Premium
A Rational Analysis of Rule‐Based Concept Learning
Author(s) -
Goodman Noah D.,
Tenenbaum Joshua B.,
Feldman Jacob,
Griffiths Thomas L.
Publication year - 2008
Publication title -
cognitive science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.498
H-Index - 114
eISSN - 1551-6709
pISSN - 0364-0213
DOI - 10.1080/03640210701802071
Subject(s) - generalization , computer science , artificial intelligence , feature (linguistics) , inference , bayesian inference , set (abstract data type) , machine learning , space (punctuation) , probably approximately correct learning , natural (archaeology) , bayesian probability , natural language processing , algorithmic learning theory , active learning (machine learning) , mathematics , linguistics , programming language , operating system , mathematical analysis , philosophy , archaeology , history
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.