首页 | 官方网站   微博 | 高级检索  
     


A Simple Method for Generating Additive Clustering Models with Limited Complexity
Authors:Lee  Michael D
Affiliation:(1) Department of Psychology, University of Adelaide, SA, 5005, Australia
Abstract:Additive clustering was originally developed within cognitive psychology to enable the development of featural models of human mental representation. The representational flexibility of additive clustering, however, suggests its more general application to modeling complicated relationships between objects in non-psychological domains of interest. This paper describes, demonstrates, and evaluates a simple method for learning additive clustering models, based on the combinatorial optimization approach known as Population-Based Incremental Learning. The performance of this new method is shown to be comparable with previously developed methods over a set of lsquobenchmarkrsquo data sets. In addition, the method developed here has the potential, by using a Bayesian analysis of model complexity that relies on an estimate of data precision, to determine the appropriate number of clusters to include in a model.
Keywords:additive clustering  population-based incremental learning  PBIL  Bayesian information criterion  BIC  cognitive modeling
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号