Multilayer perceptron trained using radial basis functions

14 September 1989

journal article
Published by Institution of Engineering and Technology (IET) in Electronics Letters

Vol. 25 (19) , 1296-1297
https://doi.org/10.1049/el:19890867

Abstract

In the letter an algebraic equation for the training of a multilayer perceptron using radial basis functions is derived. Examples using this technique for the training of a network for the exclusive-OR and related problems are presented. Suggestions on the choice of the number of centres are given

Keywords

TRAINING
NEURAL NETWORKS
ERROR BACK-PROPAGATION
RADIAL BASIS FUNCTIONS
WEIGHT MATRIX
SIGNAL PROCESSING
MULTILAYER PERCEPTRON
ALGEBRAIC EQUATION
ARTIFICIAL INTELLIGENCE
EXCLUSIVE-OR

This publication has 0 references indexed in Scilit: