The comparative synapse: a multiplication free approach to neuro-fuzzy classifiers

Author

Dogaru, Radu ; Chua, Leon O.

Author_Institution

Dept. of Appl. Electron. & Comput. Sci., California Univ., Berkeley, CA, USA

Volume

46

Issue

11

fYear

1999

fDate

11/1/1999 12:00:00 AM

Firstpage

1366

Lastpage

1371

Abstract

This paper introduces a novel synaptic model called a comparative synapse. Compared with traditional synapses, the new model is multiplication free, being thus attractive for digital implementations. Our results suggests that in an adaptive layer with binary outputs, the synaptic model does not significantly affect the system performances, provided that the input data is properly projected via a nonlinear preprocessor into a separable space. A set of benchmark classification problems were considered to illustrate this property for the case of the comparative synapse and a nonlinear preprocessor defined by fuzzy membership functions

Keywords

adaptive signal processing; fuzzy logic; fuzzy neural nets; pattern classification; piecewise linear techniques; signal classification; adaptive layer; benchmark classification problems; binary outputs; comparative synapse; digital implementations; fuzzy membership functions; multiplication free approach; neuro-fuzzy classifiers; nonlinear preprocessor; separable space; Adaptive signal processing; Artificial neural networks; Data preprocessing; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Neural network hardware; Pattern classification; Performance evaluation; Piecewise linear approximation;

fLanguage

English

Journal_Title

Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on

Publisher

ieee

ISSN

1057-7122

Type

jour

DOI

10.1109/81.802828

Filename

802828