A Rational Account of Categorization Based on Information Theory
Proceedings of the 48th Annual Conference of the Cognitive Science Society
2026
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 as well as (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).
Topics:Concept Learning
Projects:Cobweb
BibTeX
@inproceedings{maclellan-cogsci-2026,
title = {A Rational Account of Categorization Based on Information Theory},
author = {MacLellan, Christopher J. and Singaravadivelan, Karthik and Lian, Xin and Wang, Zekun and Langley, Pat},
booktitle = {Proceedings of the 48th Annual Conference of the Cognitive Science Society},
year = {2026},
}