Tensor Species: The Theory and Practice of Neural Networks

Abstract: As category theory grows in popularity within the machine learning community, those of us interested in both theory and practice are faced with the question: which abstractions are directly useful when innovating in the design of neural networks? We explain why this is a hard problem, while making use of Joyal’s theory of species to give a down-to-earth description of the data types we see in contemporary neural networks, paying close attention to performance.

Computer sciencecategory theorylogic

Audience: learners

( video )

Topos Institute Colloquium