Classification using radial basis function networks with uncertain weights

Manson, G. and Pierce, S.G. and Worden, K. (2005) Classification using radial basis function networks with uncertain weights. Key Engineering Materials, 293-294. pp. 135-142. ISSN 1013-9826

Full text not available in this repository.Request a copy from the Strathclyde author

Official URL: http://dx.doi.org/10.4028/0-87849-976-8.135

Abstract

This paper considers the performance of radial basis function neural networks for the purpose of data classification. The methods are illustrated using a simple two class problem. Two techniques for reducing the rate of misclassifications, via the introduction of an "unable to classify" label, are presented. The first of these considers the imposition of a threshold value on the classifier outputs whilst the second considers the replacement of the crisp network weights with interval ranges. Two network training techniques are investigated and it is found that, although thresholding and uncertain weights give similar results, the level of variability of network performance is dependent upon the training approach.

Creators(s):	Manson, G., Pierce, S.G. ORCID: https://orcid.org/0000-0003-0312-8766 and Worden, K.;
Item type:	Article
ID code:	7159
Keywords:	damage detection, interval arithmetic, neural network, radial basis function, Electrical engineering. Electronics Nuclear engineering, Mechanics of Materials, Materials Science(all), Mechanical Engineering
Subjects:	Technology > Electrical engineering. Electronics Nuclear engineering
Department:	Faculty of Engineering > Electronic and Electrical Engineering
Depositing user:	Strathprints Administrator
Date deposited:	14 Oct 2008
Last modified:	08 Jul 2020 00:37
Related URLs:	http://materials-science.ttp.net/0-87849...
URI:	https://strathprints.strath.ac.uk/id/eprint/7159
Export data:

CORE (COnnecting REpositories)