Category theory turns out to be useful in more and more areas.

(see e.g. MSE - Category Theory & Biology)

Question. Does anyeone know of some connection of category theory to (convolutional) neural networks (CNNs) / deep learning (or to machine learning in general, natural language processing (NLP), machine reasoning or to another topic counted as AI)?


Remark. I am aware that this question could also be posted at stack overflow or some other stack exchange site. However my idea is that it could be better to ask it on the mathematics site, since it might rather be mathematicians that have some knowledge about such connections than e.g. computer scientists themselves.


Solution 1:

Additionally to Spivaks paper (see above)

Fong Spivak Tuyeras.Backprop as Functor: A compositional perspective on supervised learning

I came along these papers (couldn't read them yet)

Healy.Category Theory Applied to Neural Modeling and Graphical Representations

Gomez + Sanz.Modeling cognitive systems with Category Theory

Healy + Caudell.Neural Networks, Knowledge and Cognition: A Mathematical Semantic Model Based upon Category Theory