most citedRelational Constraints On Neural Networks Reproduce Human Biases towards Abstract Geometric Regularity

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks

Declan Campbell, Jonathan D. Cohen

The human cognitive system exhibits remarkable flexibility and generalization capabilities, partly due to its ability to form low-dimensional, compositional representations of the…