Learning iteratively a classifier with the Bayesian Model Averaging Principle

详细信息	查看全文 | 推荐本文 |

• 作者：Rudy Sicard ; Thierry Artiè ; res ; Eric Petit
• 关键词：Bayesian model averaging ; Point estimate approximation ; Naı ; ¨ ; ve Bayes classifier ; Statistical classification
• 刊名：Pattern Recognition
• 出版年：2008
• 期刊代码：100_00313203
• 类别：cp
• 出版时间：March 2008
• 卷：41
• 期：3
• 页码：930-938
• 文件大小：295 K

摘要

We present a learning algorithm for nominal vector data. It builds a complex classifier by adding iteratively a simple function that modifies the current classifier. In order to limit overtraining problem we focus on a class of such functions for which optimal Bayesian learning is tractable. We investigate a few classes of functions that yield to models that are similar to Naı¨ve Bayes and logistic classification. We report experimental results for a collection of standard data sets that show that our learning algorithm outperforms standard learning of such these standard models.