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)→

Original post →

More from Research

Research channel →