Swinburne
Browse

Selective adjustment of rotationally-asymmetric neuron sigma-widths

Download (755.1 kB)
conference contribution
posted on 2024-07-12, 15:21 authored by Nathan Rose
Radial Basis Networks are a reliable and efficient tool for performing classification tasks. In networks that include a Gaussian output transform within the Pattern Layer neurons, the method of setting the σ-width of the Gaussian curve is critical to obtaining accurate classification. Many existing methods perform poorly in regions of the problem space between examples of differing classes, or when there is overlap between classes in the data set. A method is proposed to produce unique σ values for each weight of every neuron, resulting in each neuron having its own Gaussian 'coverage' area within problem space. This method achieves better results than the alternatives on data sets with a significant amount of overlap and when the data is unscaled.

History

Available versions

PDF (Accepted manuscript)

ISBN

9781457710865

Journal title

2011 International Joint Conference on Neural Network (IJCNN 2011), San Jose, California, United States, 31 July - 05 August 2011

Conference name

2011 International Joint Conference on Neural Network IJCNN 2011, San Jose, California, United States, 31 July - 05 August 2011

Pagination

7 pp

Publisher

IEEE

Copyright statement

Copyright © 2011 IEEE. The accepted manuscript is reproduced in accordance with the copyright policy of the publisher. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Language

eng

Usage metrics

    Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC