Volume 2 of 4 · PDF and notebooks
Physics, Architectures, and Learning
Connect geometry, physics, causality, and uncertainty with the architectures and training methods used to learn world models at scale.
18 chapters · 637 pages · Perpetual updates
What you will learn
- Represent physical and causal structure without treating every regularity as a law.
- Compare recurrent, transformer, token, diffusion, and embedding-based models.
- Design data, objectives, and training procedures around the model's intended use.
Before you start
The state, probability, and control foundations in Volume 1, plus familiarity with neural networks and gradient-based optimization.
Own Volume 2
$29 once. The PDF and companion notebook ZIP are yours to download, with every future update to this volume included.
Prefer all four volumes? Library access is $79. Owned volumes receive full upgrade credit; three distinct volumes unlock the library automatically. No combined PDF is delivered.
Included chapters
All chapters remain free to read online.
Part IV: Space, Physics, and Causality
Part V: World-Model Architectures
Version history
Kept current, not frozen in time
Library access includes every future volume and update. When a volume changes, its updated PDF appears in My books at no extra cost.
Current release
Edition 2026.10.0
First edition: 72 chapters across four standalone volume PDFs, with executable companion notebooks and perpetual updates.
Author and edition details
About the author and this edition
Michael Brenndoerfer
Michael has spent more than a decade working across software engineering, data, AI, and business. He writes to understand difficult ideas more deeply and to share what he learns in a clear, practical way.
- Edition
- First edition
- Published
- Last reviewed