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.
- AI Fundamentals (lesson)
- The Maths Behind ML (lesson)
- Machine Learning (lesson)
- Decision Tree Builder (lab)
- Forests and Boosting (lesson)
- Boosting Lab (lab)
- Evaluating Models (lesson)
- Confusion Matrix Explorer (lab)
- Neural Networks and Deep Learning (lesson)
- Gradient Descent Lab (lab)
- Neural Network Playground (lab)
- Unsupervised Learning (lesson)
- Clustering Visualizer (lab)
- AI Ethics and Safety (lesson)
- Fairness Lab (lab)
Seeing path
How machines read images, from a single convolution to detecting every object in a scene.
- Computer Vision (lesson)
- Image Filter Playground (lab)
- Object Detection (lesson)
- Object Detection Lab (lab)
- Image Segmentation (lesson)
Language path
From counting words to the transformers inside every modern chatbot.
- Natural Language Processing (lesson)
- Text Playground (lab)
- Tokenization (lesson)
- Tokenizer Lab (lab)
- Recurrent Networks Lab (lab)
- Machine Translation (lesson)
- Transformers and Attention (lesson)
- Attention Visualizer (lab)
- Transformer Explorer (lab)
- Generative AI (lesson)
- Diffusion Lab (lab)
- 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.
- Search and Optimization (lesson)
- Pathfinding Visualizer (lab)
- Travelling Salesman (lab)
- Reinforcement Learning (lesson)
- Reinforcement Learning Arena (lab)
- Recommender Systems (lesson)
- Recommender Lab (lab)
- 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.
- Large Language Models (lesson)
- Next-Token Sampling Lab (lab)
- Prompt and Context Engineering (lesson)
- Scaling Laws and Pretraining (lesson)
- Post-Training and Alignment (lesson)
- Reward Model Lab (lab)
- Reasoning Models (lesson)
- Opus 5.5, Fable 5.1 and Looped Transformers (lesson)
- Mixture of Experts (lesson)
- Mixture of Experts Lab (lab)
- Embeddings and Retrieval (lesson)
- Embedding Explorer (lab)
- AI Agents and Tool Use (lesson)
- Decision Models and Jev (lesson)
- Calibration Lab (lab)
- Multimodal AI (lesson)
- Fine-Tuning and Efficient Models (lesson)
- Model Compression Lab (lab)
- Interpretability (lesson)