Radically Compositional Cognitive Concepts
Neurons and Cognition
2019-11-18 v1 Artificial Intelligence
Computation and Language
Neural and Evolutionary Computing
Abstract
Despite ample evidence that our concepts, our cognitive architecture, and mathematics itself are all deeply compositional, few models take advantage of this structure. We therefore propose a radically compositional approach to computational neuroscience, drawing on the methods of applied category theory. We describe how these tools grant us a means to overcome complexity and improve interpretability, and supply a rigorous common language for scientific modelling, analogous to the type theories of computer science. As a case study, we sketch how to translate from compositional narrative concepts to neural circuits and back again.
Cite
@article{arxiv.1911.06602,
title = {Radically Compositional Cognitive Concepts},
author = {Toby B. St Clere Smithe},
journal= {arXiv preprint arXiv:1911.06602},
year = {2019}
}
Comments
6 pages, 2 figures; NeurIPS 2019 Context and Compositionality workshop. Work in progress