Elsevier

Fuzzy Sets and Systems

Volume 142, Issue 2, 1 March 2004, Pages 221-242
Fuzzy Sets and Systems

Extended neuro-fuzzy models of multilayer perceptrons

https://doi.org/10.1016/S0165-0114(03)00244-6Get rights and content

Abstract

In this paper the famous neural model, the multilayer perceptron, is extended to a new neural model that is called the additive-Takagi–Sugeno-type multilayer perceptron. The present study proves that this new model can also act as a universal approximator, and thus it can be used in many fields, such as system modeling and identification. The concept of f-duality and the fuzzy operator interactive-or are used to prove that the proposed neural model is functionally equal to a kind of fuzzy inference system. Further, this paper presents another new neuro-fuzzy model that is called the sigmoid-adaptive-network-based fuzzy inference system. Simulation studies show that our proposed models both have stronger approximation capability than multilayer perceptrons.

References (71)

  • A. Van Ooyen et al.

    Improving the convergence of the back-propagation algorithm

    Neural Networks

    (1992)
  • M.K. Weir

    A method for self-determination of adaptive learning rates in back propagation

    Neural Networks

    (1991)
  • D. Whitley

    Genetic algorithms and neural networksoptimizing connections and connectivity

    Computing

    (1990)
  • R.R. Yager

    Connectives and quantifiers in fuzzy logic

    Fuzzy Sets and Systems

    (1991)
  • M.F. Azeem

    Generalization of adaptive neuro-fuzzy inference systems

    IEEE Trans. Neural Networks

    (2000)
  • M.R. Azimi-Sadjadi et al.

    Fast learning process of multilayer neural networks using recursive least squares technique

    IEEE Trans. Signal Process.

    (1992)
  • J.M. Benitez

    Are artificial neural networks black boxes

    IEEE Trans. Neural Networks

    (1997)
  • G.L. Bilbro et al.

    Mean field annealing: a formalism for constructing GNC-like algorithms

    IEEE Trans. Neural Networks

    (1992)
  • J.L. Castro

    SEPARATEa machine learning method based on semi-global partitions

    IEEE Trans. Neural Networks

    (2000)
  • S. Chen

    Parallel recursive prediction error algorithms for training layered neural network

    Internat. J. Control

    (1990)
  • Chin-Teng Lin, C.S. George Lee, Neural-network-based fuzzy logic control and decision system, IEEE Trans. Comput. 40...
  • T.W.S. Chow et al.

    An accelerated recurrent network training algorithm using IIR filter model and recursive least squares method

    IEEE Trans. Circuits Systems—I: Fund. Theory Appl.

    (1997)
  • K.J. Cios, Ning Liu, A machine learning method for generation of a neural network architecture: a continuous ID3...
  • G. Cybenko

    Approximations by superposition of a sigmoidal function

    Math. Control, Signals Systems

    (1989)
  • Eiji Mizutani, J.-S. Jang, Coactive neural fuzzy modeling, in: Proc. of IEEE Internat. Conf. on Neural Networks, Vol....
  • S.E. Fahlman, Faster-learning variations on back-propagation: an empirical study, in: Proc. of 1988 Connectionist...
  • W.K.T. Fukuda et al.

    Learning algorithms of layered neural networks via extended Kalman filters

    Internat. J. Systems Sci.

    (1991)
  • B. Gabrays et al.

    General fuzzy min–max neural networks for clustering and classification

    IEEE Trans. Neural Networks

    (2000)
  • S. Geman et al.

    Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1984)
  • D.E. Goldberg

    Genetic Algorithms in Search, Optimization and Machine Learning

    (1989)
  • Guian Zhou, J. Si, Subset-based training and pruning of sigmoid neural networks, Neural Networks 12 (1999)...
  • M.T. Hagan et al.

    Training feedforward networks with the Marquardt algorithm

    IEEE Trans. Neural Networks

    (1994)
  • J.H. Holland

    Adaptation in Natural and Artificial Systems

    (1975)
  • Hong-Xing Li, C.L. Philip Chen, The equivalence between fuzzy logic systems and feedforward neural networks, IEEE...
  • K.J. Hunt

    Extending the functional equivalence of radial basis function networks and fuzzy inference systems

    IEEE Trans. Neural Networks

    (1996)
  • Cited by (22)

    • Neural networks and statistical learning, second edition

      2019, Neural Networks and Statistical Learning, Second Edition
    View all citing articles on Scopus

    The work in this paper is supported by National Science Foundation of China (Grant No. 60274057 & 60204011).

    View full text