An Online Support Vector Learning Method

Abstract

An online iterative implementation of support vector (SV) learning is presented. The method converges to the SV solution for batch data and results in a minimal support vector set. For the online case, convergence to the SV solution holds for stationary data and additional automatic methods to control regularisation are demonstrated. For online applications, methods to bound the number of support vectors in an optimal manner are described. Demonstrations of the method for a large data set discrimination and the prediction of chaotic dynamic systems and are included.

Metadata

Item Type:	Monograph
Authors/Creators:	Drezet, Pierre.M.L. Harrison, R.F.
Copyright, Publisher and Additional Information:	The Department of Automatic Control and Systems Engineering research reports offer a forum for the research output of the academic staff and research students of the Department at the University of Sheffield. Papers are reviewed for quality and presentation by a departmental editor. However, the contents and opinions expressed remain the responsibility of the authors. Some papers in the series may have been subsequently published elsewhere and you are advised to cite the later published version in these instances.
Dates:	Published: 21 June 2000
Institution:	The University of Sheffield
Academic Units:	The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) > ACSE Research Reports
Depositing User:	MRS ALISON THERESA BARNETT
Date Deposited:	19 Mar 2015 11:32
Last Modified:	26 Oct 2016 04:20
Status:	Published
Publisher:	Department of Automatic Control and Systems Engineering
Series Name:	ACSE Research Report 771
Open Archives Initiative ID (OAI ID):	oai:eprints.whiterose.ac.uk:84343

CORE (COnnecting REpositories)

An Online Support Vector Learning Method

Abstract

Metadata

Download

acse research report 771

Export

Statistics