<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<!-- saved from url=(0038)http://ais.gmd.de/~thorsten/svm_light/ -->
<HTML><HEAD><TITLE>SVM-Light Support Vector Machine</TITLE>
<META content="text/html; charset=windows-1252" http-equiv=Content-Type>
<META content="MSHTML 5.00.2920.0" name=GENERATOR>
<META content=8.0.3514 name=Version>
<META content=11/26/96 name=Date>
<META content="C:\Programme\Microsoft Office\Office\HTML.DOT"
name=Template></HEAD>
<BODY bgColor=#ffffff link=#0000ff vLink=#800080>
<TABLE border=0 cellPadding=5 cellSpacing=0>
<TBODY>
<TR>
<TD vAlign=top width="14%">
<H2><A href="http://www-ai.cs.uni-dortmund.de/logo.html"><IMG border=0
height=81 src="SVM-Light Support Vector Machine.files/eier_graybg.gif"
width=100></A></H2></TD>
<TD vAlign=top width="75%">
<H1 align=center>SVM<I><SUP>light</SUP> </H1></I>
<H1 align=center>Support Vector Machine</H1><FONT color=#000000>
<P align=center>Author: </FONT><A
href="http://ais.gmd.de/~thorsten">Thorsten Joachims</A><FONT
color=#000000> <</FONT><A
href="mailto:[email protected]">mailto:[email protected]</A><FONT
color=#000000>> <BR></FONT><A href="http://www.gmd.de/">GMD
Forschungszentrum Informationstechnik</A><FONT color=#000000>
<BR></FONT><A href="http://ais.gmd.de/">Institute for Autonomous
Intelligent Systems</A><FONT color=#000000> <BR></FONT><A
href="http://ais.gmd.de/KD">Team Knowledge Discovery</A><FONT
color=#000000> </P>
<P align=center>Developed at: <BR></FONT><A
href="http://www.uni-dortmund.de/">University of Dortmund</A><FONT
color=#000000>, </FONT><A
href="http://www.informatik.uni-dortmund.de/">Informatik</A><FONT
color=#000000>, </FONT><A
href="http://www-ai.informatik.uni-dortmund.de/">AI-Unit</A><FONT
color=#000000> <BR></FONT><A
href="http://www.statistik.uni-dortmund.de/sfb475/sfb475.htm">Collaborative
Research Center on 'Complexity Reduction in Multivariate Data'
(SFB475)</A><FONT color=#000000> </P>
<P align=center>Version: 3.50 <BR>Date: 09.11.00</FONT></P></TD>
<TD vAlign=top width="11%">
<H2><IMG height=80 src="SVM-Light Support Vector Machine.files/gmd-m.gif"
width=80></H2></TD></TR></TBODY></TABLE>
<H2>Overview</H2><FONT color=#000000>
<P>SVM<I><SUP>light</I></SUP> is an implementation of Support Vector Machines
(SVMs) in C. The main features of the program are the following: </P>
<UL></FONT>
<LI>fast optimization algorithm
<UL>
<LI>working set selection based on steepest feasible descent
<LI>"shrinking" heuristic
<LI>caching of kernel evaluations
<LI>use of folding in the linear case </LI></UL>
<LI>computes XiAlpha-estimates of the error rate, the precision, and the
recall
<LI>efficiently computes Leave-One-Out estimates of the error rate, the
precision, and the recall
<LI>includes algorithm for approximately training large transductive SVMs
(TSVMs)
<LI>can train SVMs with cost models
<LI>handles many thousands of support vectors
<LI>handles several ten-thousands of training examples
<LI>supports standard kernel functions and lets you define your own
<LI>uses sparse vector representation </LI></UL><FONT color=#000000>
<P>There is also a regression support vector machine based on
SVM<I><SUP>light</I></SUP> available at the AI-Unit: </FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/MYSVM">mySVM</A><FONT
color=#000000>. </P></FONT>
<H2>Description</H2><FONT color=#000000>
<P>SVM<I><SUP>light</I></SUP> is an implementation of Vapnik's Support Vector
Machine [</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Vapnik,
1995</A><FONT color=#000000>] for the problem of pattern recognition. The
optimization algorithm used in SVM<I><SUP>light</I></SUP> is described in
[</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Joachims,
1999a</A><FONT color=#000000>]. The algorithm has scalable memory requirements
and can handle problems with many thousands of support vectors efficiently. </P>
<P>This new version also provides methods for assessing the generalization
performance efficiently. It includes two efficient estimation methods for both
error rate and precision/recall. XiAlpha-estimates [</FONT><A
href="http://ais.gmd.de/~thorsten/svm_light/#References">Joachims,
2000a</A><FONT color=#000000>, </FONT><A
href="http://ais.gmd.de/~thorsten/svm_light/#References">Joachims,
2000b</A><FONT color=#000000>] </FONT>can be computed at essentially no
computational expense, but they are conservatively biased. Almost unbiased
estimates provides leave-one-out testing. <FONT
color=#000000>SVM<I><SUP>light</I></SUP> </FONT>exploits that the results of
most leave-one-outs (often more than 99%) are predetermined and need not be
computed <FONT color=#000000>[</FONT><A
href="http://ais.gmd.de/~thorsten/svm_light/#References">Joachims,
2000b</A><FONT color=#000000>]</FONT>.</P><FONT color=#000000>
<P>Futhermore, this version includes an algorithm for training large-scale
transductive SVMs. The algorithm proceeds by solving a sequence of optimization
problems lower-bounding the solution using a form of local search. A detailed
description of the algorithm can be found in [</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Joachims,
1999c</A><FONT color=#000000>]. </P>
<P>SVM<I><SUP>light</I></SUP> can also train SVMs with cost models (see
[</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Morik
et al., 1999</A><FONT color=#000000>]). </P>
<P>The code has been used on a large range of problems, including text
classification [</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Joachims,
1999c</A><FONT color=#000000>][</FONT><A
href="http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light.eng.html#References">Joachims,
1998a</A><FONT color=#000000>], several image recognition tasks, and medical
applications. Many tasks have the property of sparse instance vectors. This
implementation makes use of this property which leads to a very compact and
efficient representation. </P></FONT>
<H2>Source Code</H2><FONT color=#000000>
<P>The source code is free for scientific use. Please contact me, if you are
planning to use the software for commercial purposes. The software must not be
modified and distributed without prior permission of the author. If you use
SVM<I><SUP>light</I></SUP> in your scientific work, please cite as </P>
<UL>
<LI>T. Joachims, Making large-Scale SVM Learning Practical. Advances in Kernel
Methods - Support Vector Learning, B. Sch�lkopf and C. Burges and A. Smola
(ed.), MIT-Press, 1999. <BR></FONT><A
href="http://www-ai.cs.uni-dortmund.de/DOKUMENTE/joachims_99a.pdf">[PDF]</A><A
href="http://www-ai.cs.uni-dortmund.de/DOKUMENTE/joachims_99a.ps.gz">[Postscript
(gz)]</A></LI></UL><FONT color=#000000>
<P>I would also appreciate, if you sent me (a link to) your papers so that I can
learn about your research. The implementation was developed on Solaris 2.5 with
gcc, but compiles also on SunOS 3.1.4, Solaris 2.7, Linux, IRIX, Windows NT, and
Powermac (after small modifications, see </FONT><A
href="http://ais.gmd.de/~thorsten/svm_light/svm_light_faq.html">FAQ</A><FONT
color=#000000>). The source code is available at the following location: </P>
<DIR></FONT>
<P><A
href="ftp://ftp-ai.cs.uni-dortmund.de/pub/Users/t
SVM相关程序源码.zip_LibSVM_svm c_svm源码_svm程序
版权申诉
40 浏览量
2022-09-23
06:13:10
上传
评论
收藏 773KB ZIP 举报
周楷雯
- 粉丝: 80
- 资源: 1万+
最新资源
- keil2 + proteus + 8051.exe
- 1961ee27df03bd4595d28e24b00dde4e_744c805f7e4fb4d40fa3f695bfbab035_8(1).c
- mediapipe-0.9.0.1-cp37-cp37m-win-amd64.whl.zip
- windows注册表编辑工具
- mediapipe-0.9.0.1-cp37-cp37m-win-amd64.whl.zip
- 校园通行码预约管理系统20240522075502
- 车类型数据集6250张VOC+YOLO格式.zip
- The PyTorch implementation of STGCN.STGCN-main.zip
- 092300108.cpp
- 车类型数据集6000张VOC+YOLO格式.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈