Study on the function of fuzzy data curve in fuzzy-neural network system

Author

Jiang, Zhifeng ; Liu, Zemin

Author_Institution

Dept. of Radio Eng., Beijing Univ. of Posts & Telecommun., China

Volume

1

fYear

1996

fDate

26-29 Nov 1996

Firstpage

11

Abstract

This paper presents an improved fuzzy-neural network (FNN) model, which is a simple but effective fuzzy-rule based model about complex systems. Its architecture could be determined only by using the input-output data of the system. In the FNN model, the membership functions and weights would be adjusted optimally through the high speed BP learning principle, and the number of neurons in the inference layer would be confirmed through fuzzy data curves. Viewing the neural network as a fuzzy model gives an insight into the real system, and provides a method to simplify the neural network

Keywords

backpropagation; fuzzy neural nets; knowledge based systems; large-scale systems; multilayer perceptrons; neural net architecture; complex systems; fuzzy data curve; fuzzy-neural network model; fuzzy-neural network system; fuzzy-rule based model; high speed BP learning principle; inference layer; input-output data; membership functions; multilayered neural network; neural network architecture; neurons; weights; Convergence; Fuzzy logic; Fuzzy neural networks; Fuzzy reasoning; Fuzzy systems; Intelligent networks; Multi-layer neural network; Neural networks; Neurons; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON '96. Proceedings., 1996 IEEE TENCON. Digital Signal Processing Applications

Conference_Location

Perth, WA

Print_ISBN

0-7803-3679-8

Type

conf

DOI

10.1109/TENCON.1996.608687

Filename

608687