A Rational Account of Categorization Based on Information Theory

2026-02-07

AI Summary

This study investigates the cognitive mechanisms underlying human categorization from a rational perspective and proposes a novel information-theoretic theory of categorization. Integrating rational analysis with computational cognitive modeling, the approach explains decision patterns by minimizing information loss during the categorization process. The model successfully reproduces and provides principled accounts for classic experimental findings by Hayes-Roth, Medin and Schaffer, and Smith and Minda. It demonstrates explanatory power and predictive accuracy comparable to, and in some cases surpassing, those of prevailing models, thereby offering a more principled theoretical foundation for understanding human categorization behavior.

Abstract

We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how well it can account for key findings from classic categorization experiments conducted by Hayes-Roth and Hayes-Roth (1977), Medin and Schaffer (1978), and Smith and Minda (1998). We find that it explains the human categorization behavior at least as well (or better) than the independent cue and context models (Medin&Schaffer, 1978), the rational model of categorization (Anderson, 1991), and a hierarchical Dirichlet process model (Griffiths et al., 2007).

Problem

• categorization
• information theory
• rational analysis
• human behavior
• cognitive modeling

Innovation

• information theory
• rational analysis
• categorization
• computational modeling
• human behavior