Efficient training of RBF networks for classification.


Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. We show how RBFs with logistic and softmax outputs can be trained efficiently using the Fisher scoring algorithm. This approach can be used with any model which consists of a generalised linear output function applied to a model which is linear in its parameters. We compare this approach with standard non-linear optimisation algorithms on a number of datasets.

Publication DOI: https://doi.org/10.1142/S0129065704001930
Divisions: ?? 50811700Jl ??
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Electronic version of an article published as International Journal of Neural Systems, 14 (3), 2004, pp. 201-208, Article DOI: 10.1142/S0129065704001930 © World Scientific Publishing Company http://www.worldscinet.com/ijns/ijns.shtml
Uncontrolled Keywords: radial basis function,non-linear optimisation,probabilistic modelling,classification
Publication ISSN: 1793-6462
Last Modified: 27 Jun 2024 07:38
Date Deposited: 10 May 2010 13:23
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://www.wor ... 129065704001930 (Publisher URL)
PURE Output Type: Article
Published Date: 2004-06
Authors: Nabney, Ian T. (ORCID Profile 0000-0003-1513-993X)



Version: Published Version

Export / Share Citation


Additional statistics for this record