用信息论解释人类分类行为，效果优于经典模型。
A Rational Account of Categorization Based on Information Theory
- 基于信息论构建理性分类理论，强调信息效率。
- 在多个经典实验中表现与最优模型相当甚至更优。
- 适合认知科学与机器学习交叉研究者阅读。
我们提出一种基于信息论理性分析的新型分类理论。为验证该理论，研究考察其对Hayes-Roth与Hayes-Roth（1977）、Medin与Schaffer（1978）、Smith与Minda（1998）等经典分类实验结果的解释能力。结果表明，该理论对人类分类行为的解释效果不亚于（或优于）独立线索模型和上下文模型（Medin & Schaffer, 1978）、理性分类模型（Anderson, 1991）以及层次狄利克雷过程模型（Griffiths et al., 2007）。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。