Digital Gaussian membership function circuit for neuro-fuzzy hardware

Author

Basterretxea, K. ; Tarela, J.M. ; Campo, I. Del

Author_Institution

Elektronika eta Telekomunikazioak Saila, Euskal Herriko Unibertsitatea, Bilbao, Spain

Volume

42

Issue

1

fYear

2006

Abstract

A digital design of a Gaussian membership function circuit is presented. It allows positioning of the function on the universe of discourse to be selected, and its width or variance to be adjusted. The circuit is therefore suitable for implementing digital neuro-fuzzy systems with learning capabilities. The circuit allows control of the delay-time/accuracy rate, and adds a new parameter to the adjustable parameter set of the system that may be used to improve the learning algorithm and optimise system architecture

Keywords

Gaussian processes <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; fuzzy neural nets <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; fuzzy systems <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; interpolation <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; learning (artificial intelligence) <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; programmable logic arrays <neuro-fuzzy hardware, digital Gaussian membership fn. cct.>; delay-time/accuracy rate control; digital Gaussian membership function circuit; digital neuro-fuzzy systems; learning capabilities; neuro-fuzzy hardware; programmable approximation circuit; sequential synchronous design; soft computing techniques;

fLanguage

English

Journal_Title

Electronics Letters

Publisher

iet

ISSN

0013-5194

Type

jour

DOI

10.1049/el:20063712

Filename

1577612