A multilayer feedforward fuzzy neural network

Authors:
Aydoğan Savran
Affiliations:
Department of Electrical and Electronics Engineering, Ege University, İzmir, Turkey
Venue:
TAINN'05 Proceedings of the 14th Turkish conference on Artificial Intelligence and Neural Networks
Year:
2005

Citing 7
Cited 0

Introduction to non-linear optimization

Introduction to non-linear optimization
A bioreactor benchmark for adaptive network-based process control

Neural networks for control
A feedforward neural network with function shape autotuning

Neural Networks
A course in fuzzy systems and control

A course in fuzzy systems and control
Networks with trainable amplitude of activation functions

Neural Networks
Multilayer feedforward networks with adaptive spline activation function

IEEE Transactions on Neural Networks
A low-complexity fuzzy activation function for artificial neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 nonlinear system identification problem are given to show the validity of the approach.