首页 | 本学科首页   官方微博 | 高级检索  
     

基于模糊随机样本的结构风险最小化原则
引用本文:何其慧,姚登宝,王翠翠,毛军军.基于模糊随机样本的结构风险最小化原则[J].计算机工程与应用,2011,47(34):51-55.
作者姓名:何其慧  姚登宝  王翠翠  毛军军
作者单位:1.安徽经济管理学院,合肥 2300592.安徽大学 数学科学学院,合肥 2300393.安徽大学 计算智能与信号处理教育部重点实验室,合肥 230039
基金项目:国家自然科学基金(No.61073117); 安徽大学学术创新团队资助(No.KJTD001B);安徽大学人才队伍建设经费; 安徽省高等学校青年基金项目(No.2011SQRL186); 高等学校优秀青年人才基金~~
摘    要:基于模糊随机样本,提出了熵、退火熵、生长函数和VC维等概念,并在此基础上构建了基于VC维的学习过程一致收敛速度的界;给出了基于模糊随机样本的结构风险最小化原则(FSSRM原则),证明了基于FSSRM原则下收敛速度渐进分析的相关性质。

关 键 词:模糊随机样本  VC维  结构风险最小化原则  渐进分析  
修稿时间: 

Structural risk minimization principle based on fuzzy-stochastic samples
HE Qihui,YAO Dengbao,WANG Cuicui,MAO Junjun.Structural risk minimization principle based on fuzzy-stochastic samples[J].Computer Engineering and Applications,2011,47(34):51-55.
Authors:HE Qihui  YAO Dengbao  WANG Cuicui  MAO Junjun
Affiliation:1.Anhui Institute of Economic Management,Hefei 230059,China2.College of Mathematical Sciences,Anhui University,Hefei 230039,China3.Key Lab of Intelligent Computing & Signal Processing of MOE,Institute of Artificial Intelligence,Anhui University,Hefei 230039,China
Abstract:The concepts of entropy,annealed entropy,growth function and VC dimension are proposed based on fuzzystochastic samples,and on the basis of these,the bounds on the rate of uniform convergence of learning process based on VC dimension are constructed.At same time,the idea of the structural risk minimization principle based fuzzy-stochastic samples has been presented,relative properties of asymptotic analysis about convergent rate based on FSSRM principle have been also proved.
Keywords:fuzzy-stochastic samples  VC dimension  the structural risk minimization principle  asymptotic analysis  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
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