Title

Training Fuzzy Number Neural Networks Using Constrained Backpropagation

Abstract

Few training techniques are available for neural networks with fuzzy number weights, inputs, and outputs. Typically, fuzzy number neural networks are difficult to train because of the many α-cut constraints implied by the fuzzy weights. In this paper, we introduce a weight representation that simplifies the constraint equations. A constrained form of back propagation is then developed for fuzzy number neural networks. Standard backpropagation may be viewed as a constrained optimization of the linearization of the weight function. Our weight representation allows use of the additional α-cut constraints during a weight update.

Meeting Name

IEEE World Congress on Computational Intelligence (FUZZ-IEEE'98) (1998: May 4-9, Anchorage, AK)

Department(s)

Electrical and Computer Engineering

International Standard Book Number (ISBN)

078034863X

International Standard Serial Number (ISSN)

1098-7584

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 1998 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.


Share

 
COinS