The Relational Bottleneck as an Inductive Bias for Efficient Abstraction

09/12/2023
by   Taylor W. Webb, et al.
0

A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This effort has often been framed in terms of a dichotomy between empiricist and nativist approaches, most recently embodied by debates concerning deep neural networks and symbolic cognitive models. Here, we highlight a recently emerging line of work that suggests a novel reconciliation of these approaches, by exploiting an inductive bias that we term the relational bottleneck. We review a family of models that employ this approach to induce abstractions in a data-efficient manner, emphasizing their potential as candidate models for the acquisition of abstract concepts in the human mind and brain.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset