[1]杨静宇,魏兴国,孙怀江.一种快速SVM学习算法[J].南京理工大学学报(自然科学版),2003,(05):530-535.
 YangJingyu WeiXingguo SunHuaijiang.A Fast SVM Learning Algorithm[J].Journal of Nanjing University of Science and Technology,2003,(05):530-535.
点击复制

一种快速SVM学习算法()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2003年05期
页码:
530-535
栏目:
出版日期:
2003-10-30

文章信息/Info

Title:
A Fast SVM Learning Algorithm
作者:
杨静宇魏兴国孙怀江
南京理工大学计算机科学与技术系, 南京210094
Author(s):
YangJingyu WeiXingguo SunHuaijiang
Department of Computer Science and Technology,NUST,Nanjing 210094
关键词:
模式识别 机器学习 支持向量机 学习算法
Keywords:
pattern recognition machine learning support vector machine learning algorithm
分类号:
TP18
摘要:
介绍了支持向量机用于解决模式分类问题的基本原理和学习算法 ,在对SMO算法进行深入分析的基础上 ,提出了一种改进的分解算法GD ,较好地解决了训练过程中子问题的求解复杂度和迭代次数及效率之间的矛盾。实验表明 ,该算法能够大大缩短非线性核支持向量机的训练时间。
Abstract:
Support vector machine( SVM) and its learning algorithm for pattern classif icat ion are presented. Based on the analysis and comparison of the ex ist ing SVM t raining algorithms, especially SMO, a revised decomposit ion algorithm named GD is proposed. It balances w ell betw een the scale of the subquadratic programming problem and the efficiency and t imes of iteration. Experimental results show that it can substant ially reduce the t raining t ime of SVM w ith nonlinear kernels.

参考文献/References:

1 张学工. 关于统计学习理论与支持向量机[ J] . 自动化学报, 2000, 26( 1) : 32~ 42.
2 肖嵘, 王继成, 张福炎. 支持向量机理论综述[ J] . 计算机科学, 2000, 27( 3) : 1~ 3.
3 Perez-Cruz F, Navia-Vazquez A, Figueir as-Vidal A R, et al. Empir ical risk minimization for support vector classifiers[ J] . IEEE Transactions on Neural Netw orks, 2003, 14( 2) : 296~ 303.
4 Suykens J A K, van Gestel T, Vandewalle J, et al. A support vector machine formulation to PCA analysis and its kernel version[ J] . IEEE Transactions on Neural Networks, 2003, 14( 2) : 447~ 450.
5 魏兴国. 基于核方法的手写体数字识别研究[ D] . 南京: 南京理工大学计算机科学与技术系, 2003.
6 Cortes C, Vapnik V. Support vector networks[ J] . Machine Learning, 1995, 20( 2) : 273~ 297.
7 Platt J C. Fast training of SVM using sequential minimal optimization[ A] . Scholkopf B, Burges C J C, Smola A J. Advances in Kernel Methods ) Suppor t Vector Learning [ C] . Cambridge,MA: M IT Press, 1998. 185~ 208.
8 袁亚湘. 非线性规划数值方法[M] . 上海: 上海科学技术出版社, 1993.
9 Cr istianini N. Dynamically adapting kernels in suppor t v ector machines[ R] . London: Royal Holloway College, 1998.

相似文献/References:

[1]许前,郑称德,韩之俊.MTS多类判别研究[J].南京理工大学学报(自然科学版),2002,(01):92.
 XuQian ZhengChengde HanZhijun.Study of Mahalanobis-Taguchi System in Multiple Recognition[J].Journal of Nanjing University of Science and Technology,2002,(05):92.
[2]谭东宁,谭东汉.小样本机器学习理论:统计学习理论[J].南京理工大学学报(自然科学版),2001,(01):108.
 TanDongnin TanDonghan.Small-sample Machine Learning Theory: Statistical Learning Theory[J].Journal of Nanjing University of Science and Technology,2001,(05):108.
[3]赵海涛,金忠.一种改进的最佳鉴别平面[J].南京理工大学学报(自然科学版),2000,(01):88.
 ZhaoHaitao JinZhong.An Improved Optimal Discriminant Plane[J].Journal of Nanjing University of Science and Technology,2000,(05):88.
[4]杨静宇,金忠,郭跃飞.人脸图像有效鉴别特征抽取与识别[J].南京理工大学学报(自然科学版),2000,(03):193.
 YangJingyu JinZhong GuoYuefei.Efficient Discriminant Feature Extraction and Recognition of Face Images[J].Journal of Nanjing University of Science and Technology,2000,(05):193.
[5]荆晓远,金忠,杨静宇.基于子类划分的分类器设计方法[J].南京理工大学学报(自然科学版),1999,(04):293.
 JingXiaoyuan JinXiaoyuan JinZhong YangJingyu.A Classifier Design Method Based on Sub class Division[J].Journal of Nanjing University of Science and Technology,1999,(05):293.
[6]黄修武,杨静宇,郭跃飞,等.一种新颖的分组决策方法及其应用[J].南京理工大学学报(自然科学版),1999,(06):481.
 HuangXiuwu YangJingyu GuoYuefei JingXiaoyuan.A Novel Method of Grouped Decision and Its Application[J].Journal of Nanjing University of Science and Technology,1999,(05):481.
[7]孙宇,张世琪.用于FMS的工件识别技术及装置的研究[J].南京理工大学学报(自然科学版),1992,(05):26.
[8]王 文,王树锋,李洪华.基于文本语义和表情倾向的微博情感分析方法[J].南京理工大学学报(自然科学版),2014,38(06):733.
 Wang Wen,Wang Shufeng,Li Honghua.Microblogging sentiment analysis method based on text semantics and expression tendentiousness[J].Journal of Nanjing University of Science and Technology,2014,38(05):733.
[9]林 棋,张 宏,李千目.一种基于MA-LSSVM的封装式特征选择算法[J].南京理工大学学报(自然科学版),2016,40(01):10.
 Lin Qi,Zhang Hong,Li Qianmu.Wrapper feature selection algorithm based on MA-LSSVM[J].Journal of Nanjing University of Science and Technology,2016,40(05):10.
[10]於东军,李 阳.蛋白质残基接触图预测[J].南京理工大学学报(自然科学版),2019,43(01):1.[doi:10.14177/j.cnki.32-1397n.2019.43.01.001]
 Yu Dongjun,Li Yang.Protein residue-residue contact map prediction[J].Journal of Nanjing University of Science and Technology,2019,43(05):1.[doi:10.14177/j.cnki.32-1397n.2019.43.01.001]

备注/Memo

备注/Memo:
杨静宇( 1941— ) , 男, 1961 年9 月就读炮兵工程学院, 教授, 博士生导师。主要研究方向: 模式识别,人工智能。E-mail: yangjy@public1. ptt. js. cn
更新日期/Last Update: 2013-03-17