Geometric Deep Learning book draft complete after 5+ years, all chapters free online
PetarV_93 · x · 2026-11-10
Petar Veličković announced that the full draft of the Geometric Deep Learning textbook, co-authored with Michael Bronstein, Taco Cohen and others, is finally complete after 5+ years — all chapters are now freely available online.
Per the table of contents, the book has three parts:
- Geometric foundations: supervised learning, equivariant deep learning (symmetry groups, representations, the "Equivariance Cookbook"), and the GDL blueprint
- Learning on geometric domains: graphs (with recommender-system and LLM case studies), grids (LSTM), group convolutions on homogeneous spaces (TacticAI), and geometric graphs (manifold/mesh CNNs and AlphaFold 2)
- Horizons: going beyond groups
The authors welcome errata, comments, questions and exercise proposals; suggestions leading to text changes will be credited in the acknowledgements.
Related event: Geometric Deep Learning Book Draft Completed After Five Years, Free Online(2 posts)→
More from Models
- Claude Fable 5.2 said to finish 23-year-old black hole calculation, unverified — IgorCarron · 2026-11-10
- Gemini 4 Carbon spotted in GCP SKU catalog and reportedly callable on Vertex AI — testingcatalog · 2026-11-10
- The Harness, Not the Architecture, Is Where AI's Long-Term Value Accrues — DrDatta_AIIMS · 2026-11-10
- LingBot-Touch: a foundation model for heterogeneous tactile representation learning lands on HF — _akhaliq · 2026-11-10
- TuF Labs tops ARC-AGI-2 leaderboard: general approaches now beat domain-specific tricks — rbhar90 · 2026-11-10
- Gemini users hit new science guardrails: model refuses physics chats and suggests therapy — ElderMillennialBrain · 2026-11-10