NIPS Proceedingsβ

Probing the Compositionality of Intuitive Functions

Part of: Advances in Neural Information Processing Systems 29 (NIPS 2016)

[PDF] [BibTeX] [Reviews]

Authors

Conference Event Type: Poster

Abstract

How do people learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is accomplished by harnessing compositionality: complex structure is decomposed into simpler building blocks. We formalize this idea within the framework of Bayesian regression using a grammar over Gaussian process kernels. We show that participants prefer compositional over non-compositional function extrapolations, that samples from the human prior over functions are best described by a compositional model, and that people perceive compositional functions as more predictable than their non-compositional but otherwise similar counterparts. We argue that the compositional nature of intuitive functions is consistent with broad principles of human cognition.