Dense feed-forward neural networks over floats can be presented as coherent categories G whose Set-models are the networks, with inference as precomposition along a coherent functor from a span category.
Baez and Mike Stay.Physics, Topology, Logic and Computation: A Rosetta Stone.In:New Structures for Physics
2 Pith papers cite this work, alongside 81 external citations. Polarity classification is still indexing.
2
Pith papers citing it
81
external citations · Crossref
verdicts
UNVERDICTED 2representative citing papers
Develops a Functorial QFT approach and applies it to analyze the O(N) model in AdS, focusing on crossed-channel diagram contributions to conformal block decomposition in the non-singlet sector.
citing papers explorer
-
Presenting Neural Networks via Coherent Functors
Dense feed-forward neural networks over floats can be presented as coherent categories G whose Set-models are the networks, with inference as precomposition along a coherent functor from a span category.
-
Strongly Coupled Quantum Field Theory in Anti-de Sitter Spacetime
Develops a Functorial QFT approach and applies it to analyze the O(N) model in AdS, focusing on crossed-channel diagram contributions to conformal block decomposition in the non-singlet sector.