期刊文献+

基于Boosting的支持向量机组合分类器 被引量:7

Boosting-based support vector machines combination classifier
下载PDF
导出
摘要 Boosting是一种有效的分类器组合的方法,文章提出用一个改进的Boosting方法对支持向量机分类器进行集成学习,得到Boosting-MultiSVM分类器;试验结果表明,基于Boosting的支持向量机训练是一个收敛过程,相比标准的支持向量机分类器,Boosting-MultiSVM分类器的泛化性能有不同程度的提高。 Boosting is an effective classifier combination method. An improved Boosting method is presented for support vector machine classifier combination, and a Boosting-MultiSVM classifier is trained. Experimental results show that support vector machine training based on Boosting is convergent. The Boosting-MultiSVM classifier has better generalization performance than the standard support vector machine classifier.
出处 《合肥工业大学学报(自然科学版)》 CAS CSCD 北大核心 2006年第10期1220-1222,共3页 Journal of Hefei University of Technology:Natural Science
基金 安徽省自然科学基金资助项目(03042305)
关键词 支持向量机 BOOSTING 集成学习 support vector machine Boosting ensemble learning
  • 相关文献

参考文献8

  • 1Dietterich T G.Machine learning research:Four current directions[J].AI Magazine,1997,18(4):97-136.
  • 2Schapire R E.A brief introduction to boosting[A].In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence[C].Stockholm:IJCAI,1999.1 401-1 406.
  • 3VapnikVN.统计学习理论的本质[M].北京:清华大学出版社,2000..
  • 4Rātsch G,Mika S,Schālkopf B.Constructing boosting algorithms from SVMs:an application to one-class classification[J].Pattern Analysis and Machine Intelligence,2002,24(9):1 184-1 199.
  • 5Yuan-chin Ivan Chang.Boosting SVM with logistic regression[R].Taipei:Institute of Statistical Science,Academia Sinica,2003.75-80.
  • 6Scholkopf B,Burges C J C,Smola A J.Advances in kernel methods-support vector learning[M].Cambridge:MIT Press,1999.185-208.
  • 7Osuna E,Freund R,Girosi F.An improved training algorithm for support vector machines[A].Neural Networks for Signal Processing (Ⅶ)[C].New York:IEEE,1997.276-285.
  • 8Freund Y,Schapire R E.Experiments with a new boosting algorithm.In.Proc 13th International Conference on Machine Learning[C].San Francisco:Morgan Kaufmann,1996.148-146.

共引文献170

同被引文献56

引证文献7

二级引证文献17

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