Fuzzy modeling in some reduction methods of inference rules

This paper is concerned with fuzzy modeling in some reduction methods of in ference rules with gradient descent. Reduction methods are presented, which have a reduction mechanism of the rule unit that is applicable in three pa rameters-the central value and the width of the membership function in the antecedent part, and the real number in the consequent part-which constitut e the standard fuzzy system. In the present techniques, the necessary numbe r of rules is set beforehand and the rules are sequentially deleted to the prespecified number. These methodes indicate that techniques other than the reduction approach introduced previously exist. Experimental results are p resented in order to show that the effectiveness differs between the propos ed techniques according to the average inference error and the number of le arning iterations.