Research Repository

Fast linear stationary methods for Automatically Biased Support Vector Machines

Lai, Daniel and Palaniswami, Marimuthu and Mani, N (2003) Fast linear stationary methods for Automatically Biased Support Vector Machines. In: Proceedings of the International Joint Conference on Neural Networks 2003. IEEE, ‬Piscataway, pp. 2060-2065.

Full text for this resource is not available from the Research Repository.

Abstract

We present a new training algorithm, which is capable of providing Fast training for a new automatically biased SVM. We compare our agorithm to the well-known Sequential Minimal Optimization (SMO) algorithm. We then show that this method allows for the application of acceleration methods which further increases the rates of convergence.

Item Type: Book Section
ISBN: ‬9780780378988
Additional Information:

Doubletree Hotel - Jantzen Beach, Portland, Oregon, July 20-24, 2003

Uncontrolled Keywords: ResPubID19082, machine learning, matrix representation, optimization, pattern recognition, non-linear mapping, hyperplane, extrapolation method, convergence, acceleration
Subjects: FOR Classification > 0102 Applied Mathematics
FOR Classification > 0801 Artificial Intelligence and Image Processing
FOR Classification > 1702 Cognitive Science
Faculty/School/Research Centre/Department > Centre for Ageing, Rehabilitation, Exercise & Sport Science (CARES)
Depositing User: VUIR
Date Deposited: 18 Jun 2013 03:40
Last Modified: 26 Jun 2013 05:09
URI: http://vuir.vu.edu.au/id/eprint/5714
DOI: 10.1109/IJCNN.2003.1223725
ePrint Statistics: View download statistics for this item
Citations in Scopus: 3 - View on Scopus

Repository staff only

View Item View Item

Search Google Scholar