Share Email Print

Proceedings Paper

Neural network implementation of fuzzy inference for approximate case-based reasoning
Author(s): Liya Ding
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this chapter, we point out the symbolical-numerical duality of fuzzy logic and the rule-case duality of fuzzy rules in approximate reasoning. By the former, we can use a node of a neural network to represent a fuzzy proposition for the symbolic and the value passing the node (input or output) for the numeric. By the latter, we can construct a neural network structure for describing the relations of fuzzy rules and modifythe weights of the neural network to realize learning from cases (examples). The concept of the so-called approximate case-based reasoning' and its neural network implementation is set up on the above understanding. We first give the basic mechanism of approximate case-based reasoning and the neural network implementation, then extend it to more general and complex cases by several examples.

Paper Details

Date Published: 28 June 1994
PDF: 29 pages
Proc. SPIE 10312, Neural and Fuzzy Systems: The Emerging Science of Intelligent Computing, 1031203 (28 June 1994); doi: 10.1117/12.2283786
Show Author Affiliations
Liya Ding, National Univ. of Singapore (Singapore)

Published in SPIE Proceedings Vol. 10312:
Neural and Fuzzy Systems: The Emerging Science of Intelligent Computing
Sunanda D. Mitra; Madan M. Gupta; Wolfgang F. Kraske, Editor(s)

© SPIE. Terms of Use
Back to Top