Advertisement

A New Approach of Neurofuzzy Learning Algorithm

  • Masaharu Mizumoto
  • Yan Shi

Abstract

In this chapter, we develop a new approach of neurofuzzy learning algorithm for tuning fuzzy rules by using training input-output data, based on the gradient descent method. The major advantage of this approach is that fuzzy rules or membership functions can be learned without changing the form of fuzzy rule table used in usual fuzzy applications, so that the case of weak-firing can be well avoided, which is different from the conventional neurofuzzy learning algorithms. Moreover, we show the efficiency of the developed method by identifying nonlinear functions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D.E. Rumelhart, J. L. McClelland and the PDP Research Group, Parallel Distributed Processing, Cambridge, MA: MIT Press, 1986.Google Scholar
  2. [2]
    M. Maeda and S. Murakami, “An automobile tracking control with a fuzzy logic,” Proc. 3rd Fuzzy System Symposium, Osaka, 61–66, 1987 (in Japanese).Google Scholar
  3. [3]
    M. Mizumoto, “Fuzzy controls by product-sum-gravity method,” Advancement of Fuzzy Theory and Systems in China and Japan (eds. X. H. Liu and M. Mizumoto), Int. Academic Publishers, c11–c14, 1990.Google Scholar
  4. [4]
    M. Mizumoto, “Min-max-gravity method versus product-sum-gravity method for fuzzy controls,” Proc. 4th IFSA Congress, Brussels, Vol. 4 Eng., 127–130, 1991.Google Scholar
  5. [5]
    H. Ichihashi, “Iterative fuzzy modeling and a hierarchical network,” Proc. 4th IFSA Congress, Brussels, Vol.4 Eng., 49–52, 1991.Google Scholar
  6. [6]
    L. X. Wang and J. M. Mendel, “Back-propagation fuzzy system as nonlinear dynamic system identifiers,” Proc. IEEE Int. Congress on Fuzzy Systems, San Diego, 1409–1416, 1992.Google Scholar
  7. [7]
    B. Kosko, Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ 07632, 1992.Google Scholar
  8. [8]
    R. R. Yager and D. P. Filev, “Generation of fuzzy rules by mountain clustering,” International Journal of Intelligent & Fuzzy Systems 2, 209–219, 1994.Google Scholar
  9. [9]
    R. R. Yager and D.P. Filev, Essentials of Fuzzy Modeling and Control, John Wiley & Sons, 1994.Google Scholar
  10. [10]
    Y. Shi, M. Mizumoto, N. Yubazaki, and M. Otani, “A method of generating fuzzy rules based on the neuro-fuzzy learning algorithm,” Journal of Japan Society for Fuzzy Theory and Systems 8:4, 695–705, 1996 (in Japanese).Google Scholar
  11. [11]
    Y. Shi, M. Mizumoto, N. Yubazaki, and M. Otani, “A learning algorithm for tuning fuzzy rules based on the gradient descent method,” Proc. 5th IEEE Int. Conf. on Fuzzy Systems (FUZZ-IEEE’96), New Orleans, USA, Vol. 1, 55–61, 1996.Google Scholar
  12. [12]
    M. Mizumoto, “Product-sum-gravity method = Fuzzy singleton-type reasoning method = Simplified fuzzy reasoning method,” Proc. 5th IEEE Int. Con f. on Fuzzy Systems, New Orleans, Vol. 3, 2098–2102, 1996.Google Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Masaharu Mizumoto
    • 1
  • Yan Shi
    • 1
    • 2
  1. 1.Division of Information and Computer SciencesOsaka Electro-Communication UniversityNeyagawa, OsakaJapan
  2. 2.School of EngineeringKyushu Tokai UniversityKumamotoJapan

Personalised recommendations