计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (21): 51-54.DOI: 10.3778/j.issn.1002-8331.2010.21.014

• 研究、探讨 • 上一篇    下一篇

基于随机粗糙样本的结构风险最小化原则

张植明1,田景峰2   

  1. 1.河北大学 数学与计算机学院,河北 保定 071002
    2.华北电力大学 科技学院,河北 保定 071051
  • 收稿日期:2009-01-12 修回日期:2009-03-23 出版日期:2010-07-21 发布日期:2010-07-21
  • 通讯作者: 张植明

Structural risk minimization principle of random rough samples

ZHANG Zhi-ming 1,TIAN Jing-feng 2
  

  1. 1.College of Mathematics and Computer Sciences,Hebei University,Baoding,Hebei 071002,China
    2.Science and Technology College,North China Electric Power University,Baoding,Hebei 071051,China
  • Received:2009-01-12 Revised:2009-03-23 Online:2010-07-21 Published:2010-07-21
  • Contact: ZHANG Zhi-ming

摘要: 提出了退火熵,生长函数和VC维等概念,构建了基于VC维的学习过程一致收敛速度的界。然后以这些界为基础,给出基于随机粗糙样本的结构风险最小化原则。最后证明该原则是一致的并且推导出了关于渐近收敛速度的界。

关键词: 随机粗糙样本, 退火熵, 生长函数, VC维, 结构风险最小化原则, 渐进收敛速度的界

Abstract: Firstly,the concepts of annealed entropy,growth function and VC dimension are proposed and the bounds on the rate of uniform convergence of learning process based on VC dimension are constructed.Secondly,on the basis of these bounds,the idea of the structural risk minimization principle based on random rough samples is presented.Finally,the consistency of this principle is proven and the bound on the asymptotic rate of convergence is derived.

Key words: random rough samples, annealed entropy, growth function, VC dimension, structural risk minimization principle, the bound on the asymptotic rate of convergence

中图分类号: