Rxivist logo

Rxivist combines preprints from bioRxiv with data from Twitter to help you find the papers being discussed in your field. Currently indexing 60,240 bioRxiv papers from 267,843 authors.

Compositional Inductive Biases in Function Learning

By Eric Schulz, Joshua B Tenenbaum, David Duvenaud, Maarten Speekenbrink, Samuel J Gershman

Posted 03 Dec 2016
bioRxiv DOI: 10.1101/091298 (published DOI: 10.1016/j.cogpsych.2017.11.002)

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.

Download data

  • Downloaded 936 times
  • Download rankings, all-time:
    • Site-wide: 7,567 out of 60,240
    • In animal behavior and cognition: 86 out of 946
  • Year to date:
    • Site-wide: 31,276 out of 60,240
  • Since beginning of last month:
    • Site-wide: 26,631 out of 60,240

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News