Deakin University
Browse

File(s) under permanent embargo

Incremental training of support vector machines

journal contribution
posted on 2005-01-01, 00:00 authored by Alistair ShiltonAlistair Shilton, M Palaniswami, D Ralph, A C Tsoi
We propose a new algorithm for the incremental training of support vector machines (SVMs) that is suitable for problems of sequentially arriving data and fast constraint parameter variation. Our method involves using a "warm-start" algorithm for the training of SVMs, which allows us to take advantage of the natural incremental properties of the standard active set approach to linearly constrained optimization problems. Incremental training involves quickly retraining a support vector machine after adding a small number of additional training vectors to the training set of an existing (trained) support vector machine. Similarly, the problem of fast constraint parameter variation involves quickly retraining an existing support vector machine using the same training set but different constraint parameters. In both cases, we demonstrate the computational superiority of incremental training over the usual batch retraining method.

History

Journal

IEEE transactions on neural networks

Volume

16

Issue

1

Pagination

114 - 131

Publisher

Institute of Electrical and Electronics Engineers

Location

Piscataway, N.J.

ISSN

1045-9227

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Copyright notice

2005, IEEE