A Multilayer Feedforward Fuzzy Neural Network

  • Aydoğan Savran
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3949)


This paper describes the architecture and learning procedure of a multilayer feedforward fuzzy neural network (FNN). The FNN is designed by replacing the sigmoid type activation function of the multilayer neural network (NN) with the fuzzy system (FS). The Levenberg-Marquardt (LM) optimization method with a trust region approach is adapted to train the FNN. Simulation results of a nonlinear system identification problem are given to show the validity of the approach.


Membership Function Hide Layer Activation Function Fuzzy System Fuzzy Rule 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yamada, T., Yabuta, T.: Neural Network Controller using Autotuning Method for Nonlinear Functions. IEEE Transactions on Neural Networks 3, 595–601 (1992)CrossRefGoogle Scholar
  2. 2.
    Chen, C.T., Chang, W.D.: A Feedforward Neural Network with Function Shape Auto-tuning. Neural Networks 9(4), 627–641 (1996)CrossRefGoogle Scholar
  3. 3.
    Guarnieri, S., Pizza, F.: Multilayer Feedforwardt Network with Adaptive Spline Activation Function. IEEE Transactions on Neural Networks 10(3), 672–683 (1999)CrossRefGoogle Scholar
  4. 4.
    Trentin, E.: Networks with Trainable Amplitude of Activation Functions. Neural Networks 14(4/5), 471–493 (2001)CrossRefGoogle Scholar
  5. 5.
    Olivas, E.S., Guerrero, J.D.M., Valls, G.C., Lopez, A.J.S., Maravilla, J.C., Chova, L.G.: A Low-Complexity Fuzzy Activation Function for Artificial Neural Networks. IEEE Transactions on Neural Networks 14(6), 1576–1579 (2003)CrossRefGoogle Scholar
  6. 6.
    Oysal, Y., Becerikli, Y., Konar, A.F.: Generalized modeling Principles of A Nonlinear System with a Dynamic Fuzzy Network. Computers & Chemical Engineering 27, 1657–1664 (2003)CrossRefMATHGoogle Scholar
  7. 7.
    Scales, L.E.: Introduction to Non-Linear Optimization, pp. 115–118. Springer, New York (1985)CrossRefGoogle Scholar
  8. 8.
    Wang, L.X.: A Course in Fuzzy Systems and Control. Prentice-Hall, Inc., Englewood Cliffs (1997)MATHGoogle Scholar
  9. 9.
    Ungar, L.H.: A Bioreactor Benchmark for Adaptive Network-based Process Control. In: Miller III, W.T., Sutton, R.S., Werbos, P.J. (eds.) Neural Networks for Control, pp. 387–402. MIT Press, London (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Aydoğan Savran
    • 1
  1. 1.Department of Electrical and Electronics EngineeringEge UniversityİzmirTurkey

Personalised recommendations