Categorical deep learning is elegant but has yet to yield practical architectures
burny_tech · x · 2026-09-23
The author frames categorical deep learning as a categorical generalization of geometric deep learning—a formal algebraic language using category theory for specifying, composing, and analyzing architectures. So far it hasn't produced novel practical architectures (mostly toy examples), whereas group theory-based geometric deep learning did. He suggests it may one day contribute similarly.
Related event: Categorical deep learning: an algebraic theory of all architectures?(2 posts)→
More from Research
- Continuous diffusion beats discrete on random k-SAT, proposed as standard benchmark — ArashVahdat · 2026-09-23
- Grady Booch: Contemporary AI Still Lacks Abductive Reasoning, Just 'Next-Token Prediction' — Grady_Booch · 2026-09-23
- AI solves Navier-Stokes-related problem as machines upend mathematics, New Scientist reports — burny_tech · 2026-09-23
- Mathematician says OpenAI likely proved a significant partial case of the Hodge conjecture — burny_tech · 2026-09-23
- Code benchmarks are mostly slop: dev calls for narrow evals per domain, not one score — almmaasoglu · 2026-09-23
- LaBinius: lattice-based polynomial commitments hit tens of thousands of hash proofs per second — burny_tech · 2026-09-23