Fuzzy neural networks based on spline functions
I. Shimojima, Toshio Fukuda, Fumihito Arai · 2005
Recently, fuzzy systems are used in many fields and places. In order to apply the fuzzy systems to wider fields, it is necessary to study the tuning methods of the fuzzy system. Some self-tuning methods have been proposed so far. However these conventional self-tuning methods do not have sufficient capability of generalization. In this paper, we propose a new self-tuning fuzzy neural network. The fuzzy neural network consists of membership functions that are expressed by spline functions. The delta rule is applied to tune the membership functions and consequent parts. The effectiveness of the proposed methods is shown by some numerical examples.