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.
SRF002367.pdf - Version of Record
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.
|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|
Actions (login required)
Downloads per month over past year