Learning How to Generalize

Joseph L. Austerweil, Sophia Sanborn, Thomas L. Griffiths

Research output: Contribution to journalArticle

Abstract

Generalization is a fundamental problem solved by every cognitive system in essentially every domain. Although it is known that how people generalize varies in complex ways depending on the context or domain, it is an open question how people learn the appropriate way to generalize for a new context. To understand this capability, we cast the problem of learning how to generalize as a problem of learning the appropriate hypothesis space for generalization. We propose a normative mathematical framework for learning how to generalize by learning inductive biases for which properties are relevant for generalization in a domain from the statistical structure of features and concepts observed in that domain. More formally, the framework predicts that an ideal learner should learn to generalize by either taking the weighted average of the results of generalizing according to each hypothesis space, with weights given by how well each hypothesis space fits the previously observed concepts, or by using the most likely hypothesis space. We compare the predictions of this framework to human generalization behavior with three experiments in one perceptual (rectangles) and two conceptual (animals and numbers) domains. Across all three studies we find support for the framework's predictions, including individual-level support for averaging in the third study.

Original languageEnglish (US)
Article numbere12777
JournalCognitive Science
Volume43
Issue number8
DOIs
StatePublished - Jan 1 2019

All Science Journal Classification (ASJC) codes

  • Experimental and Cognitive Psychology
  • Cognitive Neuroscience
  • Artificial Intelligence

Keywords

  • Bayesian modeling
  • Category learning
  • Generalization
  • Inductive inference

Fingerprint Dive into the research topics of 'Learning How to Generalize'. Together they form a unique fingerprint.

  • Cite this