A rational analysis of rule-based concept learning

Noah A. Goodman, Joshua B. Tenenbaum, Jacob Feldman, Thomas L. Griffiths

Research output: Contribution to journalArticle

129 Scopus citations

Abstract

This article proposes a new model of human concept learning that provides a rational analysis of learning feature-based concepts. This model is built upon Bayesian inference for a grammatically structured hypothesis space - a concept language of logical rules. This article compares the model predictions to human generalization judgments in several well-known category learning experiments, and finds good agreement for both average and individual participant generalizations. This article further investigates judgments for a broad set of 7-feature concepts - a more natural setting in several ways - and again finds that the model explains human performance.

Original languageEnglish (US)
Pages (from-to)108-154
Number of pages47
JournalCognitive science
Volume32
Issue number1
DOIs
StatePublished - Jan 2008

All Science Journal Classification (ASJC) codes

  • Experimental and Cognitive Psychology
  • Cognitive Neuroscience
  • Artificial Intelligence

Keywords

  • Bayesian induction
  • Categorization
  • Concept learning
  • Language of thought
  • Probabilistic grammar
  • Rules

Fingerprint Dive into the research topics of 'A rational analysis of rule-based concept learning'. Together they form a unique fingerprint.

Cite this