Signal theory for SVM kernel design with applications to parameter estimation and sequence kernels


Nelson, J. D. B., Damper, R. I., Gunn, S. R. and Guo, B. (2008) Signal theory for SVM kernel design with applications to parameter estimation and sequence kernels. Neurocomputing, 72, (1-3), 15-22. (doi:10.1016/j.neucom.2008.01.034).

Download

[img] Postscript
Download (561Kb)

Description/Abstract

Fourier-based regularisation is considered for the support vector machine (SVM) classification problem over absolutely integrable loss functions. By considering the problem in a signal theory setting, we show that a principled and finite kernel hyperparameter search space can be discerned a priori by using the sinc kernel. The training and validation phase required to optimise the SVM can thus be limited to this hyperparameter search space. The method is adapted to a recently proposed max sequence kernel such that positive semi-definiteness, and so convergence, is guaranteed

Item Type: Article
ISSNs: 0925-2312 (print)
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Comms, Signal Processing & Control
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Electronic & Software Systems
ePrint ID: 265121
Date Deposited: 29 Jan 2008 08:22
Last Modified: 27 Mar 2014 20:09
Further Information:Google Scholar
ISI Citation Count:3
URI: http://eprints.soton.ac.uk/id/eprint/265121

Actions (login required)

View Item View Item