A living reference for modern AI

Foundation

Learn modern AI from the mathematics up.

A 5,546-page reference that connects probability, optimization, neural architectures, generative models, reasoning, safety, and scientific applications. Read it as a book, teach it as slides, or explore it with an AI tutor beside you.

Start with chapter 1 Browse all chapters

Reference: 5,546; pages
Curriculum: 46; chapters
Scope: 25; parts

FOUNDATION / READER

Part I · Foundations

Begin with the common language

01IntroductionThe map of modern generative AI 02Probability and StatisticsThe language of uncertainty 03Foundations of Generative ModellingDistributions, likelihood, and learning

Read

Teach

Tutor

One body of knowledge, several ways in

Move between rigorous reading and visual intuition without changing tools.

The interface stays consistent across chapters, slides, annotations, tutor explanations, and exported notes, so attention stays on the idea rather than the software.

Read with mathematical clarity

Rendered equations, figures, definitions, examples, references, and the original PDF stay together in one focused reader.

Open the reader

Teach from visual slides

Switch to a presentation-first view with progressive reveal, annotations, navigation controls, and export-ready notes.

Explore visual lessons

Ask the built-in tutor

Question the current chapter or slide, request a deeper explanation, review annotations, and continue by voice or text.

See how tutoring works

Build intuition through motion

Animated mathematical and architectural explanations turn model behavior, optimization, and probability into visible processes.

Open a visual chapter

Complete curriculum

Find your next chapter.

Search 44 rendered chapters or browse the complete 25-part structure from foundations to scientific and agentic applications.

46 chapters

I Foundations

5 chapters

II Probabilistic Generative Models

3 chapters

III Generative Adversarial Networks

5 chapters

IV Variational and Transport Methods

3 chapters

V Autoregressive Models and Flows

2 chapters

VI Diffusion Models

4 chapters

VII Reasoning and Recursive Computation

1 chapter

23 Recurrence, Recursion, and Reasoning

VIII Memory for Large Language Models

1 chapter

24 Memory Management for Large Language Models

IX Fine-Tuning and Alignment

1 chapter

25 Fine-Tuning and Alignment

X Continual Learning

1 chapter

26 Continual Learning

XI Agentic AI and Multi-Agent Systems

1 chapter

27 Agentic AI and Multi-Agent Systems

XII Neural Network Tricks

1 chapter

28 Neural Network Tricks

XIII Privacy and Security

1 chapter

29 Membership Inference Attacks and Model Privacy

XIV Neural Architecture Search and Adaptive Networks

1 chapter

30 Neural Architecture Search and Adaptive Networks

XV Evolutionary AI: Coevolution, Open-Ended Search, and Autonomous Discovery

1 chapter

31 Evolutionary AI: Coevolution, Open-Ended Search, and Autonomous Discovery

XVI Applications of Generative Models in Retrieval

1 chapter

32 Generative Models in Retrieval: From Memory to Meaning

XVII Generative Models for Structured Data

1 chapter

33 Generative Models for Structured Data

XVIII Generative Models for Mathematics

1 chapter

34 Generative Models for Mathematics

XIX Generative Models for PDE-Based Simulation

1 chapter

35 Generative Models for PDE-Based Simulation

XX Generative Models for Medical Image Segmentation

2 chapters

XXI Interpretability and Explainability of Generative Models

1 chapter

38 Interpretability and Explainability of Generative Models

XXII Generative Models for Weather Prediction

1 chapter

39 Generative Models for Weather Prediction

XXIII Federated Learning for Generative Models

1 chapter

40 Federated Learning for Generative Models

XXIV Generative AI for Accessibility and Disabilities

1 chapter

41 Generative AI for Accessibility and Disabilities

XXV Distributed Generative AI

5 chapters