On rule pruning using fuzzy neural networks

Shann and Fu (SF) proposed a fuzzy neural network (FNN) for rule pruning in a fuzzy controller. In this paper we first analyze the FNN of SF and discuss some of its limitations. SF attempted to eliminate redundant rules interpreting some of the connection weights as certainty factors of rules. In their strategy the connection weights are unrestricted in sign and hence their interpretation as certainty factors introduces some inconsistencies into the scheme. We propose a modification of this FNN, which eliminates these inconsistencies. Moreover, we also propose a pruning scheme which, unlike the scheme of SF, always produces a compatible rule set. Superiority of the modified FNN is established using the inverted pendulum problem. (C) 1999 Elsevier Science B.V. All rights reserved.