A multilayer feedforward fuzzy neural network
Articles > Article · 2006
Authors: Aydoğan SAVRAN
ARTIFICIAL INTELLIGENCE AND NEURAL NETWORKS, Journal Indexed in SCI, International, 2006, vol 3949, pp 78-83
Summary
This paper describes the architecture and learning procedure of a multilayer feedforward fuzzy neural network (FNN). The FNN is designed by replacing the sigmoid type activation function of the multilayer neural network (NN) with the fuzzy system (FS). The Levenberg-Marquardt (LM) optimization method with a trust region approach is adapted to train the FNN. Simulation results of a non-linear system identification problem are given to show the validity of the approach.