Deakin home > Deakin University Library > Deakin Research Online > The importance of neighbourhood size in self organising systems
Openly accessible

The importance of neighbourhood size in self organising systems

Keith-Magee, Russell, Venkatesh, Svetha and Takatsuka, Masahiro 1999, The importance of neighbourhood size in self organising systems, in ICONIP'99 : Proceedings of the 6th International Conference on Neural Information Processing, IEEE, [Washington, D. C.], pp. 267-272.

Document type: Conference Paper
Collections: School of Information Technology
Open Access Collection
Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads
venkatesh-theimportance-1999.pdf Published version application/pdf 547.71KB 4

Title The importance of neighbourhood size in self organising systems
Author(s) Keith-Magee, Russell
Venkatesh, Svetha
Takatsuka, Masahiro
Conference name International Conference on Neural Information Processing (6th : 1999 : Perth, W. A.)
Conference location Perth, W. A.
Conference dates 16-20 Nov. 1999
Title of proceedings ICONIP'99 : Proceedings of the 6th International Conference on Neural Information Processing
Editor(s) [Unknown]
Publication date 1999
Conference series International Conference on Neural Information Processing
Start page 267
End page 272
Total pages 6
Publisher IEEE
Place of publication [Washington, D. C.]
Keyword(s) gaussian outputs
biologically-derived model
gain decay
learning
neighbourhood size
output states
performance
region size
self-organising maps
topographic feature maps
winning neuron selection
Summary In recent times, the analysis of SOM (self-organising map) performance has concentrated on optimising the gain decay, rather than the size, form and decay of the neighbourhood function. We propose that the size, form and decay of region size plays a much more significant role in the learning, and especially in the development, of topographic feature maps. In this paper, a biologically-derived SOM model is presented. This model is able to select a single winning neuron and to form Gaussian outputs about this winner, without the need for a meta-level decision-making structure to artificially select a winner and fit a Gaussian output to that winner. Using this model, some fundamental characteristics of the relationship between neighbourhood size and SOM output states are demonstrated.
Notes This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
ISBN 0780358716
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Copyright notice ©1999, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044824
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Access Statistics: 10 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Tue, 01 May 2012, 11:00:37 EST