Probing the compositionality of intuitive functions

TitleProbing the compositionality of intuitive functions
Publication TypeCBMM Memos
Year of Publication2016
AuthorsSchulz, E, Tenenbaum, JB, Duvenaud, D, Speekenbrink, M, Gershman, SJ
Date Published05/2016

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.


Download:  PDF icon CBMM-Memo-048.pdf
CBMM Memo No:  048

Research Area: 

CBMM Relationship: 

  • CBMM Related