# AI-For-Beginners

> A free 12-week, 24-lesson course on AI with notebooks, quizzes and labs

- Repository: https://github.com/microsoft/AI-For-Beginners
- Category: Learning & resource lists
- Stars: 70,133 · Forks: 13,602 · Language: Jupyter Notebook · License: MIT
- Experience: Beginner friendly
- Page: https://ir.adyog.com/repos/microsoft/ai-for-beginners/

This is a self-paced course, not a software library. It runs 12 weeks across 24 lessons. Each lesson has written material, and many have a notebook and a lab to practise on.

It starts with the older symbolic approach, where knowledge is written down as rules and ontologies. It then moves to neural networks and deep learning, with code in TensorFlow and PyTorch. Later lessons cover architectures for images and text, plus less common topics such as genetic algorithms and multi-agent systems.

The README is clear about what it leaves out. Classic machine learning is covered in Microsoft's separate Machine Learning for Beginners course. Business use of AI, Azure cloud services, chatbots and the deep maths are pointed to other resources. It also says its coverage of recent models may lag the state of the art.

## What it does

- **Structured 12-week path**: 24 lessons come with quizzes and labs alongside the reading.
- **Notebooks in two frameworks**: Lessons include Jupyter notebooks in PyTorch, Keras and TensorFlow, so you can compare them.
- **Symbolic AI to neural networks**: Covers expert systems and ontologies, then perceptrons, multi-layer networks and building your own small framework before using standard ones.
- **Computer vision track**: Starts with OpenCV and moves on to convolutional neural networks and their architectures.
- **50+ translations**: The README lists more than 50 languages and explains a sparse checkout that skips translations to shrink the download.

## What you could build

- Follow a full beginner course on AI over about three months.
- Run the Jupyter notebooks to see how a perceptron and a neural network work in code.
- Compare the same neural network written in PyTorch, Keras and TensorFlow.
- Teach an introductory AI class using the lessons, labs and quizzes.
- Learn the basics of computer vision with OpenCV and convolutional networks.

## Who it's for

Students and developers new to AI who can read basic Python code; no prior machine learning knowledge is assumed.

## Get started

Clone the repository, using the sparse checkout if you want to skip the translations, then open the course setup lesson to prepare your environment. The README also links a Binder badge for running notebooks online.

```
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'
```

Tags: curriculum, deep-learning, neural-networks, computer-vision, jupyter