Linear Programming Regressive Support Vector Machine

Author

Xie, Hong ; Wei, Jiang-ping ; Liu, He-li

Author_Institution

Dept. of Electron. Eng., Shanghai Maritime Univ.

fYear

2006

fDate

13-16 Aug. 2006

Firstpage

2196

Lastpage

2199

Abstract

Based on the analysis of the general norm in structure risk to control model complexity for regressive problem, two kinds of linear programming support vector machine corresponding to l₁-norm and l_infin-norm are presented including linear and nonlinear SVMs. A numerical experiment has been done for these two kinds of linear programming support vector machines and classic support vector machine by artificial data. Simulation results show that the generalization performance of this two kind linear programming SVM is similar to classic one, l₁-SVM has less number of support vectors and faster learning speed, and learning result is not sensitive to learning parameters

Keywords

learning (artificial intelligence); linear programming; regression analysis; support vector machines; SVM; artificial data; linear programming regressive support vector machine; model complexity; regressive problem; Cybernetics; Educational institutions; Electronic mail; Information technology; Linear programming; Machine learning; Matrix decomposition; Probability distribution; Quadratic programming; Statistical learning; Support vector machines; Linear programming; Statistical learning theory; Support vector machines; VC dimension;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2006 International Conference on

Conference_Location

Dalian, China

Print_ISBN

1-4244-0061-9

Type

conf

DOI

10.1109/ICMLC.2006.258619

Filename

4028427