Structural risk minimization principle of random rough samples

doi:10.3778/j.issn.1002-8331.2010.21.014

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (21): 51-54.DOI: 10.3778/j.issn.1002-8331.2010.21.014

• 研究、探讨 • Previous Articles Next Articles

Structural risk minimization principle of random rough samples

ZHANG Zhi-ming¹，TIAN Jing-feng²

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

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.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

通讯作者: 张植明

Abstract

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

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

CLC Number:

TP181

ZHANG Zhi-ming¹，TIAN Jing-feng²
. Structural risk minimization principle of random rough samples[J]. Computer Engineering and Applications, 2010, 46(21): 51-54.

张植明¹，田景峰². 基于随机粗糙样本的结构风险最小化原则[J]. 计算机工程与应用, 2010, 46(21): 51-54.

[1]	YAO Chengkuan1, XU Jianhua2. Parameter optimization of L2-SVM with two regularization parameters [J]. Computer Engineering and Applications, 2014, 50(8): 99-102.
[2]	HE Qihui1，YAO Dengbao2，WANG Cuicui2，MAO Junjun2，3. Structural risk minimization principle based on fuzzy-stochastic samples [J]. Computer Engineering and Applications, 2011, 47(34): 51-55.
[3]	HE Yuan-tao，DENG Wei. Improvement on preprocessing algorithm of support vector machines for unbalance data set [J]. Computer Engineering and Applications, 2010, 46(10): 36-37.
[4]	ZHANG Zhi-ming. Structural risk minimization principle of birandom samples [J]. Computer Engineering and Applications, 2009, 45(1): 51-55.
[5]	ZHANG Zhi-ming. Some studies of statistical learning theory based on random rough samples [J]. Computer Engineering and Applications, 2008, 44(31): 43-46.

Structural risk minimization principle of random rough samples

基于随机粗糙样本的结构风险最小化原则

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 5

Recommended Articles

Metrics