UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Compositional inductive biases in function learning.

Schulz, E; Tenenbaum, JB; Duvenaud, D; Speekenbrink, M; Gershman, SJ; (2017) Compositional inductive biases in function learning. Cognitive Psychology , 99 pp. 44-79. 10.1016/j.cogpsych.2017.11.002. Green open access

[thumbnail of Schulz2017Compositional.pdf]
Preview
Text
Schulz2017Compositional.pdf - Accepted Version

Download (896kB) | Preview

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.

Type: Article
Title: Compositional inductive biases in function learning.
Location: Netherlands
Open access status: An open access version is available from UCL Discovery
DOI: 10.1016/j.cogpsych.2017.11.002
Publisher version: https://doi.org/10.1016/j.cogpsych.2017.11.002
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Compositionality, Function learning, Gaussian process, Pattern recognition, Structure search
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Div of Psychology and Lang Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Div of Psychology and Lang Sciences > Experimental Psychology
URI: https://discovery.ucl.ac.uk/id/eprint/10038584
Downloads since deposit
148Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item