A systolic array for nonlinear adaptive filtering and pattern recognition

Author

McWhirter, J.G. ; Broomhead, D.S. ; Shepherd, T.J.

Author_Institution

R. Signals & Radar Establ., Malvern, UK

fYear

1990

fDate

5-7 Sep 1990

Firstpage

700

Lastpage

711

Abstract

A systolic array for multidimensional fitting and interpolation using (nonlinear) radial basis functions (RBFs) is proposed. The fit may be constrained very simply to ensure that the resulting surface takes a pre-determined value at one or more specific points. The RBF processor is capable of performing a wide range of complex pattern recognition tasks. The processor, which constitutes a form of nonlinear adaptive filter, behaves like a neural network based on the multilayer, feedforward perceptron model

Keywords

adaptive filters; computerised pattern recognition; neural nets; systolic arrays; complex pattern recognition tasks; feedforward perceptron model; interpolation; multidimensional fitting; neural network; nonlinear adaptive filtering; pattern recognition; radial basis functions; systolic array; Adaptive filters; Feedforward neural networks; Interpolation; Multi-layer neural network; Multidimensional systems; Multilayer perceptrons; Neural networks; Pattern recognition; Surface fitting; Systolic arrays;

fLanguage

English

Publisher

ieee

Conference_Titel

Application Specific Array Processors, 1990. Proceedings of the International Conference on

Conference_Location

Princeton, NJ

Print_ISBN

0-8186-9089-5

Type

conf

DOI

10.1109/ASAP.1990.145504

Filename

145504