A categorical algebra for deep learning that formalizes broadcasting via axis-stride and array-broadcasted categories and supplies matching Python and TypeScript implementations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Metacat is a new categorical model for formal systems using spans in cartesian PROPs to encode inference rules and symmetric monoidal categories for proofs, with a proof-checking implementation for FOL.
citing papers explorer
-
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning
A categorical algebra for deep learning that formalizes broadcasting via axis-stride and array-broadcasted categories and supplies matching Python and TypeScript implementations.
-
Metacat: a categorical framework for formal systems
Metacat is a new categorical model for formal systems using spans in cartesian PROPs to encode inference rules and symmetric monoidal categories for proofs, with a proof-checking implementation for FOL.