A projection filter for use with parameterised learning models

Author

Day, M.J.S. ; Payne, J.S.

Author_Institution

Dept. of Comput., Buckinghamshire Chilterns Univ. Coll., High Wycombe, UK

Volume

1

fYear

1998

fDate

16-20 Aug 1998

Firstpage

867

Abstract

This paper presents a projection filter for use with parameterised learning models. Two aspects of the projection filter are considered. Firstly, the filter´s operation is demonstrated using the perceptron learning rule on a simple two class discrimination problem. Secondly, the projection filter is used to extend the learning capabilities of a nonlinear spatio-temporal neural network model. An experiment was undertaken to compare the effectiveness of applying temporal backpropagation to a multilayer feedforward network employing either finite impulse response (FIR) or projection filters. Results show that the projection filter reached a lower mean square error (MSE) when compared to the FIR version of the network

Keywords

FIR filters; backpropagation; feedforward neural nets; filtering theory; learning (artificial intelligence); multilayer perceptrons; signal processing; FIR filters; MSE; finite impulse response filters; mean square error; multilayer feedforward network; nonlinear spatio-temporal neural network model; parameterised learning models; perceptron learning rule; projection filter; projection filters; temporal backpropagation; Backpropagation algorithms; Chaos; Computer architecture; Convergence; Difference equations; Educational institutions; Filtering; Finite impulse response filter; Mean square error methods; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on

Conference_Location

Brisbane, Qld.

ISSN

1051-4651

Print_ISBN

0-8186-8512-3

Type

conf

DOI

10.1109/ICPR.1998.711287

Filename

711287