DMCA
Iterative Inversion of Fuzzified Neural Networks
| Citations: | 6 - 0 self |
BibTeX
@MISC{Park_iterativeinversion,
author = {Sungwoo Park and Taisook Han},
title = {Iterative Inversion of Fuzzified Neural Networks},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Theinversion of a neural network is a process of computing inputs which produce a given target when fed into the neural network. The inversion algorithm of crisp neural networks is based on the gradient descent searchin which a candidate inverse is iteratively refined to decrease the error between its output and the target. In this paper, we deriveaninversion algorithm of fuzzified neural networks from that of crisp neural networks. First we present a framework of learning algorithms of fuzzified neural networks and introduce the idea of adjusting schemes for fuzzy variables. 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 make three experiments on the parity-3 problem# we examine the effect of the size of training sets on the inversion and investigate how the fuzziness of inputs and targets of training sets affects the inversion. Keywords---Fuzzified Neural Network, Learning Algorithm, Inversion Algorithm I.
