Learning in neuro/fuzzy analog chips

Author

Rodríguez-Vázquez, Angel ; Vidal-Verdú, Fernando

Author_Institution

Dept. of Analog Design, Edificio CICA, Sevilla, Spain

Volume

3

fYear

1995

fDate

30 Apr-3 May 1995

Firstpage

2325

Abstract

This paper focus on the design of adaptive mixed-signal fuzzy chips. These chips have parallel architecture and feature electrically-controllable surface maps. The design methodology is based on the use of composite transistors-modular and well suited for design automation. This methodology is supported by dedicated, hardware-compatible learning algorithms that combine weight-perturbation and outstar

Keywords

analogue processing circuits; circuit CAD; fuzzy logic; fuzzy neural nets; learning (artificial intelligence); neural chips; parallel architectures; perturbation techniques; adaptive mixed-signal fuzzy chips; composite transistors; design automation; design methodology; electrically-controllable surface maps; hardware-compatible learning algorithms; neuro/fuzzy analog chips; outstar; parallel architecture; weight-perturbation; Analog computers; CMOS technology; Circuits; Design automation; Design methodology; Fuzzy control; Fuzzy systems; Inference algorithms; Parallel architectures; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2570-2

Type

conf

DOI

10.1109/ISCAS.1995.523895

Filename

523895