Compositional inductive biases in function learning
Name
Tenenbaum_Compositional inductive biases in function learning.pdf
Description
Submitted version
Size
798.6 KB
Format
Adobe PDF
Checksum (MD5)
d85b41ae9d64bbefeda4513108c7b000
Author(s)
Schulz, Eric
Tenenbaum, Joshua B
Duvenaud, David
Speekenbrink, Maarten
Gershman, Samuel J
Date Issued
2017
Journal
Cognitive Psychology
Publisher
Elsevier BV
Version
Original manuscript
Abstract
How do people recognize and learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is achieved 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, and compare this approach with other structure learning approaches. Participants consistently chose compositional (over non-compositional) extrapolations and interpolations of functions. Experiments designed to elicit priors over functional patterns revealed an inductive bias for compositional structure. Compositional functions were perceived as subjectively more predictable than non-compositional functions, and exhibited other signatures of predictability, such as enhanced memorability and reduced numerosity. Taken together, these results support the view that the human intuitive theory of functions is inherently compositional.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Center for Brains, Minds, and Machines
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/J.COGPSYCH.2017.11.002
