The Relational Bottleneck as an Inductive Bias for Efficient Abstraction

no code implementations • 12 Sep 2023 • Taylor W. Webb, Steven M. Frankland, Awni Altabaa, Simon Segert, Kamesh Krishnamurthy, Declan Campbell, Jacob Russin, Tyler Giallanza, Zack Dulberg, Randall O'Reilly, John Lafferty, Jonathan D. Cohen

A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience.

Inductive Bias

Learning Representations that Support Extrapolation

1 code implementation • ICML 2020 • Taylor W. Webb, Zachary Dulberg, Steven M. Frankland, Alexander A. Petrov, Randall C. O'Reilly, Jonathan D. Cohen

Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence.