An automatic adjustment method of backpropagation learning parameters, using fuzzy inference

Abstract

Fuzzy inference is introduced into a conventional backpropagation learning algorithm for neural networks. This procedure repeatedly adjusts the learning parameters and leads the system to convergence at the earliest possible time. The technique is appropriate in the sense that optimum learning parameters are being applied in every learning cycle automatically, whereas conventional backpropagation does not contain any well-defined rule regarding the proper selection of learning parameters.<>