Deakin University
Browse
venkatesh-anempirical-1999.pdf (535.68 kB)

An empirical study of neighbourhood decay in Kohonen's self organizing map

Download (535.68 kB)
conference contribution
posted on 1999-01-01, 00:00 authored by R Keith-Magee, Svetha VenkateshSvetha Venkatesh, M Takatsuka
In this paper, empirical results are presented which suggest that size and rate of decay of region size plays a much more significant role in the learning, and especially the development, of topographic feature maps. Using these results as a basis, a scheme for decaying region size during SOM training is proposed. The proposed technique provides near optimal training time. This scheme avoids the need for sophisticated learning gain decay schemes, and precludes the need for a priori knowledge of likely training times. This scheme also has some potential uses for continuous learning.

History

Event

International Joint Conference on Neural Networks (1999, Washington, D. C.)

Pagination

1953 - 1958

Publisher

IEEE

Location

Washington, D. C.

Place of publication

Washington, D. C.

Start date

1999-07-10

End date

1999-07-16

ISBN-10

0780355296

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

IJCNN 1999 : Proceedings of the International Joint Conference on Neural Networks

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC