Twin Support Vector Machines for Pattern Classification

Author

Jayadeva ; Khemchandani, R. ; Chandra, Suresh

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Technol., New Delhi

Volume

29

Issue

5

fYear

2007

fDate

5/1/2007 12:00:00 AM

Firstpage

905

Lastpage

910

Abstract

We propose twin SVM, a binary SVM classifier that determines two nonparallel planes by solving two related SVM-type problems, each of which is smaller than in a conventional SVM. The twin SVM formulation is in the spirit of proximal SVMs via generalized eigenvalues. On several benchmark data sets, Twin SVM is not only fast, but shows good generalization. Twin SVM is also useful for automatically discovering two-dimensional projections of the data

Keywords

eigenvalues and eigenfunctions; pattern classification; support vector machines; generalized eigenvalues; machine learning; pattern classification; support vector machines; Constraint optimization; Eigenvalues and eigenfunctions; Kernel; Machine learning; Pattern classification; Quadratic programming; Statistical learning; Support vector machine classification; Support vector machines; Support vector machines; eigenvalues; eigenvectors.; generalized eigenvalues; machine learning; pattern classification; Algorithms; Artificial Intelligence; Cluster Analysis; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2007.1068

Filename

4135685