期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于支持向量机的大样本回归算法比较研究 被引量：3

Comparison of Algorithms for Large Regression Problems Based on Support Vector Machine
在线阅读 下载PDF
导出
摘要 支持向量机的研究是当前人工智能领域的研究热点。基于支持向量机的大样本回归问题一直是一个非常具有挑战性的课题。最近,基于递归最小二乘算法,Engel等人提出了核递归最小二乘算法。文中基于块增量学习和逆学习过程,提出了自适应迭代回归算法。为了说明两种方法的性能,论文在训练速度、精度和支持向量数量等方面,对它们做了比较。模拟结果表明:核递归最小二乘算法所得到的支持向量个数比自适应迭代回归算法少,而训练时间比自适应迭代回归算法的训练时间长,训练和测试精度也比自适应迭代回归算法差。 At present,studies for support vector machines are hot topics in the field of artificial intelligence.It is a very challenging work to deal with large regression problems based on support vector machines.Recently,Engel proposed kernel recursive least square algorithm（KRIS） based on recursive least square.This paper presents an adaptive and iterarive support vector machine regression algorithm（CAISVR） based on chunking incremental learning and decremental learning procedures.In order to show their performances,comparison is given focusing on training speeds,training accuracy,generalization performances and the number of support vectors.The simulating results show that although the number of support vectors obtained by KRIS is smaller than that obtained by CAISVM,the training time of KRIS is longer than that of CAISVR,the training and testing accuracies of KRIS are lower than those of CAISVM too.
作者 杨晓伟 骆世广 余舒 吴春国 梁艳春
机构地区 华南理工大学数学科学学院 华南理工大学计算机科学与工程学院 吉林大学计算机科学与技术学院
出处 《计算机工程与应用》 CSCD 北大核心 2006年第6期36-38,57,共4页 Computer Engineering and Applications
基金 国家自然科学基金资助项目(编号:10471045) 广东省自然科学基金(编号:031360 04020079) 华南理工大学高水平大学建设苗子项目(编号:D76010)
关键词 支持向量机 自适应迭代回归算法 核递归最小二乘算法 大样本回归 support vector machines,adaptive and iterative regression algorithm,Kernel recursive least square algorithm, large regression
分类号 TP181 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献10

  • 1Osuna E,Freund R,Girosi F.An improved training algorithm for support vector machines[C].In:IEEE Workshop on Neural Networks and Signal Processing,New York:IEEE Press,1997:276～285
  • 2Joachims T.Making large-scale support vector machine learning practical[C].In:Advances in Kernel Methods-Support Vector Learning,Cambridge:MIT Press,1998:169～ 184
  • 3Platt J C.Sequential minimal optimization-a fast algorithm for training support vector machines[C].In:Advances in Kernel Methods-Support Vector Learning,Cambridge:MIT Press,1998:185～208
  • 4Keerthi S S,Shevade S K,Bhattacharyya C et al.Improvements to Platt's SMO Algorithm for SVM Classifier Design[J].Neural Computation,2001;13(3):637～649
  • 5孙剑,郑南宁,张志华.一种训练支撑向量机的改进贯序最小优化算法[J].软件学报,2002,13(10):2007-2013. 被引量：25
  • 6李建民,张钹,林福宗.序贯最小优化的改进算法[J].软件学报,2003,14(5):918-924. 被引量：30
  • 7Suykens J A K,Vandewalle J.Least Squares Support Vector Machine Classifiers[J].Neural Process Letter,1999;9:293～300
  • 8Chua K S.Efficient computations for large least square support vector machine classifiers[J].Pattern Recognition Letters,2004;24:75～80
  • 9Suykens J A K,Lukas L,Vandewalle J.Sparse Approximation Using Least Squares Support Vector Machines[C].In:IEEE International Symposium on Circuits and Systems,Switzerland:Presses Polytechniques Et Universitaires Romandes,2000:757～760
  • 10Engel Y,Mannor S,Meir R.The Kernel Recursive Least-Squares Algorithm[J].IEEE Transactions on Signal Processing,2004;52(8):2275～2285

二级参考文献19

  • 1Burges C.Atutorial on suovort vector machines for pattern recognition.Data Mining and Knowledge Discovery,1998,2(2):1-43.
  • 2Collobert R,Bengio S.SVMTorch:A support vector machine for large-scale regression and classification problems.Journal of Machine Learning Research,2001,1:143-160.
  • 3Platt J.Fast training of support vector machines using sequential minimal optimization.In:Schoelkopf B,Burges C,Smola A,eds.Advances in Kernel Methods-Suppog Vector Learning.Cambridge,MA:MIT Press,1999.185～208.
  • 4Joaehims T.Making large-scale support vector machine learning practical.In:Schoelkopf B,Burges C,Smola A,eds.Advances in Kernel Methods- Support Vector Learning.Cambridge,MA:MIT Press,1999.169～184.
  • 5Platt J.Using analytic QP and sparseness to speed training of support vector machines.In:Kearns M,Solla S,Cohn D,eds. Advances in Neural Information Processing Systems 11.Cambridge,MA:MIT Press,1999.557～563.
  • 6Flake G,Lawrence S.Efficient SVM regression training with SMO.Machine Learning,2002,46(1／3):271～290.
  • 7Keerthi S,Shevade S,Bhattcharyya C,Murthy K.Improvements to Platt’s SMO algorithm for SVM classifier design.Neural Computation,2001,13(3):637-649.
  • 8Keerthi S,Gilbert E.Convergence of a generalized SMO algorithm for SVM classifier design.Machine Learning,2002,46(1／3):351-360.
  • 9Lin CJ.On the convergence of the decomposition method for support vector machines.IEEE Transactions on Neural Networks,2001,12(6):1288-1298.
  • 10Bian, Zhao-qi, Zhang, Xue-gong. Pattern Recognition. 2nd ed., Beijing: Tsi nghua University Press, 1999 (in Chinese).边兆祺,张学工.模式识别.第2版,北京:清华大学出版社,1999.

共引文献39

同被引文献42

引证文献3

二级引证文献19

计算机工程与应用
2006年 第6期

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