This paper presents an architecture for a fuzzy neural hybrid system (FNHS). This architecture merges fuzzy logic and neural networks by replacing the rule-base of a typical fuzzy logic controller with a backpropagation neural network. A method is developed for calculating the errors needed to train the neural network. Simulation results are presented which show that the FNHS performs as well as or better than a conventional neural network. Other advantages of using this system are also presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
No takes yet. Share an insight, caveat, or question.
Challoo et al. (2002) studied this question.