A Rational Account of Categorization Based on Information Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: MacLellan, Christopher J., Singaravadivelan, Karthik, Lian, Xin, Wang, Zekun, Langley, Pat
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914532094377984
author MacLellan, Christopher J.
Singaravadivelan, Karthik
Lian, Xin
Wang, Zekun
Langley, Pat
author_facet MacLellan, Christopher J.
Singaravadivelan, Karthik
Lian, Xin
Wang, Zekun
Langley, Pat
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2603_29895
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Rational Account of Categorization Based on Information Theory
MacLellan, Christopher J.
Singaravadivelan, Karthik
Lian, Xin
Wang, Zekun
Langley, Pat
Artificial Intelligence
Information Theory
Machine Learning
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).
title A Rational Account of Categorization Based on Information Theory
topic Artificial Intelligence
Information Theory
Machine Learning
url https://arxiv.org/abs/2603.29895