# How AI For Beginners Lessons Are Organized: A Complete Guide to the 12-Week Curriculum

> Explore the AI For Beginners curriculum structure. Discover how lessons are organized in numbered folders with READMEs, notebooks, and labs for a comprehensive AI learning journey.

- Repository: [Microsoft/AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners)
- Tags: how-to-guide
- Published: 2026-08-19

---

**The AI For Beginners repository structures its curriculum under the `lessons/` directory, using numbered folders (0 through 7 and X) that contain READMEs, executable Jupyter notebooks, and optional lab assignments to guide learners from basic setup through advanced AI concepts.**

The **microsoft/AI-For-Beginners** repository delivers a comprehensive, self-paced curriculum spanning 12 weeks of content. Understanding how these **AI For Beginners lessons** are organized helps you navigate the material efficiently, whether you are browsing manually via the root [`README.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/README.md) or automating your study workflow through the predictable file system hierarchy.

## The Hierarchical Folder Structure Under `lessons/`

All course content resides inside the top-level **`lessons/`** directory. Folders use numeric prefixes (e.g., `1-Intro`, `2-Symbolic`) to enforce a logical learning sequence that mirrors the master table documented in the root **[`README.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/README.md)** (lines 81‑99).

### Course Setup and Prerequisites (0-course-setup)

The `lessons/0-course-setup/` folder contains environment configuration guides including [`setup.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/setup.md) for installation instructions, [`how-to-run.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/how-to-run.md) for execution workflows, and [`for-teachers.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/for-teachers.md) with instructor notes.

### Introduction to AI (1-Intro)

Located in `lessons/1-Intro/`, this section provides historical context and fundamental concepts through overview materials, images, and short readings.

### Symbolic AI (2-Symbolic)

Inside `lessons/2-Symbolic/`, learners explore knowledge representation, ontologies, and expert systems through markdown introductions and Jupyter notebooks such as `Animals.ipynb`, `FamilyOntology.ipynb`, and `MSConceptGraph.ipynb`, accompanied by supporting data files.

### Neural Networks (3-NeuralNetworks)

The `lessons/3-NeuralNetworks/` directory progresses from perceptrons to deep learning frameworks. It includes progressive notebooks like `Perceptron.ipynb`, `OwnFramework.ipynb`, `IntroPyTorch.ipynb`, and `IntroKerasTF.ipynb`, plus theory PDFs and hands-on labs.

### Computer Vision (4-ComputerVision)

Found in `lessons/4-ComputerVision/`, this section covers image processing, CNNs, transfer learning, and generative models. Key notebooks include `ConvNetsPyTorch.ipynb`, `ConvNetsTF.ipynb`, auto-encoder implementations, GANs, and object detection workflows.

### Natural Language Processing (5-NLP)

The `lessons/5-NLP/` folder moves from text representation to transformers and large language models. Content includes text-representation notebooks, word-embedding exercises, RNN implementations, BERT tutorials, and LLM demonstrations.

### Other AI Techniques (6-Other)

Located in `lessons/6-Other/`, this section covers specialized paradigms including genetic algorithms (`Genetic.ipynb`), reinforcement learning (`CartPole-RL-PyTorch.ipynb`), and multi-agent systems.

### AI Ethics (7-Ethics)

The `lessons/7-Ethics/` directory focuses on responsible AI principles, fairness, and safety, containing reading materials and links to Microsoft Learn responsible-AI modules.

### Extras (X-Extras)

The `lessons/X-Extras/` folder houses cutting-edge demonstrations such as `Clip.ipynb` for CLIP models and VQ-GAN experiments that extend beyond the core curriculum.

## Standardized Lesson Layout

Every **AI For Beginners lesson** follows a consistent internal structure to reduce cognitive load and support both self-paced and instructor-led learning:

- A **[`README.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/README.md)** file that introduces the topic and links to the relevant notebooks for that section.
- One or more **Jupyter notebooks** (`*.ipynb`) that combine explanatory markdown cells with runnable code, often provided in both PyTorch and TensorFlow variants where applicable.
- An optional **`lab/`** sub-directory containing hands-on assignments and additional exercises.

## Programmatic Navigation of the Curriculum

Because the repository follows a strict naming convention and file system hierarchy, you can automate the exploration of **AI For Beginners lessons** using standard Python libraries.

```python

# List all lesson directories to verify the curriculum order

import pathlib
lesson_root = pathlib.Path("lessons")
lesson_dirs = sorted([p.name for p in lesson_root.iterdir() if p.is_dir()])
print("Lesson folders:", lesson_dirs)

```

```python

# Load a specific notebook as JSON for automated processing or validation

import json, pathlib
perceptron_nb = pathlib.Path("lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb").read_text()
nb_data = json.loads(perceptron_nb)
print("Number of cells:", len(nb_data["cells"]))

```

```python

# Execute a notebook programmatically using nbclient

from nbclient import NotebookClient
nb_path = pathlib.Path("lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb")
client = NotebookClient(nb_path.read_text())
client.execute()

```

These examples demonstrate that every notebook in the curriculum can be parsed and executed uniformly, regardless of whether the topic is symbolic AI or deep learning.

## Summary

- The curriculum organizes 12 weeks of content under `lessons/` using numbered prefixes (0, 1-7, X) that indicate progression from setup to advanced topics.
- Each lesson folder contains a [`README.md`](https://github.com/microsoft/AI-For-Beginners/blob/main/README.md), framework-agnostic or dual-framework Jupyter notebooks, and an optional `lab/` sub-directory for assignments.
- The predictable structure supports both manual navigation via the root README and programmatic access for automated testing or custom learning management systems.

## Frequently Asked Questions

### How many weeks of content are in the AI For Beginners curriculum?

The repository contains 12 weeks of structured learning material. While the folder numbering uses single digits (0-7) and a letter (X) for the extras, the content is designed to span approximately 12 weeks of study when including all labs and exercises.

### Do the lessons support multiple deep learning frameworks?

Yes. According to the source code structure in `lessons/3-NeuralNetworks/` and `lessons/4-ComputerVision/`, many lessons provide parallel notebooks for PyTorch and TensorFlow (e.g., `ConvNetsPyTorch.ipynb` and `ConvNetsTF.ipynb`), allowing you to learn using your preferred framework.

### Where are the hands-on assignments located?

Each lesson folder may contain a **`lab/`** sub-directory with practical assignments and datasets. Additionally, individual notebooks often conclude with exercise sections marked in markdown cells for you to complete.

### What is the difference between lesson 7 and lesson X?

Lesson 7 (`lessons/7-Ethics/`) covers responsible AI principles, fairness, and societal impact, while lesson X (`lessons/X-Extras/`) contains experimental, cutting-edge demonstrations such as CLIP and VQ-GAN that go beyond the core foundational curriculum.