Learning paths

Five guided AI learning paths (Foundations, Seeing, Language, Deciding, Frontier) that alternate lessons with hands-on labs, from first principles to the…

Foundations path

Start here. What learning from data means, how networks train, and how to judge the result.

  1. AI Fundamentals (lesson)
  2. The Maths Behind ML (lesson)
  3. Machine Learning (lesson)
  4. Decision Tree Builder (lab)
  5. Forests and Boosting (lesson)
  6. Boosting Lab (lab)
  7. Evaluating Models (lesson)
  8. Confusion Matrix Explorer (lab)
  9. Neural Networks and Deep Learning (lesson)
  10. Gradient Descent Lab (lab)
  11. Neural Network Playground (lab)
  12. Unsupervised Learning (lesson)
  13. Clustering Visualizer (lab)
  14. AI Ethics and Safety (lesson)
  15. Fairness Lab (lab)

Seeing path

How machines read images, from a single convolution to detecting every object in a scene.

  1. Computer Vision (lesson)
  2. Image Filter Playground (lab)
  3. Object Detection (lesson)
  4. Object Detection Lab (lab)
  5. Image Segmentation (lesson)

Language path

From counting words to the transformers inside every modern chatbot.

  1. Natural Language Processing (lesson)
  2. Text Playground (lab)
  3. Tokenization (lesson)
  4. Tokenizer Lab (lab)
  5. Recurrent Networks Lab (lab)
  6. Machine Translation (lesson)
  7. Transformers and Attention (lesson)
  8. Attention Visualizer (lab)
  9. Transformer Explorer (lab)
  10. Generative AI (lesson)
  11. Diffusion Lab (lab)
  12. Speech and Audio AI (lesson)

Deciding path

How AI plans routes, learns strategies from reward, recommends what you see next and acts in the physical world.

  1. Search and Optimization (lesson)
  2. Pathfinding Visualizer (lab)
  3. Travelling Salesman (lab)
  4. Reinforcement Learning (lesson)
  5. Reinforcement Learning Arena (lab)
  6. Recommender Systems (lesson)
  7. Recommender Lab (lab)
  8. Robots and World Models (lesson)

Frontier path

The ideas behind the AI in the news: LLMs, retrieval, agents, decision models like Jev, and multimodal systems.

  1. Large Language Models (lesson)
  2. Next-Token Sampling Lab (lab)
  3. Prompt and Context Engineering (lesson)
  4. Scaling Laws and Pretraining (lesson)
  5. Post-Training and Alignment (lesson)
  6. Reward Model Lab (lab)
  7. Reasoning Models (lesson)
  8. Opus 5.5, Fable 5.1 and Looped Transformers (lesson)
  9. Mixture of Experts (lesson)
  10. Mixture of Experts Lab (lab)
  11. Embeddings and Retrieval (lesson)
  12. Embedding Explorer (lab)
  13. AI Agents and Tool Use (lesson)
  14. Decision Models and Jev (lesson)
  15. Calibration Lab (lab)
  16. Multimodal AI (lesson)
  17. Fine-Tuning and Efficient Models (lesson)
  18. Model Compression Lab (lab)
  19. Interpretability (lesson)