Adaptive membership function fusion and annihilation in fuzzy if-then rules
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 961-967 vol.2
- https://doi.org/10.1109/fuzzy.1993.327384
Abstract
The parameters of the input and output fuzzy membership functions for fuzzy if-then min-max inferencing may be adapted using supervised learning applied to training data. Under the assumption that the inference surface is in some sense smooth, the process of adaptation can reveal overdetermination of the fuzzy system in two ways. First, if two membership functions come sufficiently close to each other, they can be fused into a single membership function. Second, annihilation occurs when a membership function becomes sufficiently narrow. In both cases, the number of if-then rules is reduced. In certain cases, the overall performance of the fuzzy system can be improved by this adaptive pruning. The process of membership function fusion and annihilation is illustrated with two examples.<>Keywords
This publication has 5 references indexed in Scilit:
- A learning method of fuzzy inference rules by descent methodPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Fuzzy neural controllerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Back-propagation fuzzy system as nonlinear dynamic system identifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Fuzzy controller design without domain expertsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Neural-network-based fuzzy logic control and decision systemIEEE Transactions on Computers, 1991