首页 | 本学科首页   官方微博 | 高级检索  
     检索      

用牛顿-条件预优共轭梯度法求解光滑支持向量机的可能性研究
引用本文:熊金志,胡金莲,王斌.用牛顿-条件预优共轭梯度法求解光滑支持向量机的可能性研究[J].东莞理工学院学报,2007,14(3):38-42.
作者姓名:熊金志  胡金莲  王斌
作者单位:1. 东莞理工学院,软件学院,广东东莞,523808
2. 东莞理工学院,电子工程系,广东东莞,523808
摘    要:光滑支持向量机是目前的一个研究热点.牛顿-条件预优共轭梯度法Newton-PCG(Newtonpreconditioncd congugate gradient)是一种求解优化问题的更有效算法.列出了该算法用于求解光滑支持向量机的基本思想和基本步骤,还比较了原始牛顿法和牛顿-条件预优共轭梯度法的计算效率.结果表明,牛顿-条件预优共轭梯度法的计算效率明显高于原始牛顿法.

关 键 词:分类  支持向量机  Newton算法  Newton-PCG算法  光滑
文章编号:1009-0312(2007)03-0038-05
收稿时间:2006-10-09
修稿时间:2006-10-09

On Probability of Newton-Preconditioned Conjugate Gradient for Solving Smooth Support Vector Machines
XIONG Jin-zhi,HU Jin-lian,WANG Bin.On Probability of Newton-Preconditioned Conjugate Gradient for Solving Smooth Support Vector Machines[J].Journal of Dongguan Institute of Technology,2007,14(3):38-42.
Authors:XIONG Jin-zhi  HU Jin-lian  WANG Bin
Institution:1.Software College, Dongguan University of Technology, Dongguan 523808, China; 2.Department of Electronic Engineering, Dongguan University of Technology, Dongguan 523808, China
Abstract:Smooth support vector machine(SSVM)is an active field in SVM research.This paper presents the solutions to the problems of SSVM with a new optimization technique,the Newton-PCG(Newton-preconditioned conjugate gradient)algorithm.By comparison with their computational efficiencies,it is showed that the Newton-PCG algorithm is obviously more efficient than Newton algorithm,which is an important direction for future research on smooth SVMs.
Keywords:classification  support vector machine  Newton algorithm  Newton-PCG algorithm  smoothing
本文献已被 CNKI 维普 万方数据 等数据库收录!
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