统计研究 ›› 2009, Vol. 26 ›› Issue (2): 58-61.

• 论文 • 上一篇    下一篇

算法建模发展解析

马景义 吴喜之   

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-02-15 发布日期:2009-02-15

The Study of Development of Algorithmic Modeling

  • Received:1900-01-01 Revised:1900-01-01 Online:2009-02-15 Published:2009-02-15

摘要: Breiman并没有算法建模的一个完整体系,而且其许多研究都以工作论文的形式出现,对于这些方法机理的解析度都不够。本文在研究Breiman自1978年至2002年的论文和著作的基础上,概括出算法建模思想形成中的两个重要内容:建模目的,组合算法。

关键词: 算法建模, 贝叶斯规则, 预测误差, 组合方法

Abstract: Breiman had not given a detailed frame of algorithmic modeling, and most of his results of research displayed in working papers, and didn’t minutely dissected correspondingly. After the study of papers and works of Breiman, published from 1978 to 2001, we summary two emphases in development of algorithmic modeling: the goal of modeling and ensemble methods.

 

Key words: Algorithmic modeling, Bayesian rules, Prediction error, Ensemble methods