Radically Compositional Cognitive Concepts

TL;DR

This paper advocates for a radically compositional approach in computational neuroscience using applied category theory to enhance interpretability and model translation between narrative concepts and neural circuits.

Contribution

It introduces a novel framework leveraging category theory for compositional modeling in neuroscience, bridging narrative concepts and neural implementations.

Findings

Category theory provides a rigorous language for modeling.

Enhanced interpretability of complex neural systems.

Framework facilitates translation between concepts and neural circuits.

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.