A generalized S-K algorithm for learning v-SVM classifiers

doi:10.1016/j.patrec.2004.03.011

	A generalized S-K algorithm for learning v-SVM classifiers
	Tao, Q ; Wu, GW ; Wang, J
	2004-07-16
发表期刊	PATTERN RECOGNITION LETTERS
ISSN	0167-8655
卷号	25 期号:10 页码:1165-1171
摘要	The S-K algorithm (Schlesinger-Kozinec algorithm) and the modified kernel technique due to Friess et al. have been recently combined to solve SVM with L-2 cost function. In this paper, we generalize S-K algorithm to be applied for soft convex hulls. As a result, our algorithm can solve v-SVM based on L-1 cost function. Simple in nature, our soft algorithm is essentially a algorithm for finding the epsilon-optimal nearest points between two soft convex hulls. As only the vertexes of the hard convex hulls are used, the obvious superiority of our algorithm is that it has almost the same computational cost as that of the hard S-K algorithm. The theoretical analysis and some experiments demonstrate the performance of our algorithm. (C) 2004 Elsevier B.V. All rights reserved.
关键词	statistical machine learning support vector machines classification v-SVM S-K algorithms soft convex hulls
DOI	10.1016/j.patrec.2004.03.011
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000222392000008
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：19[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/9901
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tao, Q
作者单位	1.New Star Res Inst Appl Tech, Hefei 230031, Peoples R China 2.Chinese Acad Sci, Comp Technol Inst, Bioinformat Lab, Beijing 100080, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Tao, Q,Wu, GW,Wang, J. A generalized S-K algorithm for learning v-SVM classifiers[J]. PATTERN RECOGNITION LETTERS,2004,25(10):1165-1171.
APA	Tao, Q,Wu, GW,&Wang, J.(2004).A generalized S-K algorithm for learning v-SVM classifiers.PATTERN RECOGNITION LETTERS,25(10),1165-1171.
MLA	Tao, Q,et al."A generalized S-K algorithm for learning v-SVM classifiers".PATTERN RECOGNITION LETTERS 25.10(2004):1165-1171.