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.
The (2,1)-category of small coherent categories, April 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.CT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.