Repolode
Submit
microsoft

microsoft/AI-For-Beginners

A 12-week, 24-lesson beginner AI curriculum from Microsoft covering symbolic AI, neural networks, computer vision, NLP and ethics, with notebooks in PyTorch and TensorFlow.

View on GitHub
Stars
70,058
Forks
13,589
Open issues
24
Last commit
last month

What is it?

AI For Beginners is a structured course that introduces artificial intelligence from its symbolic roots to modern deep learning. It is organized into 24 lessons across 12 weeks, grouped into sections on symbolic AI, neural network fundamentals, computer vision, natural language processing, other techniques such as genetic algorithms and deep reinforcement learning, and AI ethics.

Each lesson includes pre-reading material, Jupyter notebooks that are typically provided in both PyTorch and TensorFlow, and optional labs. Quizzes are offered through a separate quiz app. The course is aimed at beginners and does not cover classic machine learning, business applications of AI, or Cognitive Services in depth; those topics are directed to other Microsoft Learn resources.

The repository is available in dozens of translations and can be run locally, in VS Code, or in a GitHub Codespace.

Key features

  • 0124 lessons over 12 weeks covering AI from symbolic methods to modern deep learning.
  • 02Jupyter notebooks provided in PyTorch and TensorFlow versions for many lessons.
  • 03Labs for selected topics, such as perceptrons, CNNs and deep reinforcement learning.
  • 04Coverage of computer vision, NLP, transformers, LLMs and generative models like GANs.
  • 05Dedicated lesson on AI ethics and responsible AI.
  • 06Translated into dozens of languages.

Use cases

  • A developer with little AI background who wants a structured path into neural networks.
  • A teacher building a semester-long introductory AI course with ready-made notebooks and labs.
  • A student comparing PyTorch and TensorFlow implementations of the same model.
  • Someone who wants to study CNNs, transfer learning or GANs with runnable code.

Quick start

  1. 1

    Clone the repository without translations (sparse checkout)

    git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git
  2. 2

    Enter the project folder

    cd AI-For-Beginners
  3. 3

    Limit the checkout to the course content (Bash, macOS or Linux)

    git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'
  4. 4

    Follow the setup guide in lessons/0-course-setup to run the notebooks

Things to know

  • The curriculum does not cover classic machine learning, business AI use cases or Cognitive Services in depth.
  • It may be somewhat behind the state of the art in recent models.
  • The repository with all translations is large, so a sparse checkout is recommended.

Topics

#artificial-intelligence#machine-learning#deep-learning#neural-networks#computer-vision#nlp#pytorch#tensorflow#ai#cnn

FAQ

What is AI-For-Beginners?
A 12-week, 24-lesson beginner AI curriculum from Microsoft covering symbolic AI, neural networks, computer vision, NLP and ethics, with notebooks in PyTorch and TensorFlow. AI For Beginners is a structured course that introduces artificial intelligence from its symbolic roots to modern deep learning. It is organized into 24 lessons across 12 weeks, grouped into sections on symbolic AI, neural network fundamentals, computer vision, natural language processing, other techniques such as genetic algorithms and deep reinforcement learning, and AI ethics.
Is AI-For-Beginners free to use? What license does it have?
AI-For-Beginners is open source under the MIT license. Check the license terms before using it in commercial products.
Is AI-For-Beginners still maintained?
Updated within 6 months. The last commit to AI-For-Beginners was on Sep 16, 2026.
What can I use AI-For-Beginners for?
A developer with little AI background who wants a structured path into neural networks. A teacher building a semester-long introductory AI course with ready-made notebooks and labs. A student comparing PyTorch and TensorFlow implementations of the same model. Someone who wants to study CNNs, transfer learning or GANs with runnable code.
How do I install AI-For-Beginners?
Clone the repository without translations (sparse checkout): git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git Enter the project folder: cd AI-For-Beginners Limit the checkout to the course content (Bash, macOS or Linux): git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' Follow the setup guide in lessons/0-course-setup to run the notebooks
Where can I get AI-For-Beginners?
The source code and installation instructions are on GitHub: https://github.com/microsoft/AI-For-Beginners

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects