1/1
2 files

On optimal degree selection for polynomial kernel with support vector machines : Theoretical and empirical investigations

journal contribution
posted on 06.12.2017, 00:00 authored by A B M Shawkat Ali, K Smith-Miles
The key challenge in kernel based learning algorithms is the choice of an appropriate kernel and its optimal parameters. Selecting the optimal degree of a polynomial kernel is critical to ensure good generalisation of the resulting support vector machine model. In this paper we propose Bayesian and Laplace approximation methods to estimate the polynomial degree. A rule based meta-learning approach is then proposed for automatic polynomial kernel and its optimal degree selection. The new approach is constructed and tested on different sizes of 112 datasets with binary class as well as multi class classification problems. An extensive computational evaluation of these methods is conducted, and rules are generated to determine when these approximation methods are appropriate.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Volume

11

Issue

1

Start Page

1

End Page

18

Number of Pages

18

eISSN

1875-8827

ISSN

1327-2314

Location

Netherlands

Publisher

IOS Press

Language

en-aus

Peer Reviewed

Yes

Open Access

No

Era Eligible

Yes

Journal

International Journal of Knowledge-Based and Intelligent Engineering Systems