deposit_your_work

The 2nu-SVM: A Cost-Sensitive Extension of the nu-SVM

Files in this item

Files Size Format View
Dav2005Dec9The2nuSVMA.PDF 151.3Kb application/pdf Thumbnail

Show simple item record

Item Metadata

dc.contributor.author Davenport, Mark A.
dc.creator Davenport, Mark A.
dc.date.accessioned 2007-10-31T00:41:37Z
dc.date.available 2007-10-31T00:41:37Z
dc.date.issued 2005-12-01
dc.date.submitted 2006-07-27
dc.identifier.uri http://hdl.handle.net/1911/19831
dc.description Tech Report
dc.description.abstract Standard classification algorithms aim to minimize the probability of making an incorrect classification. In many important applications, however, some kinds of errors are more important than others. In this report we review cost-sensitive extensions of standard support vector machines (SVMs). In particular, we describe cost-sensitive extensions of the C-SVM and the nu-SVM, which we denote the 2C-SVM and 2nu-SVM respectively. The C-SVM and the nu-SVM are known to be closely related, and we prove that the 2C-SVM and 2nu-SVM share a similar relationship. This demonstrates that the 2C-SVM and 2nu-SVM explore the same space of possible classifiers, and gives us a clear understanding of the parameter space for both versions.
dc.language.iso eng
dc.subject.other Image Processing and Pattern analysis
dc.title The 2nu-SVM: A Cost-Sensitive Extension of the nu-SVM
dc.type Tech Report
dc.citation.bibtexName techreport
dc.citation.journalTitle Rice University ECE Technical Report
dc.date.modified 2006-07-27
dc.contributor.center Digital Signal Processing (http://dsp.rice.edu/)
dc.citation.issueNumber TREE 0504
dc.relation.project http://www.ece.rice.edu/~md/npsvm.php
dc.relation.software http://www.dsp.rice.edu/software
dc.type.dcmi Text
dc.identifier.citation M. A. Davenport, "The 2nu-SVM: A Cost-Sensitive Extension of the nu-SVM," Rice University ECE Technical Report, no. TREE 0504, 2005.

This item appears in the following Collection(s)

  • ECE Publications [1032 items]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students
  • DSP Publications [508 items]
    Publications by Rice Faculty and graduate students in digital signal processing.