb420afc89415f24f63d92",
|
||||
"translation_date": "2025-09-23T15:15:24+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# ကွန်ပျူတာဗီရှင်းအကြောင်းမိတ်ဆက်
|
||||
|
||||
[ကွန်ပျူတာဗီရှင်း](https://wikipedia.org/wiki/Computer_vision) ဆိုတာက ကွန်ပျူတာတွေကို ဒစ်ဂျစ်တယ်ပုံရိပ်တွေကို အဆင့်မြင့်နားလည်မှုရရှိစေဖို့ ရည်ရွယ်တဲ့ အပိုင်းတစ်ခုဖြစ်ပါတယ်။ ဒီအဓိပ္ပါယ်က အတော်လေးကျယ်ပြန့်ပါတယ်၊ အကြောင်းမူတည်ပြီး *နားလည်မှု* ဆိုတာ အမျိုးမျိုးဖြစ်နိုင်ပါတယ်။ ဥပမာအားဖြင့် ပုံထဲမှာ အရာဝတ္ထုတစ်ခုကို ရှာဖွေခြင်း (**object detection**), ဖြစ်ပျက်နေတဲ့အရာကို နားလည်ခြင်း (**event detection**), ပုံကို စာသားနဲ့ ဖော်ပြခြင်း, ဒါမှမဟုတ် 3D အနေအထားနဲ့ ရှုခင်းကို ပြန်လည်တည်ဆောက်ခြင်း။ လူနဲ့ဆိုင်တဲ့ ပုံရိပ်တွေကို အထူးလုပ်ငန်းတွေပါရှိပါတယ် - အသက်အရွယ်နဲ့ ခံစားချက်ခန့်မှန်းခြင်း, မျက်နှာရှာဖွေခြင်းနဲ့ မှတ်ပုံတင်ခြင်း, 3D အနေအထားခန့်မှန်းခြင်း စသည်ဖြင့်။
|
||||
|
|
@ -117,7 +108,7 @@ Optical flow အကြောင်းကို [ဒီအလွန်ကော
|
|||
|
||||
ဒီ lab မှာ လက်သွားလက်လာရဲ့ ဗီဒီယိုကို ရိုက်ကူးပြီး optical flow ကို အသုံးပြုပြီး အပေါ်/အောက်/ဘယ်/ညာ လှုပ်ရှားမှုတွေကို ရှာဖွေဖို့ ရည်ရွယ်ပါတယ်။
|
||||
|
||||
<img src="images/palm-movement.png" width="30%" alt="Palm Movement Frame"/>
|
||||
<img src="../../../../../translated_images/my/palm-movement.341495f0e9c47da3.webp" width="30%" alt="Palm Movement Frame"/>
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "3d53d6409f80970f7281a45dee35328a",
|
||||
"translation_date": "2025-08-25T23:06:15+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Optical Flow ကို အသုံးပြု၍ လှုပ်ရှားမှုများကို ရှာဖွေခြင်း
|
||||
|
||||
[AI for Beginners Curriculum](https://aka.ms/ai-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
|
||||
"translation_date": "2025-09-23T15:14:34+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# လူသိများသော CNN အဆောက်အအုံများ
|
||||
|
||||
### VGG-16
|
||||
|
|
@ -25,7 +16,7 @@ VGG သည် convolution-pooling layers များ၏ အစဉ်အတိ
|
|||
|
||||
ResNet သည် Microsoft Research မှ 2015 ခုနှစ်တွင် တင်ပြခဲ့သော model များ၏ မိသားစုဖြစ်သည်။ ResNet ၏ အဓိကအကြောင်းအရာမှာ **residual blocks** ကို အသုံးပြုခြင်းဖြစ်သည်-
|
||||
|
||||
<img src="images/resnet-block.png" width="300"/>
|
||||
<img src="../../../../../translated_images/my/resnet-block.aba4ccbcc0944434.webp" width="300"/>
|
||||
|
||||
> [ဒီစာတမ်း](https://arxiv.org/pdf/1512.03385.pdf) မှရရှိသော ပုံ
|
||||
|
||||
|
|
@ -37,7 +28,7 @@ Identity pass-through ကို အသုံးပြုရသည့် အက
|
|||
|
||||
Google Inception architecture သည် ဤအကြောင်းအရာကို တစ်ဆင့်ပိုမိုတိုးတက်စေပြီး network layer တစ်ခုစီကို path များစွာ၏ ပေါင်းစပ်အဖြစ် တည်ဆောက်သည်-
|
||||
|
||||
<img src="images/inception.png" width="400"/>
|
||||
<img src="../../../../../translated_images/my/inception.a6605b85bcbc6f52.webp" width="400"/>
|
||||
|
||||
> [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) မှရရှိသော ပုံ
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "a560d5b845962cf33dc102266e409568",
|
||||
"translation_date": "2025-09-23T15:14:13+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Convolutional Neural Networks
|
||||
|
||||
မကြာသေးမီက ကျွန်တော်တို့ neural networks တွေဟာ ပုံတွေကို ကောင်းကောင်းကိုင်တွယ်နိုင်ပြီး၊ တစ်လွှာတည်းသော perceptron ကတောင် MNIST dataset ထဲက လက်ရေးအက္ခရာဂဏန်းတွေကို တော်တော်လေးတိကျမှုရှိရှိနဲ့ မှတ်မိနိုင်တယ်ဆိုတာကို မြင်ခဲ့ပါတယ်။ သို့သော်လည်း MNIST dataset ဟာ အထူးတလည်ဖြစ်ပြီး၊ အက္ခရာဂဏန်းတွေဟာ ပုံထဲမှာ အလယ်မှာထားရှိထားတာကြောင့် အလုပ်ကို ပိုမိုလွယ်ကူစေပါတယ်။
|
||||
|
|
@ -24,7 +15,7 @@ Patterns တွေကို ရှာဖွေဖို့ **convolutional filte
|
|||
|
||||
ဥပမာ၊ MNIST digits တွေကို 3x3 vertical edge နဲ့ horizontal edge filters တွေကို အသုံးပြုရင်၊ မူရင်းပုံထဲမှာ vertical နဲ့ horizontal edges ရှိတဲ့နေရာတွေမှာ highlight (ဥပမာ high values) တွေကို ရနိုင်ပါတယ်။ ဒါကြောင့် အဲဒီ filter နှစ်ခုကို edges တွေကို "ရှာဖွေ"ဖို့ အသုံးပြုနိုင်ပါတယ်။ အဲဒီလိုပဲ၊ အခြား low-level patterns တွေကို ရှာဖွေဖို့ filter တွေကို design လုပ်နိုင်ပါတယ်။
|
||||
|
||||
<img src="images/lmfilters.jpg" width="500" align="center"/>
|
||||
<img src="../../../../../translated_images/my/lmfilters.ea9e4868a82cf74c.webp" width="500" align="center"/>
|
||||
|
||||
> Image of [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "b70fcf7fcee862990f848c679090943f",
|
||||
"translation_date": "2025-10-03T14:58:29+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အိမ်မွေးတိရစ္ဆာန်မျက်နှာများ အမျိုးအစားခွဲခြားခြင်း
|
||||
|
||||
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
|
||||
"translation_date": "2025-09-23T15:14:56+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Pre-trained Networks and Transfer Learning
|
||||
|
||||
CNN များကို သင်ကြားရန် အချိန်များစွာ လိုအပ်ပြီး အချက်အလက်များစွာ လိုအပ်ပါသည်။ သို့သော် အချိန်အများစုမှာ ပုံများမှ pattern များကို ထုတ်ယူရန် အသုံးပြုနိုင်သော အနိမ့်အဆင့် filter များကို သင်ယူရန် အသုံးပြုသည်။ သဘာဝအတိုင်း မေးခွန်းတစ်ခု ထွက်ပေါ်လာသည် - တစ်ခုသော dataset တွင် သင်ကြားထားသော neural network ကို အသုံးပြု၍ အခြားပုံများကို အပြည့်အဝ သင်ကြားမှုမလိုအပ်ဘဲ ခွဲခြားနိုင်မည်လား?
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
|
||||
"translation_date": "2025-08-25T23:15:43+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# အနက်ရှိုင်းသော သင်ကြားမှု လေ့ကျင့်မှု နည်းလမ်းများ
|
||||
|
||||
နယူးရယ်နက်ဝက်များ ပိုမိုနက်ရှိုင်းလာသည်နှင့်အမျှ၊ ၎င်းတို့ကို လေ့ကျင့်ခြင်းလုပ်ငန်းစဉ်သည် ပိုမိုခက်ခဲလာသည်။ အဓိကပြဿနာတစ်ခုမှာ [vanishing gradients](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) သို့မဟုတ် [exploding gradients](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.) ဖြစ်သည်။ [ဒီပို့စ်](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) သည် ၎င်းပြဿနာများအပေါ် အကျဉ်းချုပ်ကောင်းတစ်ခုကို ပေးသည်။
|
||||
|
|
|
|||
|
|
@ -1,12 +1,3 @@
|
|||
<!--
|
||||
CO_OP_TRANSLATOR_METADATA:
|
||||
{
|
||||
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
|
||||
"translation_date": "2025-08-25T23:17:32+00:00",
|
||||
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
|
||||
"language_code": "my"
|
||||
}
|
||||
-->
|
||||
# Oxford အိမ်မွေးတိရစ္ဆာန်များကို Transfer Learning အသုံးပြု၍ ခွဲခြားခြင်း
|
||||
|
||||
[AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) မှ Lab Assignment။
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue