Fuzzy Number Neural Networks

Author

James P. Dunyak
Donald C. Wunsch, Missouri University of Science and TechnologyFollow

Abstract

This paper presents a practical algorithm for training 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. A transformation is used to eliminate these constraints and allow use of standard unconstrained optimization methods. The algorithm is demonstrated on a three-layer network.

Recommended Citation

J. P. Dunyak and D. C. Wunsch, "Fuzzy Number Neural Networks," Fuzzy Sets and Systems, vol. 108, no. 1, pp. 49 - 58, Elsevier, Jan 1999.

The definitive version is available at https://doi.org/10.1016/S0165-0114(97)00339-4

Department(s)

Electrical and Computer Engineering

International Standard Serial Number (ISSN)

0165-0114

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 1999 Elsevier, All rights reserved.

Publication Date

01 Jan 1999