Elsevier

Fuzzy Sets and Systems

Volume 118, Issue 2, 1 March 2001, Pages 359-367
Fuzzy Sets and Systems

A fuzzy rule-based algorithm to train perceptrons

https://doi.org/10.1016/S0165-0114(99)00068-8Get rights and content

Abstract

In this paper, a method to train perceptrons using fuzzy rules is presented. The fuzzy rules linguistically describe how to upgrade the weights as well as to state the desired output of the neurons of the hidden layers. The version for networks with one hidden layer is carefully described and illustrated with examples.

References (12)

  • J.M. Benı́tez et al.

    Are artificial neural networks black boxes

    IEEE Trans. Neural Networks

    (1997)
  • M. Delgado et al.

    A fuzzy rule based backpropagation method for training multilayer perceptrons

    Inform. Sci.

    (1998)
  • M. Delgado et al.

    A fuzzy control based algorithm to train perceptrons

    Proc. 6th IEEE Internat. Conf. on Fuzzy Systems

    (1997)
  • D. Driankov et al.

    An Introduction to Fuzzy Control

    (1993)
  • R.M. Goodman, Z. Zeng, A learning algorithm for multi-layer perceptrons with hard-limiting threshold units, Internat....
  • G.J. Klir et al.

    Fuzzy Sets and Fuzzy LogicTheory and Applications

    (1995)
There are more references available in the full text version of this article.
View full text