2008/01/01 by Noah D. Goodman, Joshua B. Tenenbaum, Jacob Feldman +1 · 1 citation
Psychology · Computer Science · Social Sciences · Mathematics · #Child and Animal Learning Development #Bayesian Modeling and Causal Inference #Language and cultural evolution #Generalization #Artificial intelligence #Computer science #Feature (linguistics) #Bayesian inference #Inference #Set (abstract data type) #Machine learning #Probably approximately correct learning #Space (punctuation) #Natural (archaeology) #Bayesian probability #Natural language processing #Algorithmic learning theory #Mathematics #Active learning (machine learning) #Linguistics
paper · pdf · doi:10.1080/03640210701802071
openalex publication_date 2008/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
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.