A Geometrical Method to Improve Performance of the Support Vector Machine

Author

Williams, P. ; Sheng Li ; Jianfeng Feng ; Si Wu

Author_Institution

Dept. of Informatics, Sussex Univ., Brighton

Volume

18

Issue

3

fYear

2007

fDate

5/1/2007 12:00:00 AM

Firstpage

942

Lastpage

947

Abstract

The performance of a support vector machine (SVM) largely depends on the kernel function used. This letter investigates a geometrical method to optimize the kernel function. The method is a modification of the one proposed by S. Amari and S. Wu. Its concern is the use of the prior knowledge obtained in a primary step training to conformally rescale the kernel function, so that the separation between the two classes of data is enlarged. The result is that the new algorithm works efficiently and overcomes the susceptibility of the original method

Keywords

geometry; support vector machines; geometrical method; kernel function; support vector machine; Artificial neural networks; Backpropagation algorithms; Distributed processing; Kernel; Machine learning; Multidimensional systems; Neural networks; Optimization methods; Support vector machines; Testing; Classification; Riemannian goemetry; conformal transformation; kernel function; support vector machine (SVM); Algorithms; Artificial Intelligence; Computer Simulation; Decision Support Techniques; Information Storage and Retrieval; Models, Theoretical; Neural Networks (Computer); Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2007.891625

Filename

4182408