University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Distributing SOM ensemble training using grid middleware

Vrusias, BL, Vomvoridis, L and Gillam, L (2007) Distributing SOM ensemble training using grid middleware IEEE International Joint Conference on Neural Networks (IJCNN 2007). 2712 - 2717. ISSN 1098-7576

[img]
Preview
PDF
SRF002367.pdf - Published Version

Download (253Kb)

Abstract

In this paper we explore the distribution of training of self-organised maps (SOM) on Grid middleware. We propose a two-level architecture and discuss an experimental methodology comprising ensembles of SOMs distributed over a Grid with periodic averaging of weights. The purpose of the experiments is to begin to systematically assess the potential for reducing the overall time taken for training by a distributed training regime against the impact on precision. Several issues are considered: (i) the optimum number of ensembles; (ii) the impact of different types of training data; and (iii) the appropriate period of averaging. The proposed architecture has been evaluated in a Grid environment, with clock-time performance recorded.

Item Type: Article
Divisions: Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Communication Systems Research
Depositing User: Melanie Hughes
Date Deposited: 23 Sep 2010 11:21
Last Modified: 23 Sep 2013 18:38
URI: http://epubs.surrey.ac.uk/id/eprint/2340

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800