Deakin University
Browse
venkatesh-theimportance-1999.pdf (547.72 kB)

The importance of neighbourhood size in self organising systems

Download (547.72 kB)
conference contribution
posted on 1999-01-01, 00:00 authored by R Keith-Magee, Svetha VenkateshSvetha Venkatesh, M Takatsuka
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.

History

Pagination

267 - 272

Location

Perth, W. A.

Open access

  • Yes

Start date

1999-11-16

End date

1999-11-20

ISBN-10

0780358716

Language

eng

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.

Publication classification

E1.1 Full written paper - refereed

Copyright notice

1999, IEEE

Title of proceedings

ICONIP'99 : Proceedings of the 6th International Conference on Neural Information Processing

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC