期刊文献+

一种快速的SVM最优核参数选择方法 被引量:4

Fast algorithm for SVM kernel parameter selection
下载PDF
导出
摘要 支持向量机是一种基于核的学习方法,核函数及核参数的选择直接影响到SVM的泛化能力。传统的参数选择方法如网格搜索法,由于其计算量大,训练过程十分耗时,提出了一种新的快速选择最优核参数方法,该方法通过计算各类别在特征空间的可分性度量值来决定最优核参数,不需训练相应SVM分类模型,从而大大缩减了训练时间,提高了训练速度,且分类精度与传统方法相比,具有相当的竞争力。实验证明,该算法是可行有效的。 Support Vector Machine(SVM) is a kernel-based method,kernel function and kernel parameter selection directly affect SVM model’s generalization ability.A popular kernel parameter selection method is the grid search method.Large computation quantity of this method makes the training process time-consuming.This paper proposes the new method which using the Separability Measure(SM) between classes in the feature space to choose the kernel parameter.Calculating such SM costs much less computation time than training the corresponding SVM models,thus the best kernel parameter can be chosen much faster,and the testing accuracy of trained SVM by the proposed method is competitive to the standard ones.Experiment results show that the proposed method is feasible and effective.
出处 《计算机工程与应用》 CSCD 北大核心 2010年第15期165-168,共4页 Computer Engineering and Applications
关键词 支持向量机(SVM) 核参数选择 特征空间 可分性度量 Support Vector Machine(SVM) kernel parameter selection feature space Separability Measure(SM)
  • 相关文献

参考文献5

  • 1张小云,刘允才.高斯核支撑向量机的性能分析[J].计算机工程,2003,29(8):22-25. 被引量:45
  • 2Takahashi F,Abe S.Optimizing directed acyclic graph support vector machines[C]//Atificial Neural Networks in Pattern Recognition (ANNPR 2003 ), 2003 : 166-170.
  • 3Phetkaew T,Kijsirikul B,Rivepiboon W.Reordering adaptive directed acyclic graphs:An improved algorithm for muhiclass support vector machines[C]//Proc Interna Joint Conf on Neural Networks(IJCNN 2003 ), 2003 : 1605-1610.
  • 4Wu Kuo-Ping,Wang Sheng-De.Choosing the Kernel parameters for Support Vector Machines by the inter-cluster distance in the feature space[EB/OL].http ://www.sciencedirect.com.
  • 5张 莉,周伟达,焦李成.一类新的支撑矢量机核[J].软件学报,2002,13(4):713-718. 被引量:13

二级参考文献10

  • 1[1]Vapnik V.An Overview of Statistical Learning Theory.IEEE Trans. Neural Networks,1999,10(5):988-999
  • 2[2]Pontil M,Verri A.Support Vector Machines for 3D Object Recognition. IEEE Tran. Pattern Analysis and Machine Intelligence,1998,20(6):637
  • 3[3]Burges C J C.A Tutorial on Support Vector Machines for Pattern Recognition.Data Mining and Knowledge Discovery,1998,2:121-167
  • 4[4]Platt J C.Sequential Minimal Optimization:A Fast Algorithm for Training Support Vector Machines.Microsoft Research Tech. Report MSR-TR-98-14,1998-04-21
  • 5吴佑寿,赵明生,丁晓青.一种激励函数可调的新人工神经网络及应用[J].中国科学(E辑),1997,27(1):55-60. 被引量:26
  • 6Vapnik,V.The Nature of Statistical Learning Theory.New York: Springer-Verlag,1995.
  • 7Cortes,C.,Vapnik,V.Support vector networks.Machine Learning,1995,20:273~297.
  • 8Burges,C.J.C.Geometry and invariance in kernel based methods.In: Sch?lkopf,B.,Burges,C.J.C.,Smola,J.,eds.Advance in Kernel Methods--Support Vector Learning.Cambridge,MA: MIT Press,1999.89~116.
  • 9K?nig,H.Eigenvalue Distribution of Compact Operator.Basel: Birkh?user,1986.
  • 10Wu,You-shou,Zhao,Ming-sheng,Ding,Xiao-qing.A new kind of ANN based on active function and its application.Science in China (Series E),1997,27(1):55~60 (in Chinese).

共引文献56

同被引文献37

  • 1刘涛,吴功宜,陈正.一种高效的用于文本聚类的无监督特征选择算法[J].计算机研究与发展,2005,42(3):381-386. 被引量:37
  • 2张翔,肖小玲,徐光祐.一种确定高斯核模型参数的新方法[J].计算机工程,2007,33(12):52-53. 被引量:12
  • 3谭松波,王月粉.中文文本分类语料库-TanCorpv1.0[EB/OL].(2007-08-29)[2008-01-20].http://www.searehforum:org.cn/tansongbo/corpus.htm.
  • 4Hu Mingqing,Chen Yiqiang,Kwok J T Y.Building sparse multiplekemel SVM classifiers[J].IEEE Transactions on Neural Networks, 2009,20(5) : 827-839.
  • 5Chapelle O, Vapnik V.Choosing multiple parameters for support vector machines[J].Machine Learning, 2002,46( 1 ) : 131-159.
  • 6Ratsch G, Onoda R G, Muller T K.Soft margins for AdaBoost[J]. Machine Learning,2001,42(3) :287-320.
  • 7Zhang Daoqiang,Chen Songcan,Zhou Zhihua.Learning the kernel parameters in kernel minimum distance classifier[J].Pattern Recognition, 2006,39( 1 ) :133-135.
  • 8Vapnik V N.The nature of statistical learning theory[M].New York: Springer, 1996.
  • 9SHI Y, EBERHART R C. A Modified Particle Swarm Optimizer[ C ]//Proceedings of IEEE International Con- ference on Evolutionary Computation, 1998:69-73.
  • 10Blei D M,Ng A Y,Jordan M I.Latent Dirichlet allocation[J].The Journal of Machine Learning Research,2003(3):993-1022.

引证文献4

二级引证文献24

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部