RomanNum3ral
/
AI-For-Beginners
mirror of https://github.com/microsoft/AI-For-Beginners.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

chore(i18n): sync translations with latest source changes (chunk 1/1, 201 changes)

This commit is contained in:
localizeflow[bot] 2026-01-30 02:00:53 +00:00
parent 33ce0e5757
commit c55d809b23
201 changed files with 1532 additions and 2117 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

398
translations/da/.co-op-translator.json Normal file
View File

@ -0,0 +1,398 @@
{
"AGENTS.md": {
"original_hash": "6b11a37115944252ab3ed04e358d830d",
"translation_date": "2025-10-03T09:23:12+00:00",
"source_file": "AGENTS.md",
"language_code": "da"
},
"README.md": {
"original_hash": "1984fc89dd304a8a33ab5584691a99aa",
"translation_date": "2026-01-30T02:00:41+00:00",
"source_file": "README.md",
"language_code": "da"
},
"SECURITY.md": {
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
"translation_date": "2025-08-28T15:01:47+00:00",
"source_file": "SECURITY.md",
"language_code": "da"
},
"etc/CODE_OF_CONDUCT.md": {
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
"translation_date": "2025-08-28T16:06:55+00:00",
"source_file": "etc/CODE_OF_CONDUCT.md",
"language_code": "da"
},
"etc/CONTRIBUTING.md": {
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
"translation_date": "2025-08-28T16:06:34+00:00",
"source_file": "etc/CONTRIBUTING.md",
"language_code": "da"
},
"etc/Mindmap.md": {
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
"translation_date": "2025-08-28T16:05:02+00:00",
"source_file": "etc/Mindmap.md",
"language_code": "da"
},
"etc/SUPPORT.md": {
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
"translation_date": "2025-08-28T16:04:01+00:00",
"source_file": "etc/SUPPORT.md",
"language_code": "da"
},
"etc/TRANSLATIONS.md": {
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
"translation_date": "2025-08-28T16:06:05+00:00",
"source_file": "etc/TRANSLATIONS.md",
"language_code": "da"
},
"etc/quiz-app/README.md": {
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
"translation_date": "2025-08-28T16:07:27+00:00",
"source_file": "etc/quiz-app/README.md",
"language_code": "da"
},
"examples/README.md": {
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
"translation_date": "2025-10-03T11:31:26+00:00",
"source_file": "examples/README.md",
"language_code": "da"
},
"lessons/0-course-setup/for-teachers.md": {
"original_hash": "a094ef9927883de1cfcee51dbd143381",
"translation_date": "2025-08-28T15:08:06+00:00",
"source_file": "lessons/0-course-setup/for-teachers.md",
"language_code": "da"
},
"lessons/0-course-setup/how-to-run.md": {
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
"translation_date": "2026-01-16T02:27:08+00:00",
"source_file": "lessons/0-course-setup/how-to-run.md",
"language_code": "da"
},
"lessons/0-course-setup/setup.md": {
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
"translation_date": "2025-12-12T19:51:59+00:00",
"source_file": "lessons/0-course-setup/setup.md",
"language_code": "da"
},
"lessons/1-Intro/README.md": {
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
"translation_date": "2025-11-18T21:33:49+00:00",
"source_file": "lessons/1-Intro/README.md",
"language_code": "da"
},
"lessons/1-Intro/assignment.md": {
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
"translation_date": "2025-11-18T21:35:07+00:00",
"source_file": "lessons/1-Intro/assignment.md",
"language_code": "da"
},
"lessons/2-Symbolic/README.md": {
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
"translation_date": "2026-01-16T02:28:23+00:00",
"source_file": "lessons/2-Symbolic/README.md",
"language_code": "da"
},
"lessons/2-Symbolic/assignment.md": {
"original_hash": "a057a8604f3976c3e309884453f1fad0",
"translation_date": "2025-08-28T15:31:00+00:00",
"source_file": "lessons/2-Symbolic/assignment.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/03-Perceptron/README.md": {
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
"translation_date": "2025-09-23T09:33:47+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
"translation_date": "2025-08-29T08:29:22+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
"translation_date": "2025-09-23T09:33:13+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
"translation_date": "2025-08-28T15:38:12+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/05-Frameworks/README.md": {
"original_hash": "ddd216f558a255260a9374008002c971",
"translation_date": "2025-09-23T09:34:04+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
"original_hash": "e452d897efb9a89700f41021834cf6e5",
"translation_date": "2025-08-28T15:42:04+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
"language_code": "da"
},
"lessons/3-NeuralNetworks/README.md": {
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
"translation_date": "2025-10-03T12:49:32+00:00",
"source_file": "lessons/3-NeuralNetworks/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/06-IntroCV/README.md": {
"original_hash": "feeca98225cb420afc89415f24f63d92",
"translation_date": "2025-09-23T09:29:06+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
"original_hash": "3d53d6409f80970f7281a45dee35328a",
"translation_date": "2025-08-28T15:20:13+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
"translation_date": "2025-09-23T09:28:10+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
"language_code": "da"
},
"lessons/4-ComputerVision/07-ConvNets/README.md": {
"original_hash": "a560d5b845962cf33dc102266e409568",
"translation_date": "2025-09-23T09:27:53+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
"original_hash": "b70fcf7fcee862990f848c679090943f",
"translation_date": "2025-10-03T14:55:29+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/08-TransferLearning/README.md": {
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
"translation_date": "2025-09-23T09:28:36+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
"translation_date": "2025-08-28T15:16:24+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
"language_code": "da"
},
"lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
"translation_date": "2025-08-28T15:17:52+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/09-Autoencoders/README.md": {
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
"translation_date": "2025-09-23T09:30:20+00:00",
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/10-GANs/README.md": {
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
"translation_date": "2025-09-23T09:31:05+00:00",
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/11-ObjectDetection/README.md": {
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
"translation_date": "2025-09-23T09:29:37+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
"translation_date": "2025-08-28T15:23:12+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/12-Segmentation/README.md": {
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
"translation_date": "2025-09-23T09:30:50+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
"translation_date": "2025-08-28T15:26:02+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
"language_code": "da"
},
"lessons/4-ComputerVision/README.md": {
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
"translation_date": "2025-08-28T15:11:46+00:00",
"source_file": "lessons/4-ComputerVision/README.md",
"language_code": "da"
},
"lessons/5-NLP/13-TextRep/README.md": {
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
"translation_date": "2025-09-23T09:37:09+00:00",
"source_file": "lessons/5-NLP/13-TextRep/README.md",
"language_code": "da"
},
"lessons/5-NLP/13-TextRep/assignment.md": {
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
"translation_date": "2025-08-28T16:03:41+00:00",
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
"language_code": "da"
},
"lessons/5-NLP/14-Embeddings/README.md": {
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
"translation_date": "2025-09-23T09:36:45+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
"language_code": "da"
},
"lessons/5-NLP/14-Embeddings/assignment.md": {
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
"translation_date": "2025-08-28T16:02:00+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
"language_code": "da"
},
"lessons/5-NLP/15-LanguageModeling/README.md": {
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
"translation_date": "2025-09-23T09:34:48+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
"language_code": "da"
},
"lessons/5-NLP/15-LanguageModeling/lab/README.md": {
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
"translation_date": "2025-08-28T15:54:06+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
"language_code": "da"
},
"lessons/5-NLP/16-RNN/README.md": {
"original_hash": "e2273cc150380a5e191903cea858f021",
"translation_date": "2025-09-23T09:36:15+00:00",
"source_file": "lessons/5-NLP/16-RNN/README.md",
"language_code": "da"
},
"lessons/5-NLP/16-RNN/assignment.md": {
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
"translation_date": "2025-08-28T16:00:34+00:00",
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
"language_code": "da"
},
"lessons/5-NLP/17-GenerativeNetworks/README.md": {
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
"translation_date": "2025-09-23T09:34:27+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
"language_code": "da"
},
"lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
"translation_date": "2025-08-28T15:53:04+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
"language_code": "da"
},
"lessons/5-NLP/18-Transformers/README.md": {
"original_hash": "f335dfcb4a993920504c387973a36957",
"translation_date": "2025-09-23T09:35:02+00:00",
"source_file": "lessons/5-NLP/18-Transformers/README.md",
"language_code": "da"
},
"lessons/5-NLP/18-Transformers/assignment.md": {
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
"translation_date": "2025-08-28T15:55:53+00:00",
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
"language_code": "da"
},
"lessons/5-NLP/19-NER/README.md": {
"original_hash": "6522312ff835796ca34136a9462fafb2",
"translation_date": "2025-09-23T09:35:57+00:00",
"source_file": "lessons/5-NLP/19-NER/README.md",
"language_code": "da"
},
"lessons/5-NLP/19-NER/lab/README.md": {
"original_hash": "032bda5068f543d6c1fcb30c34231461",
"translation_date": "2025-08-28T15:58:16+00:00",
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
"language_code": "da"
},
"lessons/5-NLP/20-LangModels/README.md": {
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
"translation_date": "2025-09-23T09:35:38+00:00",
"source_file": "lessons/5-NLP/20-LangModels/README.md",
"language_code": "da"
},
"lessons/5-NLP/README.md": {
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
"translation_date": "2025-08-28T15:51:00+00:00",
"source_file": "lessons/5-NLP/README.md",
"language_code": "da"
},
"lessons/6-Other/21-GeneticAlgorithms/README.md": {
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
"translation_date": "2025-09-23T09:26:28+00:00",
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
"language_code": "da"
},
"lessons/6-Other/22-DeepRL/README.md": {
"original_hash": "04395657fc01648f8f70484d0e55ab67",
"translation_date": "2025-09-23T09:27:25+00:00",
"source_file": "lessons/6-Other/22-DeepRL/README.md",
"language_code": "da"
},
"lessons/6-Other/22-DeepRL/lab/README.md": {
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
"translation_date": "2025-08-28T15:07:40+00:00",
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
"language_code": "da"
},
"lessons/6-Other/23-MultiagentSystems/README.md": {
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
"translation_date": "2025-09-23T09:26:42+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
"language_code": "da"
},
"lessons/6-Other/23-MultiagentSystems/assignment.md": {
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
"translation_date": "2025-08-28T15:05:53+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
"language_code": "da"
},
"lessons/7-Ethics/README.md": {
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
"translation_date": "2025-08-28T15:31:28+00:00",
"source_file": "lessons/7-Ethics/README.md",
"language_code": "da"
},
"lessons/README.md": {
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
"translation_date": "2025-08-28T15:02:19+00:00",
"source_file": "lessons/README.md",
"language_code": "da"
},
"lessons/X-Extras/X1-MultiModal/README.md": {
"original_hash": "9c592c26aca16ca085d268c732284187",
"translation_date": "2025-08-28T15:10:45+00:00",
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
"language_code": "da"
},
"lessons/sketchnotes/LICENSE.md": {
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
"translation_date": "2025-08-28T15:46:18+00:00",
"source_file": "lessons/sketchnotes/LICENSE.md",
"language_code": "da"
},
"lessons/sketchnotes/README.md": {
"original_hash": "050b8bddebafba55b129414e6ab096ab",
"translation_date": "2025-08-28T15:42:23+00:00",
"source_file": "lessons/sketchnotes/README.md",
"language_code": "da"
},
"troubleshoot.md": {
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
"translation_date": "2025-10-03T09:45:25+00:00",
"source_file": "troubleshoot.md",
"language_code": "da"
}
}

9
translations/da/AGENTS.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "6b11a37115944252ab3ed04e358d830d",
"translation_date": "2025-10-03T09:23:12+00:00",
"source_file": "AGENTS.md",
"language_code": "da"
}
-->
# AGENTS.md
## Projektoversigt

152
translations/da/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "85102ce4bfab31103e99dc8ca2e2f181",
"translation_date": "2026-01-16T02:25:12+00:00",
"source_file": "README.md",
"language_code": "da"
}
-->
[![GitHub license](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[![GitHub issues](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@ -21,13 +12,13 @@ CO_OP_TRANSLATOR_METADATA:
[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG)
# Kunstig Intelligens for Begyndere - Et Kursusprogram
# Kunstig Intelligens for Begyndere - Et Læseplan
|![Sketchnote by @girlie_mac https://twitter.com/girlie_mac](../../../../translated_images/da/ai-overview.0857791951d19500.webp)|
|![Sketchnote by @girlie_mac https://twitter.com/girlie_mac](../../translated_images/da/ai-overview.0857791951d19500.webp)|
|:---:|
| AI For Beginners - _Sketchnote af [@girlie_mac](https://twitter.com/girlie_mac)_ |
Udforsk verdenen af **Kunstig Intelligens** (AI) med vores 12-ugers, 24-lektioners kursusprogram! Det inkluderer praktiske lektioner, quizzer og laboratorier. Kursusprogrammet er begyndervenligt og dækker værktøjer som TensorFlow og PyTorch samt etik inden for AI.
Udforsk verdenen af **Kunstig Intelligens** (AI) med vores 12-ugers, 24-lektioners læseplan! Den inkluderer praktiske lektioner, quizzer og laboratorier. Læseplanen er begynder-venlig og dækker værktøjer som TensorFlow og PyTorch samt etik inden for AI.
### 🌐 Fleresproget Support
@ -35,111 +26,112 @@ Udforsk verdenen af **Kunstig Intelligens** (AI) med vores 12-ugers, 24-lektione
#### Understøttet via GitHub Action (Automatiseret & Altid Opdateret)
<!-- CO-OP TRANSLATOR LANGUAGES TABLE START -->
[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](./README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md)
[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-TW/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](./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)
> **Foretrækker du at klone lokalt?**
> Dette repository inkluderer 50+ sprogoversættelser, som væsentligt øger downloadstørrelsen. For at klone uden oversættelser, brug spars_checkout:
> Dette repository inkluderer 50+ sprogoversættelser, hvilket i væsentlig grad øger downloadstørrelsen. For at klone uden oversættelser, brug 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'
> ```
> Dette giver dig alt, hvad du behøver for at gennemføre kurset med en meget hurtigere download.
> Dette giver dig alt, hvad du behøver for at gennemføre kurset med en langt hurtigere download.
<!-- CO-OP TRANSLATOR LANGUAGES TABLE END -->
**Hvis du ønsker, at yderligere oversættelsessprog understøttes, er de listet [her](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
**Hvis du ønsker yderligere sprogunderstøttelse, er de understøttede sprog listet [her](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Deltag i fællesskabet
[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG)
## Hvad du vil lære
**[Mindmap af Kurset](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
**[Mindmap for Kurset](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
I dette kursusprogram vil du lære:
I denne læseplan vil du lære:
* Forskellige tilgange til Kunstig Intelligens, inklusive den "gode gamle" symbolske tilgang med **Videnrepræsentation** og ræsonnering ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
* **Neurale Netværk** og **Deep Learning**, som er kernen i moderne AI. Vi vil illustrere begreberne bag disse vigtige emner ved brug af kode i to af de mest populære frameworks - [TensorFlow](http://Tensorflow.org) og [PyTorch](http://pytorch.org).
* **Neurale Arkitekturer** til arbejde med billeder og tekst. Vi vil dække nyere modeller, men kan være en smule mangelfulde i forhold til det nyeste og mest avancerede.
* Forskellige tilgange til Kunstig Intelligens, inklusive den "gamle gode" symbolske tilgang med **Vidensrepræsentation** og ræsonnering ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
* **Neurale Netværk** og **Deep Learning**, som er kernen i moderne AI. Vi vil illustrere begreberne bag disse vigtige emner ved hjælp af kode i to af de mest populære frameworks - [TensorFlow](http://Tensorflow.org) og [PyTorch](http://pytorch.org).
* **Neurale Arkitekturer** til arbejde med billeder og tekst. Vi dækker nyere modeller, men kan være lidt mangelfulde med hensyn til state-of-the-art.
* Mindre populære AI-tilgange, såsom **Genetiske Algoritmer** og **Multi-Agent Systemer**.
Hvad vi ikke vil dække i dette kursusprogram:
Hvad vi ikke dækker i denne læseplan:
> [Find alle yderligere ressourcer til dette kursus i vores Microsoft Learn samling](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
> [Find alle yderligere ressourcer til dette kursus i vores Microsoft Learn-kollektion](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
* Forretningscases for brug af **AI i forretning**. Overvej at tage [Introduktion til AI for forretningsbrugere](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) læringssti på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), udviklet i samarbejde med [INSEAD](https://www.insead.edu/).
* **Klassisk Maskinlæring**, som er godt beskrevet i vores [Maskinlæring for Begyndere Kursusprogram](http://github.com/Microsoft/ML-for-Beginners).
* Praktiske AI-applikationer bygget ved hjælp af **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Til dette anbefaler vi, at du starter med moduler på Microsoft Learn om [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [naturlig sprogbehandling](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativ AI med Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** og andre.
* Specifikke ML **Cloud Frameworks**, såsom [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), eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Overvej at bruge læringsstierne [Byg og drift maskinlæringsløsninger med Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) og [Byg og drift maskinlæringsløsninger med Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
* **Samtale-baseret AI** og **Chat Bots**. Der findes en separat [Opret samtale-AI løsninger](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) læringssti, og du kan også henvise til [denne blogpost](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for flere detaljer.
* **Dyb matematik** bag deep learning. Til dette anbefaler vi [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) af Ian Goodfellow, Yoshua Bengio og Aaron Courville, som også er tilgængelig online på [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
* Business cases for brugen af **AI i Forretning**. Overvej at tage [Introduktion til AI for forretningsbrugere](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) læringssti på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), udviklet i samarbejde med [INSEAD](https://www.insead.edu/).
* **Klassisk Maskinlæring**, som er godt beskrevet i vores [Maskinlæring for Begyndere-læseplan](http://github.com/Microsoft/ML-for-Beginners).
* Praktiske AI-applikationer bygget ved hjælp af **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. For dette anbefaler vi, at du starter med moduler fra Microsoft Learn for [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [naturlig sprogbehandling](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativ AI med Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** og andre.
* Specifikke ML **Cloud Frameworks**, såsom [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), eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Overvej at bruge [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) og [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) læringsstier.
* **Samtale-AI** og **Chatbots**. Der findes en separat [Opret samtale-AI-løsninger](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) læringssti, og du kan også henvise til [dette blogindlæg](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for flere detaljer.
* **Dybtgående matematik** bag deep learning. Til dette anbefaler vi [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) af Ian Goodfellow, Yoshua Bengio og Aaron Courville, som også er tilgængelig online på [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
For en blid introduktion til _AI i skyen_ emner kan du overveje at tage [Kom godt i gang med kunstig intelligens på Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) læringssti.
For en blid introduktion til _AI i Skyen_ -emner kan du overveje at tage [Kom godt i gang med kunstig intelligens på Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) læringssti.
# Indhold
| | Lektion Link | PyTorch/Keras/TensorFlow | Laboratorium |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
| 0 | [Opsætning af Kurset](./lessons/0-course-setup/setup.md) | [Opsæt dit Udviklingsmiljø](./lessons/0-course-setup/how-to-run.md) | |
| 0 | [Kursusopsætning](./lessons/0-course-setup/setup.md) | [Opsæt dit udviklingsmiljø](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Introduktion til AI**](./lessons/1-Intro/README.md) | | |
| 01 | [Introduktion og Historie om AI](./lessons/1-Intro/README.md) | - | - |
| 01 | [Introduktion og historie om AI](./lessons/1-Intro/README.md) | - | - |
| II | **Symbolsk AI** |
| 02 | [Videnrepræsentation og Ekspertsystemer](./lessons/2-Symbolic/README.md) | [Ekspertsystemer](./lessons/2-Symbolic/Animals.ipynb) / [Ontologi](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Konceptgraf](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Introduktion til Neurale Netværk**](./lessons/3-NeuralNetworks/README.md) |||
| 02 | [Vidensrepræsentation og ekspertsystemer](./lessons/2-Symbolic/README.md) | [Ekspertsystemer](./lessons/2-Symbolic/Animals.ipynb) / [Ontologi](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Begrebsgraf](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Introduktion til neurale netværk**](./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) |
| 04 | [Multi-Layered Perceptron og oprettelse af vores eget 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 til frameworks (PyTorch/TensorFlow) og overfitting](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
| IV | [**Computer Vision**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Udforsk Computer Vision på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
| 06 | [Intro to Computer Vision. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
| 07 | [Convolutional Neural Networks](./lessons/4-ComputerVision/07-ConvNets/README.md) & [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 | [**Natural Language Processing**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Udforsk Natural Language Processing på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Text Representation. 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 | [Semantic word embeddings. Word2Vec and 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 | [Language Modeling. Training your own embeddings](./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) |
| 06 | [Intro til Computer Vision. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
| 07 | [Convolutional Neural Networks](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkitekturer](./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 | [Fortrænede netværk og transfer learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) og [Træningstricks](./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 og 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 & kunstnerisk stiloverførsel](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Objektdetektion](./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 | [Semantisk segmentering. 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 | [**Naturlig Sprogbehandling**](./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) | [Udforsk Naturlig Sprogbehandling på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Tekstrepræsentation. 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 | [Semantiske ord-embeddings. Word2Vec og 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 | [Sprogsmodellering. Træning af dine egne embeddings](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 16 | [Recurrent Neural Networks](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | |
| 17 | [Generative Recurrent Networks](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
| 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
| 19 | [Named Entity Recognition](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) |
| 20 | [Large Language Models, Prompt Programming and Few-Shot Tasks](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| 20 | [Store sprogmodeller, promptprogrammering og few-shot opgaver](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Andre AI-teknikker** || |
| 21 | [Genetic Algorithms](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
| 22 | [Deep Reinforcement Learning](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Multi-Agent Systems](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| 21 | [Genetiske algoritmer](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
| 22 | [Deep reinforcement learning](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Multi-agent systemer](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **AI-etik** | | |
| 24 | [AI Ethics and Responsible 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 | **Ekstra materiale** | | |
| 25 | [Multi-Modal Networks, CLIP and VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
| 24 | [AI-etik og ansvarligt AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Principper for ansvarligt AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
| IX | **Ekstra** | | |
| 25 | [Multi-modale netværk, CLIP og VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Hver lektion indeholder
* Forlæsningsmateriale
* Eksekverbare Jupyter-notebooks, som ofte er specifikke for frameworket (**PyTorch** eller **TensorFlow**). Den eksekverbare notebook indeholder også meget teoretisk materiale, så for at forstå emnet skal man igennem mindst én version af notebook’en (enten PyTorch eller TensorFlow).
* **Laboratorier** tilgængelige for nogle emner, som giver dig mulighed for at prøve at anvende det lærte materiale på et specifikt problem.
* Forudgående læsemateriale
* Eksekverbare Jupyter notebooks, som ofte er specifikke for frameworket (**PyTorch** eller **TensorFlow**). Den eksekverbare notebook indeholder også meget teoretisk materiale, så for at forstå emnet skal du gennemgå mindst én version af notebook'en (enten PyTorch eller TensorFlow).
* **Labs** tilgængelige for nogle emner, som giver dig mulighed for at prøve at anvende materialet, du har lært, på et specifikt problem.
* Nogle sektioner indeholder links til [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moduler, der dækker relaterede emner.
## Kom godt i gang
### 🎯 Ny til AI? Start her!
Hvis du er helt ny til AI og vil have hurtige, praktiske eksempler, så tjek vores [**Begyndervenlige eksempler**](./examples/README.md)! Disse inkluderer:
Hvis du er helt ny til AI og ønsker hurtige, praktiske eksempler, så kig på vores [**Begynder-venlige eksempler**](./examples/README.md)! Disse inkluderer:
- 🌟 **Hello AI World** - Dit første AI-program (mønster genkendelse)
- 🧠 **Simple Neural Network** - Byg et neuralt netværk fra bunden
- 🖼️ **Image Classifier** - Klassificer billeder med detaljerede kommentarer
- 💬 **Tekstfølelse** - Analyser positiv/negativ tekst
- 🌟 **Hej AI-verden** - Dit første AI-program (mønster-genkendelse)
- 🧠 **Simpelt neuralt netværk** - Byg et neuralt netværk fra bunden
Disse eksempler er designet til at hjælpe dig med at forstå AI-koncepter, før du dykker ned i det fulde pensum.
- 🖼️ **Billedklassifikator** - Klassificer billeder med detaljerede kommentarer
- 💬 **Tekst-sentiment** - Analyser positiv/negativ tekst
### 📚 Opsætning af hele pensum
Disse eksempler er designet til at hjælpe dig med at forstå AI-koncepter, inden du dykker ned i det fulde pensum.
- Vi har oprettet en [opsætningslektion](./lessons/0-course-setup/setup.md) for at hjælpe dig med at sætte dit udviklingsmiljø op. - For undervisere har vi også oprettet en [pensumopsætningslektion](./lessons/0-course-setup/for-teachers.md)!
- Sådan [kører du koden i VSCode eller en Codespace](./lessons/0-course-setup/how-to-run.md)
### 📚 Opsætning af det fulde pensum
- Vi har lavet en [opsætningslektion](./lessons/0-course-setup/setup.md) for at hjælpe dig med opsætningen af dit udviklingsmiljø. - For undervisere har vi også lavet en [pensumopsætningslektion](./lessons/0-course-setup/for-teachers.md)!
- Hvordan du [kører koden i VSCode eller en Codespace](./lessons/0-course-setup/how-to-run.md)
Følg disse trin:
@ -147,33 +139,33 @@ Fork Repository: Klik på knappen "Fork" øverst til højre på denne side.
Klon Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git`
Glem ikke at give denne repo en stjerne (🌟) for nemmere at finde den senere.
Glem ikke at give denne repo en stjerne (🌟), så du nemmere kan finde den senere.
## Mød andre lærende
Deltag i vores [officielle AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) for at møde og netværke med andre, der tager dette kursus, og få support.
Deltag i vores [officielle AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) for at møde og netværke med andre lærende, der tager dette kursus, og få støtte.
Hvis du har produktfeedback eller spørgsmål, mens du bygger, så besøg vores [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
Hvis du har feedback på produktet eller spørgsmål undervejs, besøg vores [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
## Quizzer
> **En note om quizzer**: Alle quizzer findes i Quiz-app mappen under etc\quiz-app, eller [Online her](https://ff-quizzes.netlify.app/) De er linket fra lektionerne, quiz-appen kan køre lokalt eller implementeres til Azure; følg instruktionerne i `quiz-app` mappen. De lokaliseres gradvist.
> **En note om quizzer**: Alle quizzer findes i Quiz-app mappen i etc\quiz-app, eller [Online Her](https://ff-quizzes.netlify.app/) De er linket fra lektionerne, quiz-appen kan køres lokalt eller deployeres til Azure; følg instruktionerne i `quiz-app` mappen. De bliver gradvist oversat.
## Hjælp ønskes
## Brug for hjælp
Har du forslag eller fundet stavefejl eller kodefejl? Opret et issue eller lav en pull request.
Har du forslag eller har fundet stave- eller kodefejl? Opret en issue eller et pull request.
## Særlige tak
## Speciel tak
* **✍️ Hovedforfatter:** [Dmitry Soshnikov](http://soshnikov.com), PhD
* **✍️ Primær forfatter:** [Dmitry Soshnikov](http://soshnikov.com), PhD
* **🔥 Redaktør:** [Jen Looper](https://twitter.com/jenlooper), PhD
* **🎨 Sketchnote illustrator:** [Tomomi Imura](https://twitter.com/girlie_mac)
* **✅ Quiz-skaber:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
* **🙏 Kernenbidragydere:** [Evgenii Pishchik](https://github.com/Pe4enIks)
* **✅ Quizskaber:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
* **🙏 Kernebidragydere:** [Evgenii Pishchik](https://github.com/Pe4enIks)
## Andre pensummer
## Andre pensumforløb
Vores team producerer andre pensummer! Tjek:
Vores team laver andre pensumforløb! Se her:
<!-- CO-OP TRANSLATOR OTHER COURSES START -->
### LangChain
@ -221,7 +213,7 @@ Hvis du sidder fast eller har spørgsmål om at bygge AI-apps. Deltag med andre
[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG)
Hvis du har produktfeedback eller fejl under udvikling, besøg:
Hvis du har produktfeedback eller fejl under udviklingen, besøg:
[![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum)
@ -229,5 +221,5 @@ Hvis du har produktfeedback eller fejl under udvikling, besøg:
<!-- CO-OP TRANSLATOR DISCLAIMER START -->
**Ansvarsfraskrivelse**:
Dette dokument er oversat ved hjælp af AI-oversættelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selvom vi bestræber os på nøjagtighed, bedes du være opmærksom på, at automatiserede oversættelser kan indeholde fejl eller unøjagtigheder. Det oprindelige dokument på dets oprindelige sprog bør betragtes som den autoritative kilde. For kritisk information anbefales professionel menneskelig oversættelse. Vi påtager os intet ansvar for misforståelser eller fejltolkninger, der opstår som følge af brugen af denne oversættelse.
Dette dokument er blevet oversat ved hjælp af AI-oversættelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selvom vi bestræber os på nøjagtighed, bedes du være opmærksom på, at automatiserede oversættelser kan indeholde fejl eller unøjagtigheder. Det oprindelige dokument på dets modersmål skal betragtes som den autoritative kilde. For kritiske oplysninger anbefales professionel menneskelig oversættelse. Vi påtager os intet ansvar for misforståelser eller fejltolkninger, der opstår som følge af brugen af denne oversættelse.
<!-- CO-OP TRANSLATOR DISCLAIMER END -->

9
translations/da/SECURITY.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
"translation_date": "2025-08-28T15:01:47+00:00",
"source_file": "SECURITY.md",
"language_code": "da"
}
-->
## Sikkerhed
Microsoft tager sikkerheden af vores softwareprodukter og -tjenester alvorligt, hvilket inkluderer alle kildekoderepositorier, der administreres gennem vores GitHub-organisationer, som inkluderer [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) og [vores GitHub-organisationer](https://opensource.microsoft.com/).

9
translations/da/etc/CODE_OF_CONDUCT.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
"translation_date": "2025-08-28T16:06:55+00:00",
"source_file": "etc/CODE_OF_CONDUCT.md",
"language_code": "da"
}
-->
# Microsoft Open Source Adfærdskodeks
Dette projekt har vedtaget [Microsoft Open Source Adfærdskodeks](https://opensource.microsoft.com/codeofconduct/).

9
translations/da/etc/CONTRIBUTING.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
"translation_date": "2025-08-28T16:06:34+00:00",
"source_file": "etc/CONTRIBUTING.md",
"language_code": "da"
}
-->
# Bidrag
Dette projekt byder velkommen til bidrag og forslag. De fleste bidrag kræver, at du accepterer en Contributor License Agreement (CLA), der erklærer, at du har retten til, og faktisk giver os rettighederne til at bruge dit bidrag. For detaljer, besøg https://cla.microsoft.com.

9
translations/da/etc/Mindmap.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
"translation_date": "2025-08-28T16:05:02+00:00",
"source_file": "etc/Mindmap.md",
"language_code": "da"
}
-->
# AI
## [Introduktion til AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)

9
translations/da/etc/SUPPORT.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
"translation_date": "2025-08-28T16:04:01+00:00",
"source_file": "etc/SUPPORT.md",
"language_code": "da"
}
-->
# Support
## Sådan indsender du problemer og får hjælp

9
translations/da/etc/TRANSLATIONS.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
"translation_date": "2025-08-28T16:06:05+00:00",
"source_file": "etc/TRANSLATIONS.md",
"language_code": "da"
}
-->
# Bidrag ved at oversætte lektioner
Vi byder velkommen til oversættelser af lektionerne i dette pensum!

9
translations/da/etc/quiz-app/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
"translation_date": "2025-08-28T16:07:27+00:00",
"source_file": "etc/quiz-app/README.md",
"language_code": "da"
}
-->
# Quizzer
Disse quizzer er før- og efterforelæsningsquizzer for AI-læseplanen på https://aka.ms/ai-beginners

9
translations/da/examples/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
"translation_date": "2025-10-03T11:31:26+00:00",
"source_file": "examples/README.md",
"language_code": "da"
}
-->
# Begynder-venlige AI-eksempler
Velkommen! Denne mappe indeholder enkle, selvstændige eksempler, der hjælper dig med at komme i gang med AI og maskinlæring. Hvert eksempel er designet til at være begyndervenligt med detaljerede kommentarer og trin-for-trin forklaringer.

9
translations/da/lessons/0-course-setup/for-teachers.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a094ef9927883de1cfcee51dbd143381",
"translation_date": "2025-08-28T15:08:06+00:00",
"source_file": "lessons/0-course-setup/for-teachers.md",
"language_code": "da"
}
-->
# For undervisere
Vil du gerne bruge dette pensum i dit klasseværelse? Du er meget velkommen!

9
translations/da/lessons/0-course-setup/how-to-run.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
"translation_date": "2026-01-16T02:27:08+00:00",
"source_file": "lessons/0-course-setup/how-to-run.md",
"language_code": "da"
}
-->
# Sådan kører du koden
Dette kursusindhold indeholder mange eksekverbare eksempler og laboratorier, som du vil ønske at køre. For at kunne gøre dette, har du brug for muligheden for at eksekvere Python-kode i Jupyter Notebooks, som leveres som en del af dette kursusindhold. Du har flere muligheder for at køre koden:

9
translations/da/lessons/0-course-setup/setup.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
"translation_date": "2025-12-12T19:51:59+00:00",
"source_file": "lessons/0-course-setup/setup.md",
"language_code": "da"
}
-->
# Kom godt i gang med dette pensum
## Er du studerende?

9
translations/da/lessons/1-Intro/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
"translation_date": "2025-11-18T21:33:49+00:00",
"source_file": "lessons/1-Intro/README.md",
"language_code": "da"
}
-->
# Introduktion til AI
![Oversigt over introduktion til AI-indhold i en doodle](../../../../translated_images/da/ai-intro.bf28d1ac4235881c.webp)

9
translations/da/lessons/1-Intro/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
"translation_date": "2025-11-18T21:35:07+00:00",
"source_file": "lessons/1-Intro/assignment.md",
"language_code": "da"
}
-->
# Spil Jam
Spil er et område, der i høj grad er blevet påvirket af udviklingen inden for AI og ML. I denne opgave skal du skrive en kort opgave om et spil, som du kan lide, og som er blevet påvirket af AI's udvikling. Det skal være et spil, der er gammelt nok til at være blevet påvirket af flere typer computerbehandlingssystemer. Et godt eksempel er skak eller Go, men kig også på videospil som Pong eller Pac-Man. Skriv et essay, der diskuterer spillets fortid, nutid og AI-fremtid.

17
translations/da/lessons/2-Symbolic/README.md
View File

@ -1,15 +1,6 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
"translation_date": "2026-01-16T02:28:23+00:00",
"source_file": "lessons/2-Symbolic/README.md",
"language_code": "da"
}
-->
# Videnrepræsentation og Ekspertsystemer
![Oversigt over Symbolsk AI indhold](../../../../../../translated_images/da/ai-symbolic.715a30cb610411a6.webp)
![Oversigt over Symbolsk AI indhold](../../../../translated_images/da/ai-symbolic.715a30cb610411a6.webp)
> Sketchnote af [Tomomi Imura](https://twitter.com/girlie_mac)
@ -41,7 +32,7 @@ Ofte definerer vi ikke viden strengt, men vi placerer den i forhold til andre re
Derfor er problemet med **videnrepræsentation** at finde en effektiv måde at repræsentere viden inden i en computer i form af data, så det kan bruges automatisk. Dette kan ses som et spektrum:
![Spektrum af videnrepræsentation](../../../../../../translated_images/da/knowledge-spectrum.b60df631852c0217.webp)
![Spektrum af videnrepræsentation](../../../../translated_images/da/knowledge-spectrum.b60df631852c0217.webp)
> Billede af [Dmitry Soshnikov](http://soshnikov.com)
@ -94,7 +85,7 @@ Blok-syntaks | Indrykning | | |
En af de tidlige succeser inden for symbolsk AI var de såkaldte **ekspertsystemer** – computersystemer designet til at optræde som eksperter inden for et begrænset problemområde. De var baseret på en **videndatabase** udvundet fra én eller flere menneskelige eksperter, og indeholdt en **inferenmotor**, der udførte ræsonnering ovenpå denne.
![Human Architecture](../../../../../../translated_images/da/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../../../translated_images/da/arch-kbs.3ec5c150b09fa8da.webp)
![Human Architecture](../../../../translated_images/da/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../translated_images/da/arch-kbs.3ec5c150b09fa8da.webp)
---------------------------------------------|------------------------------------------------
Forenklet struktur af et menneskeligt neuralt system | Arkitektur af et videnbaseret system
@ -106,7 +97,7 @@ Ekspertsystemer er bygget som det menneskelige ræsonneringssystem, der indehold
Som eksempel kan vi tage følgende ekspertsystem til at bestemme et dyr baseret på dets fysiske karakteristika:
![AND-OR Tree](../../../../../../translated_images/da/AND-OR-Tree.5592d2c70187f283.webp)
![AND-OR Tree](../../../../translated_images/da/AND-OR-Tree.5592d2c70187f283.webp)
> Billede af [Dmitry Soshnikov](http://soshnikov.com)

9
translations/da/lessons/2-Symbolic/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a057a8604f3976c3e309884453f1fad0",
"translation_date": "2025-08-28T15:31:00+00:00",
"source_file": "lessons/2-Symbolic/assignment.md",
"language_code": "da"
}
-->
# Byg en ontologi
At opbygge en vidensbase handler om at kategorisere en model, der repræsenterer fakta om et emne. Vælg et emne - som en person, et sted eller en ting - og byg derefter en model af det emne. Brug nogle af de teknikker og modelopbygningsstrategier, der er beskrevet i denne lektion. Et eksempel kunne være at skabe en ontologi for en stue med møbler, lamper osv. Hvordan adskiller stuen sig fra køkkenet? Badeværelset? Hvordan ved du, at det er en stue og ikke en spisestue? Brug [Protégé](https://protege.stanford.edu/) til at opbygge din ontologi.

13
translations/da/lessons/3-NeuralNetworks/03-Perceptron/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
"translation_date": "2025-09-23T09:33:47+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
"language_code": "da"
}
-->
# Introduktion til Neurale Netværk: Perceptron
## [Quiz før lektionen](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@ -15,7 +6,7 @@ En af de første forsøg på at implementere noget, der minder om et moderne neu
| | |
|--------------|-----------|
|<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/da/Rosenblatt-wikipedia.294821b285ac796d.webp' alt='Frank Rosenblatt'/> | <img src='../../../../../translated_images/da/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp' alt='The Mark 1 Perceptron' />|
> Billeder [fra Wikipedia](https://en.wikipedia.org/wiki/Perceptron)
@ -34,7 +25,7 @@ y(x) = f(w<sup>T</sup>x)
hvor f er en step-aktiveringsfunktion
<!-- 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/da/activation-func.b4924007c7ce7764.webp"/>
## Træning af Perceptron

9
translations/da/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
"translation_date": "2025-08-29T08:29:22+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
"language_code": "da"
}
-->
# Multi-klasse klassifikation med Perceptron
Lab-opgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

11
translations/da/lessons/3-NeuralNetworks/04-OwnFramework/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
"translation_date": "2025-09-23T09:33:13+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
"language_code": "da"
}
-->
# Introduktion til Neurale Netværk. Multi-Layered Perceptron
I den forrige sektion lærte du om den simpleste model for neurale netværk - enlaget perceptron, en lineær to-klasse klassifikationsmodel.
@ -65,7 +56,7 @@ Gradient descent-algoritmen forbliver den samme, men det bliver mere udfordrende
Bemærk, at den venstre del af alle disse udtryk er den samme, og derfor kan vi effektivt beregne afledte ved at starte fra tab-funktionen og gå "baglæns" gennem beregningsgrafen. Derfor kaldes metoden til træning af et flerlaget perceptron for **backpropagation**, eller 'backprop'.
<img alt="beregningsgraf" src="images/ComputeGraphGrad.png"/>
<img alt="beregningsgraf" src="../../../../../translated_images/da/ComputeGraphGrad.4626252c0de03507.webp"/>
> TODO: billedhenvisning

9
translations/da/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
"translation_date": "2025-08-28T15:38:12+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
"language_code": "da"
}
-->
# MNIST Klassifikation med Vores Egen Ramme
Lab-opgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/da/lessons/3-NeuralNetworks/05-Frameworks/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ddd216f558a255260a9374008002c971",
"translation_date": "2025-09-23T09:34:04+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
"language_code": "da"
}
-->
# Neural Netværk Frameworks
Som vi allerede har lært, skal vi gøre to ting for at kunne træne neurale netværk effektivt:

9
translations/da/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "e452d897efb9a89700f41021834cf6e5",
"translation_date": "2025-08-28T15:42:04+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
"language_code": "da"
}
-->
# Klassifikation med PyTorch/TensorFlow
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/da/lessons/3-NeuralNetworks/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
"translation_date": "2025-10-03T12:49:32+00:00",
"source_file": "lessons/3-NeuralNetworks/README.md",
"language_code": "da"
}
-->
# Introduktion til Neurale Netværk
![Oversigt over indholdet i Intro Neural Networks i en doodle](../../../../translated_images/da/ai-neuralnetworks.1c687ae40bc86e83.webp)

11
translations/da/lessons/4-ComputerVision/06-IntroCV/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "feeca98225cb420afc89415f24f63d92",
"translation_date": "2025-09-23T09:29:06+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
"language_code": "da"
}
-->
# Introduktion til Computer Vision
[Computer Vision](https://wikipedia.org/wiki/Computer_vision) er en disciplin, der har til formål at give computere en højere forståelse af digitale billeder. Dette er en bred definition, da *forståelse* kan betyde mange forskellige ting, herunder at finde et objekt på et billede (**objektdetektion**), forstå hvad der sker (**begivenhedsdetektion**), beskrive et billede med tekst eller rekonstruere en scene i 3D. Der er også særlige opgaver relateret til menneskelige billeder: alder- og følelsesestimering, ansigtsdetektion og -identifikation samt 3D-positur-estimering, for blot at nævne nogle få.
@ -115,7 +106,7 @@ Læs mere om optisk flow [i denne fremragende tutorial](https://learnopencv.com/
I denne opgave skal du tage en video med simple gestusser, og dit mål er at udtrække op/ned/venstre/højre bevægelser ved hjælp af optisk flow.
<img src="images/palm-movement.png" width="30%" alt="Palm Movement Frame"/>
<img src="../../../../../translated_images/da/palm-movement.341495f0e9c47da3.webp" width="30%" alt="Palm Movement Frame"/>
---

9
translations/da/lessons/4-ComputerVision/06-IntroCV/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "3d53d6409f80970f7281a45dee35328a",
"translation_date": "2025-08-28T15:20:13+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
"language_code": "da"
}
-->
# Registrering af bevægelser ved hjælp af optisk flow
Laboratorieopgave fra [AI for Beginners Curriculum](https://aka.ms/ai-beginners).

13
translations/da/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
"translation_date": "2025-09-23T09:28:10+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
"language_code": "da"
}
-->
# Velkendte CNN-arkitekturer
### VGG-16
@ -25,7 +16,7 @@ Som du kan se, følger VGG en traditionel pyramidearkitektur, som er en sekvens
ResNet er en familie af modeller foreslået af Microsoft Research i 2015. Hovedideen bag ResNet er brugen af **residualblokke**:
<img src="images/resnet-block.png" width="300"/>
<img src="../../../../../translated_images/da/resnet-block.aba4ccbcc0944434.webp" width="300"/>
> Billede fra [denne artikel](https://arxiv.org/pdf/1512.03385.pdf)
@ -37,7 +28,7 @@ Du kan også tænke på dette netværk som værende i stand til at justere sin k
Google Inception-arkitekturen tager denne idé et skridt videre og bygger hvert netværkslag som en kombination af flere forskellige veje:
<img src="images/inception.png" width="400"/>
<img src="../../../../../translated_images/da/inception.a6605b85bcbc6f52.webp" width="400"/>
> Billede fra [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)

11
translations/da/lessons/4-ComputerVision/07-ConvNets/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a560d5b845962cf33dc102266e409568",
"translation_date": "2025-09-23T09:27:53+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
"language_code": "da"
}
-->
# Konvolutionelle Neurale Netværk
Vi har tidligere set, at neurale netværk er ret gode til at arbejde med billeder, og selv et enkeltlags perceptron kan genkende håndskrevne cifre fra MNIST-datasættet med rimelig nøjagtighed. Dog er MNIST-datasættet meget specielt, da alle cifre er centreret i billedet, hvilket gør opgaven enklere.
@ -24,7 +15,7 @@ For at udtrække mønstre vil vi bruge begrebet **konvolutionelle filtre**. Som
For eksempel, hvis vi anvender 3x3 vertikale og horisontale kantfiltre på MNIST-cifre, kan vi fremhæve (f.eks. høje værdier), hvor der er vertikale og horisontale kanter i vores oprindelige billede. Disse to filtre kan således bruges til at "lede efter" kanter. På samme måde kan vi designe forskellige filtre til at finde andre lavniveau-mønstre:
<img src="images/lmfilters.jpg" width="500" align="center"/>
<img src="../../../../../translated_images/da/lmfilters.ea9e4868a82cf74c.webp" width="500" align="center"/>
> Billede af [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)

9
translations/da/lessons/4-ComputerVision/07-ConvNets/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "b70fcf7fcee862990f848c679090943f",
"translation_date": "2025-10-03T14:55:29+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
"language_code": "da"
}
-->
# Klassifikation af kæledyrs ansigter
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/da/lessons/4-ComputerVision/08-TransferLearning/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
"translation_date": "2025-09-23T09:28:36+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
"language_code": "da"
}
-->
# Forudtrænede Netværk og Transfer Learning
Træning af CNN'er kan tage meget tid, og der kræves en stor mængde data til denne opgave. Meget af tiden bruges dog på at lære de bedste lavniveau-filtre, som et netværk kan bruge til at udtrække mønstre fra billeder. Et naturligt spørgsmål opstår: Kan vi bruge et neuralt netværk, der er trænet på ét datasæt, og tilpasse det til at klassificere andre billeder uden at skulle gennemgå en fuld træningsproces?

9
translations/da/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
"translation_date": "2025-08-28T15:16:24+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
"language_code": "da"
}
-->
# Tricks til træning af dybe neurale netværk
Når neurale netværk bliver dybere, bliver træningsprocessen mere og mere udfordrende. Et stort problem er de såkaldte [forsvindende gradienter](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) eller [eksploderende gradienter](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Denne artikel](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) giver en god introduktion til disse problemer.

9
translations/da/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
"translation_date": "2025-08-28T15:17:52+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
"language_code": "da"
}
-->
# Klassificering af Oxford Pets ved hjælp af Transfer Learning
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

15
translations/da/lessons/4-ComputerVision/09-Autoencoders/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
"translation_date": "2025-09-23T09:30:20+00:00",
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
"language_code": "da"
}
-->
# Autoencodere
Når vi træner CNN'er, er en af udfordringerne, at vi har brug for en stor mængde mærkede data. I tilfælde af billedklassifikation skal vi opdele billeder i forskellige klasser, hvilket kræver manuelt arbejde.
@ -46,7 +37,7 @@ Opsummeret:
* Vi sampler en vektor `sample` fra fordelingen N(z<sub>mean</sub>,exp(z<sub>log\_sigma</sub>)).
* Decoderen forsøger at dekode det oprindelige billede ved hjælp af `sample` som inputvektor.
<img src="images/vae.png" width="50%">
<img src="../../../../../translated_images/da/vae.464c465a5b6a9e25.webp" width="50%">
> Billede fra [denne blogpost](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) af Isaak Dykeman
@ -57,13 +48,13 @@ Variationsautoencodere bruger en kompleks tab-funktion, der består af to dele:
En vigtig fordel ved VAE'er er, at de gør det relativt nemt at generere nye billeder, fordi vi ved, hvilken fordeling vi skal sample latente vektorer fra. For eksempel, hvis vi træner en VAE med en 2D latent vektor på MNIST, kan vi derefter variere komponenterne i den latente vektor for at få forskellige cifre:
<img alt="vaemnist" src="images/vaemnist.png" width="50%"/>
<img alt="vaemnist" src="../../../../../translated_images/da/vaemnist.cab9e602dc08dc50.webp" width="50%"/>
> Billede af [Dmitry Soshnikov](http://soshnikov.com)
Bemærk, hvordan billederne flyder ind i hinanden, når vi begynder at tage latente vektorer fra forskellige dele af det latente parameter-rum. Vi kan også visualisere dette rum i 2D:
<img alt="vaemnist cluster" src="images/vaemnist-diag.png" width="50%"/>
<img alt="vaemnist cluster" src="../../../../../translated_images/da/vaemnist-diag.694315f775d5d666.webp" width="50%"/>
> Billede af [Dmitry Soshnikov](http://soshnikov.com)

13
translations/da/lessons/4-ComputerVision/10-GANs/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
"translation_date": "2025-09-23T09:31:05+00:00",
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
"language_code": "da"
}
-->
# Generative Adversarial Networks
I den forrige sektion lærte vi om **generative modeller**: modeller, der kan generere nye billeder, der ligner dem i træningsdatasættet. VAE var et godt eksempel på en generativ model.
@ -17,7 +8,7 @@ Men hvis vi forsøger at generere noget virkelig meningsfuldt, som et maleri i r
Hovedideen bag en GAN er at have to neurale netværk, der trænes mod hinanden:
<img src="images/gan_architecture.png" width="70%"/>
<img src="../../../../../translated_images/da/gan_architecture.8f3a5ab62b8d5d69.webp" width="70%"/>
> Billede af [Dmitry Soshnikov](http://soshnikov.com)
@ -41,7 +32,7 @@ En generator er lidt mere kompleks. Du kan betragte den som en omvendt discrimin
> ✅ Fordi konvolutionslaget implementeres som et lineært filter, der bevæger sig hen over billedet, er dekonvolution i bund og grund det samme som konvolution og kan implementeres med samme laglogik.
<img src="images/gan_arch_detail.png" width="70%"/>
<img src="../../../../../translated_images/da/gan_arch_detail.46b95fd366f8e543.webp" width="70%"/>
> Billede af [Dmitry Soshnikov](http://soshnikov.com)

9
translations/da/lessons/4-ComputerVision/11-ObjectDetection/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
"translation_date": "2025-09-23T09:29:37+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
"language_code": "da"
}
-->
# Objektgenkendelse
De billedklassifikationsmodeller, vi hidtil har arbejdet med, tog et billede og producerede et kategorisk resultat, som f.eks. klassen 'nummer' i et MNIST-problem. Men i mange tilfælde ønsker vi ikke blot at vide, at et billede viser objekter – vi vil også kunne bestemme deres præcise placering. Det er netop formålet med **objektgenkendelse**.

9
translations/da/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
"translation_date": "2025-08-28T15:23:12+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
"language_code": "da"
}
-->
# Hoveddetektion ved brug af Hollywood Heads Dataset
Lab-opgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

15
translations/da/lessons/4-ComputerVision/12-Segmentation/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
"translation_date": "2025-09-23T09:30:50+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
"language_code": "da"
}
-->
# Segmentering
Vi har tidligere lært om Objektgenkendelse, som giver os mulighed for at lokalisere objekter i et billede ved at forudsige deres *bounding boxes*. Men til nogle opgaver har vi ikke kun brug for bounding boxes, men også mere præcis objektlokalisering. Denne opgave kaldes **segmentering**.
@ -20,7 +11,7 @@ Segmentering kan betragtes som **pixelklassificering**, hvor vi for **hver** pix
Ved instance segmentering er disse får forskellige objekter, men ved semantisk segmentering repræsenteres alle får af én klasse.
<img src="images/instance_vs_semantic.jpeg" width="50%">
<img src="../../../../../translated_images/da/instance_vs_semantic.eee9812bebf8cd45.webp" width="50%">
> Billede fra [denne blogpost](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@ -29,7 +20,7 @@ Der findes forskellige neurale arkitekturer til segmentering, men de har alle sa
* **Encoder** udtrækker features fra inputbilledet.
* **Decoder** transformerer disse features til **maske-billedet**, med samme størrelse og antal kanaler svarende til antallet af klasser.
<img src="images/segm.png" width="80%">
<img src="../../../../../translated_images/da/segm.92442f2cb42ff4fa.webp" width="80%">
> Billede fra [denne publikation](https://arxiv.org/pdf/2001.05566.pdf)
@ -43,7 +34,7 @@ I denne lektion vil vi se segmentering i praksis ved at træne et netværk til a
> ✅ Denne teknik er særligt velegnet til denne type medicinsk billedbehandling, men hvilke andre anvendelser i den virkelige verden kan du forestille dig?
<img alt="navi" src="images/navi.png"/>
<img alt="navi" src="../../../../../translated_images/da/navi.2f20b727910110ea.webp"/>
> Billede fra PH<sup>2</sup> Database

9
translations/da/lessons/4-ComputerVision/12-Segmentation/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
"translation_date": "2025-08-28T15:26:02+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
"language_code": "da"
}
-->
# Segmentering af menneskekroppen
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/da/lessons/4-ComputerVision/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
"translation_date": "2025-08-28T15:11:46+00:00",
"source_file": "lessons/4-ComputerVision/README.md",
"language_code": "da"
}
-->
# Computer Vision
![Oversigt over Computer Vision-indhold i en doodle](../../../../translated_images/da/ai-computervision.6506ebebac3fbf76.webp)

13
translations/da/lessons/5-NLP/13-TextRep/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
"translation_date": "2025-09-23T09:37:09+00:00",
"source_file": "lessons/5-NLP/13-TextRep/README.md",
"language_code": "da"
}
-->
# Repræsentation af tekst som tensorer
## [Quiz før forelæsning](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@ -25,7 +16,7 @@ Vores mål vil være at klassificere nyhedsartiklen i en af kategorierne baseret
Hvis vi vil løse opgaver inden for Natural Language Processing (NLP) med neurale netværk, skal vi finde en måde at repræsentere tekst som tensorer. Computere repræsenterer allerede teksttegn som tal, der kortlægges til skrifttyper på din skærm ved hjælp af kodninger som ASCII eller UTF-8.
<img alt="Billede, der viser diagrammet, der kortlægger et tegn til en ASCII- og binær repræsentation" src="images/ascii-character-map.png" width="50%"/>
<img alt="Billede, der viser diagrammet, der kortlægger et tegn til en ASCII- og binær repræsentation" src="../../../../../translated_images/da/ascii-character-map.18ed6aa7f3b0a7ff.webp" width="50%"/>
> [Billedkilde](https://www.seobility.net/en/wiki/ASCII)
@ -48,7 +39,7 @@ I nogle tilfælde kan vi overveje at bruge tri-grams -- kombinationer af tre ord
Når vi løser opgaver som tekstklassifikation, skal vi kunne repræsentere tekst med én vektor af fast størrelse, som vi vil bruge som input til den endelige tætte klassifikator. En af de enkleste måder at gøre dette på er at kombinere alle individuelle ordrepræsentationer, f.eks. ved at lægge dem sammen. Hvis vi lægger one-hot encodings af hvert ord sammen, ender vi med en vektor af frekvenser, der viser, hvor mange gange hvert ord optræder i teksten. En sådan repræsentation af tekst kaldes **bag of words** (BoW).
<img src="images/bow.png" width="90%"/>
<img src="../../../../../translated_images/da/bow.3811869cff59368d.webp" width="90%"/>
> Billede af forfatteren

9
translations/da/lessons/5-NLP/13-TextRep/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
"translation_date": "2025-08-28T16:03:41+00:00",
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
"language_code": "da"
}
-->
# Opgave: Notebooks
Brug de notebooks, der er tilknyttet denne lektion (enten PyTorch- eller TensorFlow-versionen), og kør dem igen med dit eget datasæt, måske et fra Kaggle, brugt med korrekt kildeangivelse. Omskriv notebooken for at fremhæve dine egne resultater. Prøv nogle innovative datasæt, der måske kan overraske, såsom [dette om UFO-observationer](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) fra NUFORC.

9
translations/da/lessons/5-NLP/14-Embeddings/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
"translation_date": "2025-09-23T09:36:45+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
"language_code": "da"
}
-->
# Indlejring
## [Quiz før forelæsning](https://ff-quizzes.netlify.app/en/ai/quiz/27)

9
translations/da/lessons/5-NLP/14-Embeddings/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
"translation_date": "2025-08-28T16:02:00+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
"language_code": "da"
}
-->
# Opgave: Notebooks
Brug de notebooks, der er knyttet til denne lektion (enten PyTorch- eller TensorFlow-versionen), og kør dem igen med dit eget datasæt, måske et fra Kaggle, brugt med korrekt kildeangivelse. Omskriv notebooken for at fremhæve dine egne resultater. Prøv en anden type datasæt og dokumentér dine resultater, ved at bruge tekst som [disse Beatles-sangtekster](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).

9
translations/da/lessons/5-NLP/15-LanguageModeling/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
"translation_date": "2025-09-23T09:34:48+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
"language_code": "da"
}
-->
# Sproglig Modellering
Semantiske indlejringer, såsom Word2Vec og GloVe, er faktisk et første skridt mod **sproglig modellering** - at skabe modeller, der på en eller anden måde *forstår* (eller *repræsenterer*) sprogets natur.

9
translations/da/lessons/5-NLP/15-LanguageModeling/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
"translation_date": "2025-08-28T15:54:06+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
"language_code": "da"
}
-->
# Træning af Skip-Gram Model
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

11
translations/da/lessons/5-NLP/16-RNN/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "e2273cc150380a5e191903cea858f021",
"translation_date": "2025-09-23T09:36:15+00:00",
"source_file": "lessons/5-NLP/16-RNN/README.md",
"language_code": "da"
}
-->
# Rekurrente Neurale Netværk
## [Quiz før forelæsning](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@ -31,7 +22,7 @@ Lad os se, hvordan en simpel RNN-celle er organiseret. Den accepterer den tidlig
En simpel RNN-celle har to vægtmatricer indeni: én transformerer et inputsymbol (lad os kalde den W), og en anden transformerer en inputtilstand (H). I dette tilfælde beregnes netværkets output som &sigma;(W&times;X<sub>i</sub>+H&times;S<sub>i-1</sub>+b), hvor &sigma; er aktiveringsfunktionen, og b er en ekstra bias.
<img alt="RNN Celle Anatomi" src="images/rnn-anatomy.png" width="50%"/>
<img alt="RNN Celle Anatomi" src="../../../../../translated_images/da/rnn-anatomy.79ee3f3920b3294b.webp" width="50%"/>
> Billede af forfatteren

9
translations/da/lessons/5-NLP/16-RNN/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
"translation_date": "2025-08-28T16:00:34+00:00",
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
"language_code": "da"
}
-->
# Opgave: Notebooks
Brug de notebooks, der er knyttet til denne lektion (enten PyTorch- eller TensorFlow-versionen), og kør dem igen med dit eget datasæt, måske et fra Kaggle, brugt med korrekt kildeangivelse. Omskriv notebooken for at fremhæve dine egne resultater. Prøv en anden type datasæt og dokumentér dine resultater, ved at bruge tekst som [dette Kaggle-konkurrence-datasæt om vejrtweets](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).

11
translations/da/lessons/5-NLP/17-GenerativeNetworks/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
"translation_date": "2025-09-23T09:34:27+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
"language_code": "da"
}
-->
# Generative netværk
## [Quiz før forelæsning](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@ -36,7 +27,7 @@ Vi vil træne denne RNN til at generere tekst trin for trin. Ved hvert trin tage
Når vi genererer tekst (under inferens), starter vi med en **prompt**, som sendes gennem RNN-celler for at generere dens mellemliggende tilstand, og derefter starter genereringen fra denne tilstand. Vi genererer ét tegn ad gangen og sender tilstanden og det genererede tegn til en anden RNN-celle for at generere det næste, indtil vi har genereret nok tegn.
<img src="images/rnn-generate-inf.png" width="60%"/>
<img src="../../../../../translated_images/da/rnn-generate-inf.5168dc65e0370eea.webp" width="60%"/>
> Billede af forfatteren

9
translations/da/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
"translation_date": "2025-08-28T15:53:04+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
"language_code": "da"
}
-->
# Ord-niveau Tekstgenerering med RNN'er
Laboratorieopgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

11
translations/da/lessons/5-NLP/18-Transformers/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f335dfcb4a993920504c387973a36957",
"translation_date": "2025-09-23T09:35:02+00:00",
"source_file": "lessons/5-NLP/18-Transformers/README.md",
"language_code": "da"
}
-->
# Attention Mekanismer og Transformers
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@ -56,7 +47,7 @@ Idéen med positionskodning er følgende:
* Trænbar embedding, svarende til token-embedding. Dette er den tilgang, vi overvejer her. Vi anvender embedding-lag oven på både tokens og deres positioner, hvilket resulterer i embedding-vektorer af samme dimensioner, som vi derefter lægger sammen.
* Fast positionskodningsfunktion, som foreslået i det originale papir.
<img src="images/pos-embedding.png" width="50%"/>
<img src="../../../../../translated_images/da/pos-embedding.e41ce9b6cf6078af.webp" width="50%"/>
> Billede af forfatteren

9
translations/da/lessons/5-NLP/18-Transformers/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
"translation_date": "2025-08-28T15:55:53+00:00",
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
"language_code": "da"
}
-->
# Opgave: Transformers
Eksperimentér med Transformers på HuggingFace! Prøv nogle af de scripts, de stiller til rådighed, for at arbejde med de forskellige modeller, der er tilgængelige på deres side: https://huggingface.co/docs/transformers/run_scripts. Prøv et af deres datasæt, og importer derefter et af dine egne fra dette pensum eller fra Kaggle, og se, om du kan generere interessante tekster. Lav en notebook med dine resultater.

11
translations/da/lessons/5-NLP/19-NER/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "6522312ff835796ca34136a9462fafb2",
"translation_date": "2025-09-23T09:35:57+00:00",
"source_file": "lessons/5-NLP/19-NER/README.md",
"language_code": "da"
}
-->
# Navngiven Enhedsgenkendelse
Indtil nu har vi primært fokuseret på én NLP-opgave - klassifikation. Men der findes også andre NLP-opgaver, som kan løses med neurale netværk. En af disse opgaver er **[Navngiven Enhedsgenkendelse](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), som handler om at genkende specifikke enheder i tekst, såsom steder, personnavne, dato-tidsintervaller, kemiske formler og så videre.
@ -17,7 +8,7 @@ Indtil nu har vi primært fokuseret på én NLP-opgave - klassifikation. Men der
Forestil dig, at du vil udvikle en chatbot, der fungerer som Amazon Alexa eller Google Assistant. Intelligente chatbots arbejder ved at *forstå*, hvad brugeren ønsker, ved at udføre tekstklassifikation på den indtastede sætning. Resultatet af denne klassifikation kaldes **intent**, som afgør, hvad chatbotten skal gøre.
<img alt="Bot NER" src="images/bot-ner.png" width="50%"/>
<img alt="Bot NER" src="../../../../../translated_images/da/bot-ner.4b09235dbb0ad275.webp" width="50%"/>
> Billede af forfatteren

9
translations/da/lessons/5-NLP/19-NER/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "032bda5068f543d6c1fcb30c34231461",
"translation_date": "2025-08-28T15:58:16+00:00",
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
"language_code": "da"
}
-->
# NER
Labøvelse fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/da/lessons/5-NLP/20-LangModels/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
"translation_date": "2025-09-23T09:35:38+00:00",
"source_file": "lessons/5-NLP/20-LangModels/README.md",
"language_code": "da"
}
-->
# Forudtrænede Store Sproglige Modeller
I alle vores tidligere opgaver har vi trænet et neuralt netværk til at udføre en bestemt opgave ved hjælp af et mærket datasæt. Med store transformer-modeller, såsom BERT, bruger vi sprogmodellering på en selv-superviseret måde til at bygge en sprogmodel, som derefter specialiseres til specifikke downstream-opgaver med yderligere domænespecifik træning. Det er dog blevet demonstreret, at store sproglige modeller også kan løse mange opgaver uden nogen form for domænespecifik træning. En familie af modeller, der kan gøre dette, kaldes **GPT**: Generative Pre-Trained Transformer.

9
translations/da/lessons/5-NLP/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
"translation_date": "2025-08-28T15:51:00+00:00",
"source_file": "lessons/5-NLP/README.md",
"language_code": "da"
}
-->
# Naturlig Sprogbehandling
![Oversigt over NLP-opgaver i en doodle](../../../../translated_images/da/ai-nlp.b22dcb8ca4707cea.webp)

9
translations/da/lessons/6-Other/21-GeneticAlgorithms/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
"translation_date": "2025-09-23T09:26:28+00:00",
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
"language_code": "da"
}
-->
# Genetiske Algoritmer
## [Quiz før forelæsning](https://ff-quizzes.netlify.app/en/ai/quiz/41)

11
translations/da/lessons/6-Other/22-DeepRL/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "04395657fc01648f8f70484d0e55ab67",
"translation_date": "2025-09-23T09:27:25+00:00",
"source_file": "lessons/6-Other/22-DeepRL/README.md",
"language_code": "da"
}
-->
# Deep Reinforcement Learning
Forstærkningslæring (RL) betragtes som en af de grundlæggende paradigmer inden for maskinlæring, ved siden af superviseret læring og usuperviseret læring. Mens vi i superviseret læring baserer os på datasæt med kendte resultater, er RL baseret på **at lære ved at gøre**. For eksempel, når vi ser et computerspil for første gang, begynder vi at spille, selv uden at kende reglerne, og snart bliver vi bedre, blot ved at spille og justere vores adfærd.
@ -34,7 +25,7 @@ I har sikkert alle set moderne balanceringsenheder som *Segway* eller *Gyroscoot
En forenklet version af balancering er kendt som **CartPole**-problemet. I CartPole-verdenen har vi en horisontal slider, der kan bevæge sig til venstre eller højre, og målet er at balancere en vertikal stang oven på slideren, mens den bevæger sig.
<img alt="en cartpole" src="images/cartpole.png" width="200"/>
<img alt="en cartpole" src="../../../../../translated_images/da/cartpole.f52a67f27e058170.webp" width="200"/>
For at oprette og bruge dette miljø har vi brug for et par linjer Python-kode:

9
translations/da/lessons/6-Other/22-DeepRL/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
"translation_date": "2025-08-28T15:07:40+00:00",
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
"language_code": "da"
}
-->
## Miljøet
Mountain Car-miljøet består af en bil, der er fanget i en dal. Dit mål er at hoppe ud af dalen og nå flaget. De handlinger, du kan udføre, er at accelerere til venstre, til højre eller gøre ingenting. Du kan observere bilens position langs x-aksen og dens hastighed.

11
translations/da/lessons/6-Other/23-MultiagentSystems/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
"translation_date": "2025-09-23T09:26:42+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
"language_code": "da"
}
-->
# Multi-Agent Systemer
En af de mulige måder at opnå intelligens på er den såkaldte **emergente** (eller **synergetiske**) tilgang, som er baseret på, at den samlede adfærd af mange relativt simple agenter kan resultere i en mere kompleks (eller intelligent) adfærd for systemet som helhed. Teoretisk set bygger dette på principperne om [Kollektiv Intelligens](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentisme](https://en.wikipedia.org/wiki/Global_brain) og [Evolutionær Kybernetik](https://en.wikipedia.org/wiki/Global_brain), som siger, at højere niveau-systemer opnår en form for merværdi, når de korrekt kombineres fra lavere niveau-systemer (det såkaldte *princip om metasystem-transition*).
@ -60,7 +51,7 @@ Du kan [downloade](https://ccl.northwestern.edu/netlogo/download.shtml) og insta
En fantastisk ting ved NetLogo er, at det indeholder et bibliotek med fungerende modeller, som du kan prøve. Gå til **File &rightarrow; Models Library**, og du har mange kategorier af modeller at vælge imellem.
<img alt="NetLogo Models Library" src="images/NetLogo-ModelLib.png" width="60%"/>
<img alt="NetLogo Models Library" src="../../../../../translated_images/da/NetLogo-ModelLib.efe023afb4763c05.webp" width="60%"/>
> Et skærmbillede af modelbiblioteket af Dmitry Soshnikov

9
translations/da/lessons/6-Other/23-MultiagentSystems/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
"translation_date": "2025-08-28T15:05:53+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
"language_code": "da"
}
-->
# NetLogo Opgave
Tag en af modellerne i NetLogos bibliotek og brug den til at simulere en virkelighedsnær situation så præcist som muligt. Et godt eksempel kunne være at justere Virus-modellen i mappen Alternative Visualizations for at vise, hvordan den kan bruges til at modellere spredningen af COVID-19. Kan du bygge en model, der efterligner en virkelig viral spredning?

9
translations/da/lessons/7-Ethics/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
"translation_date": "2025-08-28T15:31:28+00:00",
"source_file": "lessons/7-Ethics/README.md",
"language_code": "da"
}
-->
# Etisk og Ansvarlig AI
Du er næsten færdig med dette kursus, og jeg håber, at du nu tydeligt kan se, at AI er baseret på en række formelle matematiske metoder, der gør det muligt for os at finde sammenhænge i data og træne modeller til at efterligne nogle aspekter af menneskelig adfærd. På dette tidspunkt i historien betragter vi AI som et meget kraftfuldt værktøj til at udtrække mønstre fra data og anvende disse mønstre til at løse nye problemer.

9
translations/da/lessons/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
"translation_date": "2025-08-28T15:02:19+00:00",
"source_file": "lessons/README.md",
"language_code": "da"
}
-->
# Oversigt
![Oversigt i en doodle](../../../translated_images/da/ai-overview.0857791951d19500.webp)

9
translations/da/lessons/X-Extras/X1-MultiModal/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "9c592c26aca16ca085d268c732284187",
"translation_date": "2025-08-28T15:10:45+00:00",
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
"language_code": "da"
}
-->
# Multi-Modal Netværk
Efter succesen med transformer-modeller til løsning af NLP-opgaver, er de samme eller lignende arkitekturer blevet anvendt til computer vision-opgaver. Der er en stigende interesse i at bygge modeller, der kan *kombinere* vision og naturlige sprogfunktioner. En af disse forsøg blev gjort af OpenAI, og det kaldes CLIP og DALL.E.

9
translations/da/lessons/sketchnotes/LICENSE.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
"translation_date": "2025-08-28T15:46:18+00:00",
"source_file": "lessons/sketchnotes/LICENSE.md",
"language_code": "da"
}
-->
Attribution-ShareAlike 4.0 International
=======================================================================

9
translations/da/lessons/sketchnotes/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "050b8bddebafba55b129414e6ab096ab",
"translation_date": "2025-08-28T15:42:23+00:00",
"source_file": "lessons/sketchnotes/README.md",
"language_code": "da"
}
-->
Alle sketchnotes fra pensum kan downloades her.
🎨 Oprettet af: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))

9
translations/da/troubleshoot.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
"translation_date": "2025-10-03T09:45:25+00:00",
"source_file": "troubleshoot.md",
"language_code": "da"
}
-->
# AI-For-Beginners Fejlfindingsguide
Denne guide hjælper dig med at løse almindelige problemer, der opstår ved brug eller bidrag til [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners)-repositoryet. Hvert problem inkluderer baggrund, symptomer, forklaringer og trin-for-trin løsninger.

398
translations/sv/.co-op-translator.json Normal file
View File

@ -0,0 +1,398 @@
{
"AGENTS.md": {
"original_hash": "6b11a37115944252ab3ed04e358d830d",
"translation_date": "2025-10-03T09:22:45+00:00",
"source_file": "AGENTS.md",
"language_code": "sv"
},
"README.md": {
"original_hash": "1984fc89dd304a8a33ab5584691a99aa",
"translation_date": "2026-01-30T01:59:08+00:00",
"source_file": "README.md",
"language_code": "sv"
},
"SECURITY.md": {
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
"translation_date": "2025-08-28T15:01:34+00:00",
"source_file": "SECURITY.md",
"language_code": "sv"
},
"etc/CODE_OF_CONDUCT.md": {
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
"translation_date": "2025-08-28T16:06:50+00:00",
"source_file": "etc/CODE_OF_CONDUCT.md",
"language_code": "sv"
},
"etc/CONTRIBUTING.md": {
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
"translation_date": "2025-08-28T16:06:24+00:00",
"source_file": "etc/CONTRIBUTING.md",
"language_code": "sv"
},
"etc/Mindmap.md": {
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
"translation_date": "2025-08-28T16:04:36+00:00",
"source_file": "etc/Mindmap.md",
"language_code": "sv"
},
"etc/SUPPORT.md": {
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
"translation_date": "2025-08-28T16:03:53+00:00",
"source_file": "etc/SUPPORT.md",
"language_code": "sv"
},
"etc/TRANSLATIONS.md": {
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
"translation_date": "2025-08-28T16:05:54+00:00",
"source_file": "etc/TRANSLATIONS.md",
"language_code": "sv"
},
"etc/quiz-app/README.md": {
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
"translation_date": "2025-08-28T16:07:07+00:00",
"source_file": "etc/quiz-app/README.md",
"language_code": "sv"
},
"examples/README.md": {
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
"translation_date": "2025-10-03T11:31:15+00:00",
"source_file": "examples/README.md",
"language_code": "sv"
},
"lessons/0-course-setup/for-teachers.md": {
"original_hash": "a094ef9927883de1cfcee51dbd143381",
"translation_date": "2025-08-28T15:07:54+00:00",
"source_file": "lessons/0-course-setup/for-teachers.md",
"language_code": "sv"
},
"lessons/0-course-setup/how-to-run.md": {
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
"translation_date": "2026-01-16T02:22:35+00:00",
"source_file": "lessons/0-course-setup/how-to-run.md",
"language_code": "sv"
},
"lessons/0-course-setup/setup.md": {
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
"translation_date": "2025-12-12T19:50:22+00:00",
"source_file": "lessons/0-course-setup/setup.md",
"language_code": "sv"
},
"lessons/1-Intro/README.md": {
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
"translation_date": "2025-11-18T21:31:40+00:00",
"source_file": "lessons/1-Intro/README.md",
"language_code": "sv"
},
"lessons/1-Intro/assignment.md": {
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
"translation_date": "2025-11-18T21:32:40+00:00",
"source_file": "lessons/1-Intro/assignment.md",
"language_code": "sv"
},
"lessons/2-Symbolic/README.md": {
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
"translation_date": "2026-01-16T02:22:50+00:00",
"source_file": "lessons/2-Symbolic/README.md",
"language_code": "sv"
},
"lessons/2-Symbolic/assignment.md": {
"original_hash": "a057a8604f3976c3e309884453f1fad0",
"translation_date": "2025-08-28T15:30:53+00:00",
"source_file": "lessons/2-Symbolic/assignment.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/03-Perceptron/README.md": {
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
"translation_date": "2025-09-23T09:22:26+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
"translation_date": "2025-08-29T08:26:33+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
"translation_date": "2025-09-23T09:21:43+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
"translation_date": "2025-08-28T15:38:05+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/05-Frameworks/README.md": {
"original_hash": "ddd216f558a255260a9374008002c971",
"translation_date": "2025-09-23T09:22:45+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
"original_hash": "e452d897efb9a89700f41021834cf6e5",
"translation_date": "2025-08-28T15:41:56+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
"language_code": "sv"
},
"lessons/3-NeuralNetworks/README.md": {
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
"translation_date": "2025-10-03T12:49:15+00:00",
"source_file": "lessons/3-NeuralNetworks/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/06-IntroCV/README.md": {
"original_hash": "feeca98225cb420afc89415f24f63d92",
"translation_date": "2025-09-23T09:17:24+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
"original_hash": "3d53d6409f80970f7281a45dee35328a",
"translation_date": "2025-08-28T15:20:05+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
"translation_date": "2025-09-23T09:16:43+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/07-ConvNets/README.md": {
"original_hash": "a560d5b845962cf33dc102266e409568",
"translation_date": "2025-09-23T09:16:25+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
"original_hash": "b70fcf7fcee862990f848c679090943f",
"translation_date": "2025-10-03T14:55:20+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/08-TransferLearning/README.md": {
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
"translation_date": "2025-09-23T09:17:00+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
"translation_date": "2025-08-28T15:15:46+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
"translation_date": "2025-08-28T15:17:45+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/09-Autoencoders/README.md": {
"original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
"translation_date": "2025-09-23T09:18:34+00:00",
"source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/10-GANs/README.md": {
"original_hash": "0ff65b4da07b23697235de2beb2a3c25",
"translation_date": "2025-09-23T09:19:20+00:00",
"source_file": "lessons/4-ComputerVision/10-GANs/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/11-ObjectDetection/README.md": {
"original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
"translation_date": "2025-09-23T09:17:55+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
"original_hash": "ad568d55ae65c856fe929fc2b278510a",
"translation_date": "2025-08-28T15:22:59+00:00",
"source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/12-Segmentation/README.md": {
"original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
"translation_date": "2025-09-23T09:19:02+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
"original_hash": "365f0decfe0f47b460bbde8227c5009d",
"translation_date": "2025-08-28T15:25:54+00:00",
"source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
"language_code": "sv"
},
"lessons/4-ComputerVision/README.md": {
"original_hash": "58a52f000089c1d8906a4daa4ab1169b",
"translation_date": "2025-08-28T15:11:39+00:00",
"source_file": "lessons/4-ComputerVision/README.md",
"language_code": "sv"
},
"lessons/5-NLP/13-TextRep/README.md": {
"original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
"translation_date": "2025-09-23T09:26:11+00:00",
"source_file": "lessons/5-NLP/13-TextRep/README.md",
"language_code": "sv"
},
"lessons/5-NLP/13-TextRep/assignment.md": {
"original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
"translation_date": "2025-08-28T16:03:35+00:00",
"source_file": "lessons/5-NLP/13-TextRep/assignment.md",
"language_code": "sv"
},
"lessons/5-NLP/14-Embeddings/README.md": {
"original_hash": "b708c9b85b833864c73c6281f1e6b96e",
"translation_date": "2025-09-23T09:25:49+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/README.md",
"language_code": "sv"
},
"lessons/5-NLP/14-Embeddings/assignment.md": {
"original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
"translation_date": "2025-08-28T16:01:54+00:00",
"source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
"language_code": "sv"
},
"lessons/5-NLP/15-LanguageModeling/README.md": {
"original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
"translation_date": "2025-09-23T09:23:36+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
"language_code": "sv"
},
"lessons/5-NLP/15-LanguageModeling/lab/README.md": {
"original_hash": "5130f01fdc5ebb83032b23d489027aac",
"translation_date": "2025-08-28T15:53:58+00:00",
"source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
"language_code": "sv"
},
"lessons/5-NLP/16-RNN/README.md": {
"original_hash": "e2273cc150380a5e191903cea858f021",
"translation_date": "2025-09-23T09:25:23+00:00",
"source_file": "lessons/5-NLP/16-RNN/README.md",
"language_code": "sv"
},
"lessons/5-NLP/16-RNN/assignment.md": {
"original_hash": "47f7d3c6a5373543e051e4d1140ce898",
"translation_date": "2025-08-28T16:00:27+00:00",
"source_file": "lessons/5-NLP/16-RNN/assignment.md",
"language_code": "sv"
},
"lessons/5-NLP/17-GenerativeNetworks/README.md": {
"original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
"translation_date": "2025-09-23T09:23:09+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
"language_code": "sv"
},
"lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
"original_hash": "439e12796197a90e7623d4c9c057b9c2",
"translation_date": "2025-08-28T15:52:59+00:00",
"source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
"language_code": "sv"
},
"lessons/5-NLP/18-Transformers/README.md": {
"original_hash": "f335dfcb4a993920504c387973a36957",
"translation_date": "2025-09-23T09:23:48+00:00",
"source_file": "lessons/5-NLP/18-Transformers/README.md",
"language_code": "sv"
},
"lessons/5-NLP/18-Transformers/assignment.md": {
"original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
"translation_date": "2025-08-28T15:55:47+00:00",
"source_file": "lessons/5-NLP/18-Transformers/assignment.md",
"language_code": "sv"
},
"lessons/5-NLP/19-NER/README.md": {
"original_hash": "6522312ff835796ca34136a9462fafb2",
"translation_date": "2025-09-23T09:25:02+00:00",
"source_file": "lessons/5-NLP/19-NER/README.md",
"language_code": "sv"
},
"lessons/5-NLP/19-NER/lab/README.md": {
"original_hash": "032bda5068f543d6c1fcb30c34231461",
"translation_date": "2025-08-28T15:58:05+00:00",
"source_file": "lessons/5-NLP/19-NER/lab/README.md",
"language_code": "sv"
},
"lessons/5-NLP/20-LangModels/README.md": {
"original_hash": "97836d30a6bec736f8e3b4411c572bc2",
"translation_date": "2025-09-23T09:24:25+00:00",
"source_file": "lessons/5-NLP/20-LangModels/README.md",
"language_code": "sv"
},
"lessons/5-NLP/README.md": {
"original_hash": "8ef02a9318257ea140ed3ed74442096d",
"translation_date": "2025-08-28T15:50:08+00:00",
"source_file": "lessons/5-NLP/README.md",
"language_code": "sv"
},
"lessons/6-Other/21-GeneticAlgorithms/README.md": {
"original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
"translation_date": "2025-09-23T09:15:06+00:00",
"source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
"language_code": "sv"
},
"lessons/6-Other/22-DeepRL/README.md": {
"original_hash": "04395657fc01648f8f70484d0e55ab67",
"translation_date": "2025-09-23T09:15:59+00:00",
"source_file": "lessons/6-Other/22-DeepRL/README.md",
"language_code": "sv"
},
"lessons/6-Other/22-DeepRL/lab/README.md": {
"original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
"translation_date": "2025-08-28T15:07:34+00:00",
"source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
"language_code": "sv"
},
"lessons/6-Other/23-MultiagentSystems/README.md": {
"original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
"translation_date": "2025-09-23T09:15:24+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
"language_code": "sv"
},
"lessons/6-Other/23-MultiagentSystems/assignment.md": {
"original_hash": "cf654ca60c7f86c8dad28596fb42994b",
"translation_date": "2025-08-28T15:05:46+00:00",
"source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
"language_code": "sv"
},
"lessons/7-Ethics/README.md": {
"original_hash": "437c988596e751072e41a5aad3fcc5d9",
"translation_date": "2025-08-28T15:31:12+00:00",
"source_file": "lessons/7-Ethics/README.md",
"language_code": "sv"
},
"lessons/README.md": {
"original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
"translation_date": "2025-08-28T15:02:14+00:00",
"source_file": "lessons/README.md",
"language_code": "sv"
},
"lessons/X-Extras/X1-MultiModal/README.md": {
"original_hash": "9c592c26aca16ca085d268c732284187",
"translation_date": "2025-08-28T15:10:16+00:00",
"source_file": "lessons/X-Extras/X1-MultiModal/README.md",
"language_code": "sv"
},
"lessons/sketchnotes/LICENSE.md": {
"original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
"translation_date": "2025-08-28T15:43:45+00:00",
"source_file": "lessons/sketchnotes/LICENSE.md",
"language_code": "sv"
},
"lessons/sketchnotes/README.md": {
"original_hash": "050b8bddebafba55b129414e6ab096ab",
"translation_date": "2025-08-28T15:42:17+00:00",
"source_file": "lessons/sketchnotes/README.md",
"language_code": "sv"
},
"troubleshoot.md": {
"original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
"translation_date": "2025-10-03T09:44:58+00:00",
"source_file": "troubleshoot.md",
"language_code": "sv"
}
}

9
translations/sv/AGENTS.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "6b11a37115944252ab3ed04e358d830d",
"translation_date": "2025-10-03T09:22:45+00:00",
"source_file": "AGENTS.md",
"language_code": "sv"
}
-->
# AGENTS.md
## Projektöversikt

128
translations/sv/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "85102ce4bfab31103e99dc8ca2e2f181",
"translation_date": "2026-01-16T02:20:59+00:00",
"source_file": "README.md",
"language_code": "sv"
}
-->
[![GitHub license](https://img.shields.io/github/license/microsoft/AI-For-Beginners.svg)](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[![GitHub contributors](https://img.shields.io/github/contributors/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[![GitHub issues](https://img.shields.io/github/issues/microsoft/AI-For-Beginners.svg)](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@ -23,23 +14,23 @@ CO_OP_TRANSLATOR_METADATA:
# Artificiell Intelligens för Nybörjare - En Kursplan
|![Sketchnote av @girlie_mac https://twitter.com/girlie_mac](../../../../translated_images/sv/ai-overview.0857791951d19500.webp)|
|![Sketchnote av @girlie_mac https://twitter.com/girlie_mac](../../translated_images/sv/ai-overview.0857791951d19500.webp)|
|:---:|
| AI För Nybörjare - _Sketchnote av [@girlie_mac](https://twitter.com/girlie_mac)_ |
Utforska världen av **Artificiell Intelligens** (AI) med vår 12-veckors, 24-lektioners kursplan! Den inkluderar praktiska lektioner, quiz och labbar. Kursplanen är nybörjarvänlig och täcker verktyg som TensorFlow och PyTorch, samt etik inom AI
Utforska världen av **Artificiell Intelligens** (AI) med vår 12-veckors, 24-lektioners kursplan! Den inkluderar praktiska lektioner, quiz och labbar. Kursplanen är nybörjarvänlig och täcker verktyg som TensorFlow och PyTorch, samt etik inom AI.
### 🌐 Stöds på flera språk
### 🌐 Flerspråkigt Stöd
#### Stöds via GitHub Action (Automatiserat & Alltid Uppdaterat)
<!-- CO-OP TRANSLATOR LANGUAGES TABLE START -->
[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh/README.md) | [Chinese (Traditional, Hong Kong)](../hk/README.md) | [Chinese (Traditional, Macau)](../mo/README.md) | [Chinese (Traditional, Taiwan)](../tw/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../br/README.md) | [Portuguese (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](./README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md)
[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-TW/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](../no/README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../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](./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)
> **Föredrar du att klona lokalt?**
> Detta arkiv innehåller över 50 språköversättningar vilket avsevärt ökar nedladdningsstorleken. För att klona utan översättningar, använd sparse checkout:
> Detta arkiv inkluderar över 50 språköversättningar som avsevärt ökar storleken vid nedladdning. För att klona utan översättningar, använd sparse checkout:
> ```bash
> git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git
> cd AI-For-Beginners
@ -48,9 +39,9 @@ Utforska världen av **Artificiell Intelligens** (AI) med vår 12-veckors, 24-le
> Detta ger dig allt du behöver för att genomföra kursen med en mycket snabbare nedladdning.
<!-- CO-OP TRANSLATOR LANGUAGES TABLE END -->
**Om du vill få stöd för fler översättningsspråk finns de listade [här](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
**Om du önskar att fler översättningsspråk ska stödjas finns de listade [här](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Gå med i gemenskapen
## Gå med i communityn
[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG)
## Vad du kommer att lära dig
@ -59,54 +50,54 @@ Utforska världen av **Artificiell Intelligens** (AI) med vår 12-veckors, 24-le
I denna kursplan kommer du att lära dig:
* Olika tillvägagångssätt för Artificiell Intelligens, inklusive det "goda gamla" symboliska tillvägagångssättet med **Kunskapsrepresentation** och resonemang ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
* **Neurala Nätverk** och **Djupinlärning**, som är kärnan i modern AI. Vi kommer att illustrera koncepten bakom dessa viktiga ämnen med kod i två av de mest populära ramverken - [TensorFlow](http://Tensorflow.org) och [PyTorch](http://pytorch.org).
* **Neurala Arkitekturer** för arbete med bilder och text. Vi kommer att täcka nyare modeller men kan sakna en del av det allra senaste.
* Mindre vanliga AI-tillvägagångssätt, såsom **Genetiska Algoritmer** och **Multi-Agent System**.
* Olika tillvägagångssätt till Artificiell Intelligens, inklusive det "goda gamla" symboliska tillvägagångssättet med **Kunskapsrepresentation** och resonemang ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
* **Neurala Nätverk** och **Djupinlärning**, som är kärnan i modern AI. Vi kommer att illustrera koncepten bakom dessa viktiga ämnen med hjälp av kod i två av de mest populära ramverken - [TensorFlow](http://Tensorflow.org) och [PyTorch](http://pytorch.org).
* **Neurala Arkitekturer** för att arbeta med bilder och text. Vi kommer att täcka senaste modeller men kan vara något bristfälliga i det senaste inom fältet.
* Mindre populära AI-tillvägagångssätt, såsom **Genetiska Algoritmer** och **Multi-Agent System**.
Vad vi inte kommer att täcka i denna kursplan:
> [Hitta alla extra resurser för denna kurs i vår Microsoft Learn-samling](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
* Affärsfall för att använda **AI i företag**. Överväg att ta [Introduktion till AI för affärsanvändare](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) lärväg på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), utvecklad i samarbete med [INSEAD](https://www.insead.edu/).
* **Klassisk Maskininlärning**, som omfattas väl i vår [Maskininlärning för Nybörjare Kursplan](http://github.com/Microsoft/ML-for-Beginners).
* Praktiska AI-applikationer byggda med **[Kognitiva Tjänster](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. För detta rekommenderar vi att du börjar med moduler på Microsoft Learn för [vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [naturlig språkbehandling](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativ AI med Azure OpenAI-tjänst](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** med flera.
* Specifika ML **molnramverk**, såsom [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) eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Överväg att använda lärvägarna [Bygg och driftsätt maskininlärningslösningar med Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) och [Bygg och driftsätt maskininlärningslösningar med Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
* **Konverserande AI** och **Chattbotar**. Det finns en separat lärväg för [Skapa konverserande AI-lösningar](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), och du kan även hänvisa till [detta blogginlägg](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) för mer detaljer.
* **Djup matematik** bakom djupinlärning. För detta rekommenderar vi [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) av Ian Goodfellow, Yoshua Bengio och Aaron Courville, som också är tillgänglig online på [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
* Affärsfall för användning av **AI i affärer**. Överväg att ta [Introduktion till AI för affärsanvändare](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) lärväg på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), utvecklad i samarbete med [INSEAD](https://www.insead.edu/).
* **Klassisk Maskininlärning**, som är väl beskriven i vår [Maskininlärning för nybörjare-kursplan](http://github.com/Microsoft/ML-for-Beginners).
* Praktiska AI-applikationer byggda med **[Kognitiva Tjänster](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. För detta rekommenderar vi att du börjar med moduler på Microsoft Learn för [datorseende](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [bearbetning av naturligt språk](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativ AI med Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** och andra.
* Specifika ML **molnramverk**, såsom [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), eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Överväg att använda lärvägarna [Bygg och driftsätt maskininlärningslösningar med Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) och [Bygg och driftsätt maskininlärningslösningar med Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
* **Konversations-AI** och **Chattbottar**. Det finns en separat [Skapa konversations-AI lösningar](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) lärväg, och du kan även läsa [detta blogginlägg](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) för mer detaljer.
* **Djup matematik** bakom djupinlärning. För detta rekommenderar vi [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) av Ian Goodfellow, Yoshua Bengio och Aaron Courville, som också finns online på [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
För en mjuk introduktion till _AI i molnet_-ämnen kan du överväga att ta lärvägen [Kom igång med artificiell intelligens på Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
För en mjuk introduktion till _AI i molnet_-ämnen kan du överväga att gå lärvägen [Kom igång med artificiell intelligens på Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
# Innehåll
| | Lektionlänk | PyTorch/Keras/TensorFlow | Lab |
| | Lektion Länk | PyTorch/Keras/TensorFlow | Lab |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
| 0 | [Kursinställning](./lessons/0-course-setup/setup.md) | [Ställ in din utvecklingsmiljö](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Introduktion till AI**](./lessons/1-Intro/README.md) | | |
| 01 | [Introduktion och AI:s historia](./lessons/1-Intro/README.md) | - | - |
| II | **Symbolisk AI** |
| 02 | [Kunskapsrepresentation och expertsystem](./lessons/2-Symbolic/README.md) | [Expertsystem](./lessons/2-Symbolic/Animals.ipynb) / [Ontologi](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Begreppsgraf](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Introduktion till Neurala Nätverk**](./lessons/3-NeuralNetworks/README.md) |||
| III | [**Introduktion till neurala nätverk**](./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 | [Flerlagers Perceptron och skapa vårt eget ramverk](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
| 04 | [Flerlagers perceptron och skapa vårt eget ramverk](./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 | [Introduktion till ramverk (PyTorch/TensorFlow) och överanpassning](./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 | [**Datorseende**](./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)| [Utforska datorseende på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
| 06 | [Introduktion till datorseende. 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 | [Konvolutionella neurala nätverk](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkitekturer](./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 | [Förtränade nätverk och överföringsinlärning](./lessons/4-ComputerVision/08-TransferLearning/README.md) och [Träningsknep](./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) |
| 08 | [Förtränade nätverk och transfer learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) och [Träningsknep](./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 | [Autoenkodare och VAE:er](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
| 10 | [Generativa adversariella nätverk & konstnärlig stilöverföring](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Objektigenkänning](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
| 10 | [Generativa adversariella nätverk och stilöverföring](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Objektdetektering](./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 | [Semantisk segmentering. 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 | [**Naturlig språkbehandling**](./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) | [Utforska naturlig språkbehandling på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Textrepresentation. 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) | |
| 13 | [Textrepresentation. Bag of Words/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 | [Semantiska ordinbäddningar. Word2Vec och 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 | [Språkmodellering. Träna dina egna inbäddningar](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 15 | [Språkmodellering. Träna egna inbäddningar](./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 | [Generativa rekurrenta nätverk](./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 | [Namngiven entities-igenkänning](./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 | [Stora språkmodeller, promptprogrammering och få-skott-uppgifter](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| 19 | [Named Entity Recognition (NAMN)](./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 | [Stora språkmodeller, promptprogrammering och få-skotts-uppgifter](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Andra AI-tekniker** || |
| 21 | [Genetiska algoritmer](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
| 22 | [Djup förstärkningsinlärning](./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) |
@ -119,51 +110,52 @@ För en mjuk introduktion till _AI i molnet_-ämnen kan du överväga att ta lä
## Varje lektion innehåller
* Förberedande läsmaterial
* Exekverbara Jupyter Notebooks, som ofta är specifika för ramverket (**PyTorch** eller **TensorFlow**). Den exekverbara notebooken innehåller också mycket teoretiskt material, så för att förstå ämnet behöver du gå igenom minst en version av notebooken (antingen PyTorch eller TensorFlow).
* **Laborationer** tillgängliga för vissa ämnen, som ger dig möjlighet att prova att tillämpa materialet du har lärt dig på ett specifikt problem.
* Körbara Jupyter Notebooks, som ofta är specifika för ramverket (**PyTorch** eller **TensorFlow**). Den körbara notebooken innehåller också mycket teoretiskt material, så för att förstå ämnet behöver du gå igenom minst en version av notebooken (antingen PyTorch eller TensorFlow).
* **Laborationer** tillgängliga för vissa ämnen, som ger dig möjlighet att prova att tillämpa materialet du lärt dig på ett specifikt problem.
* Vissa avsnitt innehåller länkar till [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moduler som täcker relaterade ämnen.
## Kom igång
### 🎯 Ny till AI? Börja här!
### 🎯 Nybörjare inom AI? Börja här!
Om du är helt ny inom AI och vill ha snabba, praktiska exempel, kolla in våra [**nybörjarvänliga exempel**](./examples/README.md)! Dessa inkluderar:
Om du är helt ny inom AI och vill ha snabba, praktiska exempel, kolla in våra [**Nybörjarvänliga exempel**](./examples/README.md)! Dessa inkluderar:
- 🌟 **Hello AI World** - Ditt första AI-program (mönsterigenkänning)
- 🌟 **Hej AI-världen** - Ditt första AI-program (mönsterigenkänning)
- 🧠 **Enkel neuralt nätverk** - Bygg ett neuralt nätverk från grunden
- 🖼️ **Bildklassificerare** - Klassificera bilder med detaljerade kommentarer
- 💬 **Textsentiment** - Analysera positiv/negativ text
Dessa exempel är utformade för att hjälpa dig att förstå AI-koncept innan du dyker in i hela läroplanen.
### 📚 Fullständig läroplansinstallation
### 📚 Fullständig Curriculum-inställning
- Vi har skapat en [installationslektion](./lessons/0-course-setup/setup.md) för att hjälpa dig att sätta upp din utvecklingsmiljö. - För lärare har vi också skapat en [läroplansinstallationslektion](./lessons/0-course-setup/for-teachers.md)!
- Vi har skapat en [installationslektion](./lessons/0-course-setup/setup.md) för att hjälpa dig med att ställa in din utvecklingsmiljö. - För lärare har vi också skapat en [curriculum-inställningslektion](./lessons/0-course-setup/for-teachers.md)!
- Hur man [kör koden i VSCode eller en Codespace](./lessons/0-course-setup/how-to-run.md)
Följ dessa steg:
Forka arkivet: Klicka på knappen "Fork" uppe till höger på denna sida.
Gaffla arkivet: Klicka på "Fork"-knappen i övre högra hörnet av denna sida.
Klona arkivet: `git clone https://github.com/microsoft/AI-For-Beginners.git`
Klon arkivet: `git clone https://github.com/microsoft/AI-For-Beginners.git`
Glöm inte att ge stjärna (🌟) till detta repo för att hitta det lättare senare.
Glöm inte att stjärnmärka (🌟) detta repo för att hitta det lättare senare.
## Träffa andra studerande
## Möt andra elever
Gå med i vår [officiella AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) för att träffa och nätverka med andra som tar denna kurs och få support.
Gå med i vår [officiella AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) för att mötas och nätverka med andra elever som går kursen och få stöd.
Om du har produktfeedback eller frågor under byggandet, besök vår [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
Om du har produktfeedback eller frågor under byggandet, besök vårt [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
## Quizzer
## Quiz
> **En notis om quizzer**: Alla quizzer finns i Quiz-app-mappen i etc\quiz-app, eller [Online här](https://ff-quizzes.netlify.app/) De är länkade från lektionerna, quiz-appen kan köras lokalt eller distribueras till Azure; följ instruktionerna i `quiz-app`-mappen. De håller på att gradvis lokaliseras.
> **En notis om quiz**: Alla quiz finns i Quiz-app-mappen i etc\quiz-app, eller [online här](https://ff-quizzes.netlify.app/). De länkas från lektionerna; quiz-appen kan köras lokalt eller distribueras till Azure; följ instruktionerna i `quiz-app`-mappen. De lokaliseras gradvis.
## Hjälp efterfrågas
## Hjälp önskas
Har du förslag eller hittat stavfel eller kodfel? Skapa en issue eller skicka en pull request.
Har du förslag eller hittat stavfel eller kodfel? Skapa en issue eller ett pull request.
## Specialtack
## Speciella tack
* **✍️ Huvudförfattare:** [Dmitry Soshnikov](http://soshnikov.com), PhD
* **🔥 Redaktör:** [Jen Looper](https://twitter.com/jenlooper), PhD
@ -182,7 +174,7 @@ Vårt team producerar andra läroplaner! Kolla in:
---
### Azure / Edge / MCP / Agenter
### Azure / Edge / MCP / Agents
[![AZD for Beginners](https://img.shields.io/badge/AZD%20for%20Beginners-0078D4?style=for-the-badge&labelColor=E5E7EB&color=0078D4)](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
[![Edge AI for Beginners](https://img.shields.io/badge/Edge%20AI%20for%20Beginners-00B8E4?style=for-the-badge&labelColor=E5E7EB&color=00B8E4)](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
[![MCP for Beginners](https://img.shields.io/badge/MCP%20for%20Beginners-009688?style=for-the-badge&labelColor=E5E7EB&color=009688)](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
@ -198,36 +190,36 @@ Vårt team producerar andra läroplaner! Kolla in:
---
### Kärninlärning
### Kärnlärande
[![ML for Beginners](https://img.shields.io/badge/ML%20for%20Beginners-22C55E?style=for-the-badge&labelColor=E5E7EB&color=22C55E)](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
[![Data Science for Beginners](https://img.shields.io/badge/Data%20Science%20for%20Beginners-84CC16?style=for-the-badge&labelColor=E5E7EB&color=84CC16)](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
[![AI for Beginners](https://img.shields.io/badge/AI%20for%20Beginners-A3E635?style=for-the-badge&labelColor=E5E7EB&color=A3E635)](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
[![Cybersecurity for Beginners](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
[![Web Dev for Beginners](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
[![IoT for Beginners](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
[![XR Development for Beginners](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
[![Cybersäkerhet för nybörjare](https://img.shields.io/badge/Cybersecurity%20for%20Beginners-F97316?style=for-the-badge&labelColor=E5E7EB&color=F97316)](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
[![Webbutveckling för nybörjare](https://img.shields.io/badge/Web%20Dev%20for%20Beginners-EC4899?style=for-the-badge&labelColor=E5E7EB&color=EC4899)](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
[![IoT för nybörjare](https://img.shields.io/badge/IoT%20for%20Beginners-14B8A6?style=for-the-badge&labelColor=E5E7EB&color=14B8A6)](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
[![XR-utveckling för nybörjare](https://img.shields.io/badge/XR%20Development%20for%20Beginners-38BDF8?style=for-the-badge&labelColor=E5E7EB&color=38BDF8)](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
---
### Copilot-serie
[![Copilot for AI Paired Programming](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
[![Copilot for C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
[![Copilot Adventure](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
[![Copilot för AI-parprogrammering](https://img.shields.io/badge/Copilot%20for%20AI%20Paired%20Programming-FACC15?style=for-the-badge&labelColor=E5E7EB&color=FACC15)](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
[![Copilot för C#/.NET](https://img.shields.io/badge/Copilot%20for%20C%23/.NET-FBBF24?style=for-the-badge&labelColor=E5E7EB&color=FBBF24)](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
[![Copilotäventyr](https://img.shields.io/badge/Copilot%20Adventure-FDE68A?style=for-the-badge&labelColor=E5E7EB&color=FDE68A)](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
<!-- CO-OP TRANSLATOR OTHER COURSES END -->
## Få hjälp
Om du fastnar eller har frågor om att bygga AI-appar. Gå med i diskussioner med medstudenter och erfarna utvecklare om MCP. Det är en stödjande gemenskap där frågor är välkomna och kunskap delas fritt.
Om du fastnar eller har frågor om att bygga AI-appar. Gå med bland andra elever och erfarna utvecklare i diskussioner om MCP. Det är en stödjande gemenskap där frågor är välkomna och kunskap delas fritt.
[![Microsoft Foundry Discord](https://dcbadge.limes.pink/api/server/nTYy5BXMWG)](https://discord.gg/nTYy5BXMWG)
Om du har produktfeedback eller felmeddelanden under byggandet, besök:
Om du har produktfeedback eller fel under byggandet, besök:
[![Microsoft Foundry Developer Forum](https://img.shields.io/badge/GitHub-Microsoft_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum)
---
<!-- CO-OP TRANSLATOR DISCLAIMER START -->
**Ansvarsfriskrivning**:
Detta dokument har översatts med hjälp av AI-översättningstjänsten [Co-op Translator](https://github.com/Azure/co-op-translator). Trots att vi strävar efter noggrannhet, vänligen observera att automatiska översättningar kan innehålla fel eller brister. Det ursprungliga dokumentet på dess ursprungliga språk ska betraktas som den auktoritativa källan. För viktig information rekommenderas professionell mänsklig översättning. Vi ansvarar inte för några missförstånd eller feltolkningar som kan uppstå till följd av användningen av denna översättning.
**Ansvarsfriskrivning**:
Detta dokument har översatts med hjälp av AI-översättningstjänsten [Co-op Translator](https://github.com/Azure/co-op-translator). Även om vi strävar efter noggrannhet, vänligen observera att automatiska översättningar kan innehålla fel eller brister. Det ursprungliga dokumentet på dess modersmål bör betraktas som den auktoritativa källan. För kritisk information rekommenderas professionell mänsklig översättning. Vi ansvarar inte för eventuella missförstånd eller feltolkningar som uppstår genom användningen av denna översättning.
<!-- CO-OP TRANSLATOR DISCLAIMER END -->

9
translations/sv/SECURITY.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
"translation_date": "2025-08-28T15:01:34+00:00",
"source_file": "SECURITY.md",
"language_code": "sv"
}
-->
## Säkerhet
Microsoft tar säkerheten för våra mjukvaruprodukter och tjänster på största allvar, vilket inkluderar alla källkodsförråd som hanteras via våra GitHub-organisationer, såsom [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) och [våra GitHub-organisationer](https://opensource.microsoft.com/).

9
translations/sv/etc/CODE_OF_CONDUCT.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
"translation_date": "2025-08-28T16:06:50+00:00",
"source_file": "etc/CODE_OF_CONDUCT.md",
"language_code": "sv"
}
-->
# Microsoft Open Source Uppförandekod
Det här projektet har antagit [Microsoft Open Source Uppförandekod](https://opensource.microsoft.com/codeofconduct/).

9
translations/sv/etc/CONTRIBUTING.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "847a587aa1b83f4d00858183ff3ed18a",
"translation_date": "2025-08-28T16:06:24+00:00",
"source_file": "etc/CONTRIBUTING.md",
"language_code": "sv"
}
-->
# Bidra
Det här projektet välkomnar bidrag och förslag. De flesta bidrag kräver att du godkänner ett Contributor License Agreement (CLA) som intygar att du har rätt att, och faktiskt gör, ge oss rättigheterna att använda ditt bidrag. För mer information, besök https://cla.microsoft.com.

9
translations/sv/etc/Mindmap.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
"translation_date": "2025-08-28T16:04:36+00:00",
"source_file": "etc/Mindmap.md",
"language_code": "sv"
}
-->
# AI
## [Introduktion till AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)

9
translations/sv/etc/SUPPORT.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "fdfc08baee91e402938a2b1f94fe0949",
"translation_date": "2025-08-28T16:03:53+00:00",
"source_file": "etc/SUPPORT.md",
"language_code": "sv"
}
-->
# Support
## Hur man rapporterar problem och får hjälp

9
translations/sv/etc/TRANSLATIONS.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
"translation_date": "2025-08-28T16:05:54+00:00",
"source_file": "etc/TRANSLATIONS.md",
"language_code": "sv"
}
-->
# Bidra genom att översätta lektioner
Vi välkomnar översättningar av lektionerna i detta läroplan!

9
translations/sv/etc/quiz-app/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "d699cf8509f74baa5b0b838de5cf0662",
"translation_date": "2025-08-28T16:07:07+00:00",
"source_file": "etc/quiz-app/README.md",
"language_code": "sv"
}
-->
# Quizzer
Dessa quizzer är för- och efterföreläsningsquizzer för AI-kursplanen på https://aka.ms/ai-beginners

9
translations/sv/examples/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
"translation_date": "2025-10-03T11:31:15+00:00",
"source_file": "examples/README.md",
"language_code": "sv"
}
-->
# Nybörjarvänliga AI-exempel
Välkommen! Den här katalogen innehåller enkla, fristående exempel för att hjälpa dig komma igång med AI och maskininlärning. Varje exempel är utformat för att vara nybörjarvänligt med detaljerade kommentarer och steg-för-steg-förklaringar.

9
translations/sv/lessons/0-course-setup/for-teachers.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a094ef9927883de1cfcee51dbd143381",
"translation_date": "2025-08-28T15:07:54+00:00",
"source_file": "lessons/0-course-setup/for-teachers.md",
"language_code": "sv"
}
-->
# För lärare
Vill du använda detta kursmaterial i ditt klassrum? Varsågod!

9
translations/sv/lessons/0-course-setup/how-to-run.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a4717bd9103b9f6cd84d534b83534689",
"translation_date": "2026-01-16T02:22:35+00:00",
"source_file": "lessons/0-course-setup/how-to-run.md",
"language_code": "sv"
}
-->
# Hur man kör koden
Detta kursmaterial innehåller många exekverbara exempel och labbar som du vill köra. För att göra detta behöver du möjligheten att köra Python-kod i Jupyter Notebook-filer som tillhandahålls som en del av detta kursmaterial. Du har flera alternativ för att köra koden:

9
translations/sv/lessons/0-course-setup/setup.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
"translation_date": "2025-12-12T19:50:22+00:00",
"source_file": "lessons/0-course-setup/setup.md",
"language_code": "sv"
}
-->
# Komma igång med denna läroplan
## Är du en student?

9
translations/sv/lessons/1-Intro/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
"translation_date": "2025-11-18T21:31:40+00:00",
"source_file": "lessons/1-Intro/README.md",
"language_code": "sv"
}
-->
# Introduktion till AI
![Sammanfattning av innehållet i Introduktion till AI i en skiss](../../../../translated_images/sv/ai-intro.bf28d1ac4235881c.webp)

9
translations/sv/lessons/1-Intro/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a334df77a82aaaf2a29c77065d3e481e",
"translation_date": "2025-11-18T21:32:40+00:00",
"source_file": "lessons/1-Intro/assignment.md",
"language_code": "sv"
}
-->
# Speljam
Spel är ett område som har påverkats starkt av utvecklingen inom AI och ML. I denna uppgift ska du skriva en kort uppsats om ett spel som du gillar och som har påverkats av AI:s utveckling. Det bör vara ett tillräckligt gammalt spel för att ha påverkats av flera typer av databehandlingssystem. Ett bra exempel är schack eller Go, men titta också på videospel som Pong eller Pac-Man. Skriv en uppsats som diskuterar spelets förflutna, nutid och AI-framtid.

17
translations/sv/lessons/2-Symbolic/README.md
View File

@ -1,15 +1,6 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
"translation_date": "2026-01-16T02:22:50+00:00",
"source_file": "lessons/2-Symbolic/README.md",
"language_code": "sv"
}
-->
# Kunskapsrepresentation och expertsystem
![Summary of Symbolic AI content](../../../../../../translated_images/sv/ai-symbolic.715a30cb610411a6.webp)
![Summary of Symbolic AI content](../../../../translated_images/sv/ai-symbolic.715a30cb610411a6.webp)
> Sketchnote av [Tomomi Imura](https://twitter.com/girlie_mac)
@ -41,7 +32,7 @@ Ofta definierar vi inte kunskap strikt, utan vi relaterar det till andra närlig
Således är problemet med **kunskapsrepresentation** att finna ett effektivt sätt att representera kunskap i en dator i form av data, för att göra den automatiskt användbar. Detta kan ses som ett spektrum:
![Knowledge representation spectrum](../../../../../../translated_images/sv/knowledge-spectrum.b60df631852c0217.webp)
![Knowledge representation spectrum](../../../../translated_images/sv/knowledge-spectrum.b60df631852c0217.webp)
> Bild av [Dmitry Soshnikov](http://soshnikov.com)
@ -94,7 +85,7 @@ Blocksyntax | Indent | | |
En av de tidiga framgångarna för symbolisk AI var de så kallade **expertsystemen** – datasystem utformade för att agera som experter inom ett begränsat problemområde. De byggde på en **kunskapsbas** extraherad från en eller flera mänskliga experter, och innehöll en **slutledningsmotor** som utförde resonemang ovanpå den.
![Human Architecture](../../../../../../translated_images/sv/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../../../translated_images/sv/arch-kbs.3ec5c150b09fa8da.webp)
![Human Architecture](../../../../translated_images/sv/arch-human.5d4d35f1bba3ab1c.webp) | ![Knowledge-Based System](../../../../translated_images/sv/arch-kbs.3ec5c150b09fa8da.webp)
---------------------------------------------|------------------------------------------------
Förenklad struktur av ett mänskligt nervsystem | Arkitektur för ett kunskapsbaserat system
@ -106,7 +97,7 @@ Expertsystem byggs som det mänskliga resonemangssystemet, som innehåller **kor
Som exempel, låt oss betrakta följande expertsystem för att bestämma ett djur baserat på dess fysiska egenskaper:
![AND-OR Tree](../../../../../../translated_images/sv/AND-OR-Tree.5592d2c70187f283.webp)
![AND-OR Tree](../../../../translated_images/sv/AND-OR-Tree.5592d2c70187f283.webp)
> Bild av [Dmitry Soshnikov](http://soshnikov.com)

9
translations/sv/lessons/2-Symbolic/assignment.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a057a8604f3976c3e309884453f1fad0",
"translation_date": "2025-08-28T15:30:53+00:00",
"source_file": "lessons/2-Symbolic/assignment.md",
"language_code": "sv"
}
-->
# Bygg en ontologi
Att bygga en kunskapsbas handlar om att kategorisera en modell som representerar fakta om ett ämne. Välj ett ämne - som en person, en plats eller en sak - och bygg sedan en modell av det ämnet. Använd några av de tekniker och strategier för modellbyggande som beskrivs i denna lektion. Ett exempel skulle vara att skapa en ontologi för ett vardagsrum med möbler, lampor och så vidare. Hur skiljer sig vardagsrummet från köket? Badrummet? Hur vet du att det är ett vardagsrum och inte en matsal? Använd [Protégé](https://protege.stanford.edu/) för att bygga din ontologi.

13
translations/sv/lessons/3-NeuralNetworks/03-Perceptron/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "c34cbba802058b6fa267e1a294d4e510",
"translation_date": "2025-09-23T09:22:26+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
"language_code": "sv"
}
-->
# Introduktion till neurala nätverk: Perceptron
## [Quiz före föreläsning](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@ -15,7 +6,7 @@ Ett av de första försöken att implementera något liknande ett modernt neural
| | |
|--------------|-----------|
|<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/sv/Rosenblatt-wikipedia.294821b285ac796d.webp' alt='Frank Rosenblatt'/> | <img src='../../../../../translated_images/sv/Mark_I_perceptron_wikipedia.1f84eaa2d4b76ec9.webp' alt='The Mark 1 Perceptron' />|
> Bilder [från Wikipedia](https://en.wikipedia.org/wiki/Perceptron)
@ -34,7 +25,7 @@ y(x) = f(w<sup>T</sup>x)
där f är en stegaktiveringsfunktion
<!-- 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/sv/activation-func.b4924007c7ce7764.webp"/>
## Träning av perceptron

9
translations/sv/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
"translation_date": "2025-08-29T08:26:33+00:00",
"source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
"language_code": "sv"
}
-->
# Multi-klassklassificering med Perceptron
Labuppgift från [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

11
translations/sv/lessons/3-NeuralNetworks/04-OwnFramework/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "789d6c3fb6fc7948a470b33078a5983a",
"translation_date": "2025-09-23T09:21:43+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
"language_code": "sv"
}
-->
# Introduktion till neurala nätverk. Flerlagers perceptron
I föregående avsnitt lärde du dig om den enklaste modellen för neurala nätverk – en enlagers perceptron, en linjär tvåklassklassificeringsmodell.
@ -65,7 +56,7 @@ Gradientnedstigningsalgoritmen förblir densamma, men det blir svårare att ber
Observera att den vänstra delen av alla dessa uttryck är densamma, och därför kan vi effektivt beräkna derivatorna genom att börja från förlustfunktionen och gå "bakåt" genom beräkningsgrafen. Därför kallas metoden för att träna ett flerlagers perceptron för **backpropagation**, eller 'backprop'.
<img alt="compute graph" src="images/ComputeGraphGrad.png"/>
<img alt="compute graph" src="../../../../../translated_images/sv/ComputeGraphGrad.4626252c0de03507.webp"/>
> TODO: bildcitering

9
translations/sv/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
"translation_date": "2025-08-28T15:38:05+00:00",
"source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
"language_code": "sv"
}
-->
# MNIST-klassificering med vårt eget ramverk
Labuppgift från [AI för nybörjare-kursen](https://github.com/microsoft/ai-for-beginners).

9
translations/sv/lessons/3-NeuralNetworks/05-Frameworks/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ddd216f558a255260a9374008002c971",
"translation_date": "2025-09-23T09:22:45+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
"language_code": "sv"
}
-->
# Ramverk för neurala nätverk
Som vi redan har lärt oss, för att kunna träna neurala nätverk effektivt behöver vi göra två saker:

9
translations/sv/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "e452d897efb9a89700f41021834cf6e5",
"translation_date": "2025-08-28T15:41:56+00:00",
"source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
"language_code": "sv"
}
-->
# Klassificering med PyTorch/TensorFlow
Labuppgift från [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

9
translations/sv/lessons/3-NeuralNetworks/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "f862a99d88088163df12270e2f2ad6c3",
"translation_date": "2025-10-03T12:49:15+00:00",
"source_file": "lessons/3-NeuralNetworks/README.md",
"language_code": "sv"
}
-->
# Introduktion till neurala nätverk
![Sammanfattning av innehållet i Introduktion till neurala nätverk i en skiss](../../../../translated_images/sv/ai-neuralnetworks.1c687ae40bc86e83.webp)

11
translations/sv/lessons/4-ComputerVision/06-IntroCV/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "feeca98225cb420afc89415f24f63d92",
"translation_date": "2025-09-23T09:17:24+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
"language_code": "sv"
}
-->
# Introduktion till datorseende
[Computer Vision](https://wikipedia.org/wiki/Computer_vision) är ett område som syftar till att ge datorer en hög nivå av förståelse för digitala bilder. Detta är en ganska bred definition, eftersom *förståelse* kan innebära många olika saker, inklusive att hitta ett objekt på en bild (**objektdetektion**), förstå vad som händer (**händelsedetektion**), beskriva en bild i text eller rekonstruera en scen i 3D. Det finns också specifika uppgifter relaterade till bilder av människor: ålders- och känsloestimering, ansiktsdetektion och identifiering, samt 3D-positionsestimering, för att nämna några.
@ -115,7 +106,7 @@ Läs mer om optiskt flöde [i denna utmärkta handledning](https://learnopencv.c
I detta labb kommer du att ta en video med enkla gester, och ditt mål är att extrahera upp/ner/vänster/höger rörelser med hjälp av optiskt flöde.
<img src="images/palm-movement.png" width="30%" alt="Palm Movement Frame"/>
<img src="../../../../../translated_images/sv/palm-movement.341495f0e9c47da3.webp" width="30%" alt="Palm Movement Frame"/>
---

9
translations/sv/lessons/4-ComputerVision/06-IntroCV/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "3d53d6409f80970f7281a45dee35328a",
"translation_date": "2025-08-28T15:20:05+00:00",
"source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
"language_code": "sv"
}
-->
# Upptäcka rörelser med optisk flöde
Labuppgift från [AI för nybörjare-kursen](https://aka.ms/ai-beginners).

13
translations/sv/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
"translation_date": "2025-09-23T09:16:43+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
"language_code": "sv"
}
-->
# Välkända CNN-arkitekturer
### VGG-16
@ -25,7 +16,7 @@ Som du kan se följer VGG en traditionell pyramidarkitektur, vilket är en sekve
ResNet är en familj av modeller som föreslogs av Microsoft Research år 2015. Huvudidén med ResNet är att använda **residualblock**:
<img src="images/resnet-block.png" width="300"/>
<img src="../../../../../translated_images/sv/resnet-block.aba4ccbcc0944434.webp" width="300"/>
> Bild från [denna artikel](https://arxiv.org/pdf/1512.03385.pdf)
@ -37,7 +28,7 @@ Du kan också tänka på detta nätverk som att det kan anpassa sin komplexitet
Google Inception-arkitekturen tar denna idé ett steg längre och bygger varje nätverkslager som en kombination av flera olika vägar:
<img src="images/inception.png" width="400"/>
<img src="../../../../../translated_images/sv/inception.a6605b85bcbc6f52.webp" width="400"/>
> Bild från [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)

11
translations/sv/lessons/4-ComputerVision/07-ConvNets/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "a560d5b845962cf33dc102266e409568",
"translation_date": "2025-09-23T09:16:25+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
"language_code": "sv"
}
-->
# Konvolutionella neurala nätverk
Vi har tidigare sett att neurala nätverk är ganska bra på att hantera bilder, och till och med en enkel lager-perceptron kan känna igen handskrivna siffror från MNIST-datasetet med rimlig noggrannhet. Men MNIST-datasetet är väldigt speciellt, eftersom alla siffror är centrerade i bilden, vilket gör uppgiften enklare.
@ -24,7 +15,7 @@ För att extrahera mönster kommer vi att använda begreppet **konvolutionella f
Till exempel, om vi applicerar 3x3 vertikala och horisontella kantfilter på MNIST-siffrorna, kan vi få framhöjningar (t.ex. höga värden) där det finns vertikala och horisontella kanter i vår ursprungliga bild. Således kan dessa två filter användas för att "leta efter" kanter. På samma sätt kan vi designa olika filter för att leta efter andra låg-nivå mönster:
<img src="images/lmfilters.jpg" width="500" align="center"/>
<img src="../../../../../translated_images/sv/lmfilters.ea9e4868a82cf74c.webp" width="500" align="center"/>
> Bild av [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)

9
translations/sv/lessons/4-ComputerVision/07-ConvNets/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "b70fcf7fcee862990f848c679090943f",
"translation_date": "2025-10-03T14:55:20+00:00",
"source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
"language_code": "sv"
}
-->
# Klassificering av husdjursansikten
Labuppgift från [AI för nybörjare-kursen](https://github.com/microsoft/ai-for-beginners).

9
translations/sv/lessons/4-ComputerVision/08-TransferLearning/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
"translation_date": "2025-09-23T09:17:00+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
"language_code": "sv"
}
-->
# Förtränade nätverk och transfer learning
Att träna CNNs kan ta mycket tid, och det krävs en stor mängd data för att utföra uppgiften. Mycket av tiden går åt till att lära nätverket de bästa låg-nivåfiltren för att kunna extrahera mönster från bilder. En naturlig fråga uppstår - kan vi använda ett neuralt nätverk som tränats på ett dataset och anpassa det för att klassificera andra bilder utan att behöva genomföra en fullständig träningsprocess?

9
translations/sv/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
"translation_date": "2025-08-28T15:15:46+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
"language_code": "sv"
}
-->
# Träningsknep för djupinlärning
När neurala nätverk blir djupare blir processen att träna dem alltmer utmanande. Ett stort problem är de så kallade [försvinnande gradienterna](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) eller [exploderande gradienter](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Det här inlägget](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) ger en bra introduktion till dessa problem.

9
translations/sv/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
View File

@ -1,12 +1,3 @@
<!--
CO_OP_TRANSLATOR_METADATA:
{
"original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
"translation_date": "2025-08-28T15:17:45+00:00",
"source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
"language_code": "sv"
}
-->
# Klassificering av Oxford Pets med Transfer Learning
Labuppgift från [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).

Some files were not shown because too many files have changed in this diff Show More