A novel fuzzy BP learning algorithm for four-layer regular fuzzy neural networks

Authors:
Liu Puyin;Yang Wenqiang
Affiliations:
Department of Mathematics, National University of Defense Technology, Changsha, China;Department of Mathematics, National University of Defense Technology, Changsha, China
Venue:
CIMMACS'05 Proceedings of the 4th WSEAS international conference on Computational intelligence, man-machine systems and cybernetics
Year:
2005

Citing 10
Cited 0

A learning algorithm of fuzzy neural networks with triangular fuzzy weights

Fuzzy Sets and Systems - Special issue on fuzzy neural control
Can neural nets be universal approximators for fuzzy functions?

Fuzzy Sets and Systems
The fuzzy neural network approximation lemma

Fuzzy Sets and Systems
Fuzzy number neural networks

Fuzzy Sets and Systems
Analyses of regular fuzzy neural networks for approximation capabilities

Fuzzy Sets and Systems
Numerical analysis of the learning of fuzzified neural networks from fuzzy if—then rules

Fuzzy Sets and Systems - Special issue on clustering and learning
Fuzzified neural network based on fuzzy number operations

Fuzzy Sets and Systems - Fuzzy intervals
Fuzzy Neural Network Theory and Application

Fuzzy Neural Network Theory and Application
The min-max function differentiation and training of fuzzy neural networks

IEEE Transactions on Neural Networks
Efficient learning algorithms for three-layer regular feedforward fuzzy neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The general fuzzy numbers are approximately represented as polygonal fuzzy numbers, which can be determined by finite nested closed interval. Based on interval arithmetic the input-output (I/O) relationship of a four-layer feedforward regular fuzzy neural network (FNN) is analyzed systematically. By introducing semi-jump function 'Lor' a group of partial derivative formulas are established for the error function of the four-layer regular FNN, in which the maximum operator '∧' and minimum operator '∨' are included. A BP learning algorithm for fuzzy weights of the regular FNN is developed. To speed the convergence of the algorithm the learning constant is updated in each iteration step. Our experimental results show that the novel fuzzy BP algorithm can train a regular FNN efficiently to realize a family of fuzzy inference rules approximately, and to finish a uncomplete fuzzy inference rule table to demonstrate the FNN trained by our learning scheme having strong generalization capability.