Results

**1 - 1**of**1**### unknown title

"... Abstract — The inversion algorithm of a fuzzy neural network is a process of computing inputs that produce a given target when fed into the neural network. The inversion algorithm of fuzzy neural networks is based on the gradient descent method, in which we obtain a new estimate inverse of , and ad ..."

Abstract
- Add to MetaCart

(Show Context)
Abstract — The inversion algorithm of a fuzzy neural network is a process of computing inputs that produce a given target when fed into the neural network. The inversion algorithm of fuzzy neural networks is based on the gradient descent method, in which we obtain a new estimate inverse of , and adjust the total inputs in the input layer, then iteratively decrease the error between its output and the target. First, we present a framework of learning algorithms of fuzzified neural networks and introduce the idea of fuzzy number. Next, we derive the inversion algorithm of fuzzified neural networks by applying the adjusting scheme for fuzzy variables to total inputs in the input layer. Finally, we give an example based on if-then rule and apply the proposed method on it. Index Term — Fuzzy neural networks, learning algorithm, Inversion algorithm, fuzzy triangular, fuzzy trapezoidal, fuzzy number. I.