Learning to Learn Functions

Michael Y. Li, Fred Callaway, William D. Thompson, Ryan P. Adams, Thomas L. Griffiths

Research output: Contribution to journalArticlepeer-review

Abstract

Humans can learn complex functional relationships between variables from small amounts of data. In doing so, they draw on prior expectations about the form of these relationships. In three experiments, we show that people learn to adjust these expectations through experience, learning about the likely forms of the functions they will encounter. Previous work has used Gaussian processes—a statistical framework that extends Bayesian nonparametric approaches to regression—to model human function learning. We build on this work, modeling the process of learning to learn functions as a form of hierarchical Bayesian inference about the Gaussian process hyperparameters.

Original languageEnglish (US)
Article numbere13262
JournalCognitive science
Volume47
Issue number4
DOIs
StatePublished - Apr 2023

All Science Journal Classification (ASJC) codes

  • Experimental and Cognitive Psychology
  • Artificial Intelligence
  • Cognitive Neuroscience

Keywords

  • Bayesian nonparametrics
  • Function learning
  • Gaussian process
  • Hierarchical Bayesian models
  • Learning-to-learn

Fingerprint

Dive into the research topics of 'Learning to Learn Functions'. Together they form a unique fingerprint.

Cite this