DeepAI AI Chat
Log In Sign Up

Radically Compositional Cognitive Concepts

by   Toby B. St Clere Smithe, et al.
University of Oxford

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.


page 1

page 2

page 3

page 4


Compositional Inverses of AGW-PPs

In this paper, we present two methods to obtain the compositional invers...

Categories of Semantic Concepts

Modelling concept representation is a foundational problem in the study ...

Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience

Jackendoff (2002) posed four challenges that linguistic combinatoriality...

On the Horizon: Interactive and Compositional Deepfakes

Over a five-year period, computing methods for generating high-fidelity,...

A Statistical Analysis of Compositional Surveys

A common statistical problem is inference from positive-valued multivari...

Flexible Compositional Learning of Structured Visual Concepts

Humans are highly efficient learners, with the ability to grasp the mean...

A Compositional Framework for Scientific Model Augmentation

Scientists construct and analyze computational models to understand the ...