Advertisement

Second Approximation Results

  • James J. Buckley
  • Thomas Feuring
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 25)

Abstract

This chapter is to be a fuzzification of Chapter 4. We wish to see if there are approximation results between fuzzy neural nets, fuzzy expert systems (not the discretized version of Chapter 4), and fuzzy input-output controllers (to be discussed below). However, we first must study the fuzzification of the universal approximator results of Chapter 3.

Keywords

Fuzzy Number Triangular Fuzzy Number Fuzzy Neural Network Interval Arithmetic Fuzzy Function 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References Chapter 8

  1. 1.
    L.C. de Barros, R.C. Bassanezi and P.A. Tonelli: On the Continuity of Zadeh’s Extension, Proc. 7th IFSA, Prague, June 25–29, 1997, Vol. II, pp. 3–8.Google Scholar
  2. 2.
    J.J. Buckley: Training a Fuzzy Neural Net, Joint NAFIPS/IFIS/NASA Conf., San Antonio, Tx, Dec. 18–20, 1994, pp. 73–77.Google Scholar
  3. 3.
    J.J. Buckley: Approximation Aspects of Fuzzy Models, Handbook of Fuzzy Computation, Oxford Univ. Press, to appear.Google Scholar
  4. 4.
    J.J. Buckley and E. Eslami: Fuzzy Neural Nets: Capabilities, in: W. Pedrycz (ed.) Fuzzy Modelling: Paradigms and Practice, Kluwer, 1996, pp. 167–183.CrossRefGoogle Scholar
  5. 5.
    J.J. Buckley and T. Feuring: Universal Approximators for Fuzzy Functions, Fuzzy Sets and Systems, to appear.Google Scholar
  6. 6.
    J.J. Buckley and T. Feuring: The Study of Fuzzy Functions I: Universal Approximations, Proc. WCCI 98, Anchorage, May 4–9, 1998, Vol. I, pp. 750–754.Google Scholar
  7. 7.
    J.J. Buckley and Y. Hayashi: Numerical Relationships between Neural Nets, Continuous Functions and Fuzzy Systems, Fuzzy Sets and Systems 60 (1993) PP. 1–8.Google Scholar
  8. 8.
    J.J. Buckley and Y. Hayashi: Are Regular Fuzzy Neural Nets Universal Approximators? Proc. IJCNN, Nagoya, Japan, Oct. 25–29, 1993, Vol. 1, pp. 721–724.Google Scholar
  9. 9.
    J.J. Buckley and Y. Hayashi: Fuzzy Input-Output Controllers are Universal Approximators, Fuzzy Sets and Systems 58 (1993) pp. 273–278.MathSciNetMATHCrossRefGoogle Scholar
  10. 10.
    J.J. Buckley and Y. Hayashi: Can Fuzzy Neural Nets Approximate Continuous Fuzzy Functions, Fuzzy Sets and Systems 61 (1994) pp. 43–51.MathSciNetMATHCrossRefGoogle Scholar
  11. 11.
    P. Diamond and P. Kloeden: Metric Spaces of Fuzzy Sets, World Scientific, Singapore, 1994.MATHCrossRefGoogle Scholar
  12. 12.
    Th. Feuring: Learning in Fuzzy Neural Networks. IEEE Conf. on Neural Networks, Washington, 1996, pp. 1061–1066.Google Scholar
  13. 13.
    Th. Feuring: Developing Learning Algorithms for Fuzzy Neural Networks. Proc. of 15th IASTED International Conference on Modelling, Identification and Control, Innsbruck, Ed. M. H. Hamza, IASTED-Acta Press Anaheim, 1996, pp. 133–136.Google Scholar
  14. 14.
    Th. Feuring: Fuzzy Neural Networks are Overlapping. IEEE International Conference on Fuzzy Systems, New Orleans, 1996, pp. 1154–1160.Google Scholar
  15. 15.
    Th. Feuring, J.J. Buckley: A Learning Algorithm for Fuzzy Neural Nets. W. Brauer (Ed.) Fuzzy-Neuro Systems ‘88–Computational Intelligence, Proc. 5th Intern. Workshop on FNS ‘88, Munich, March, 18–20, Infix, 1998, pp. 138–145.Google Scholar
  16. 16.
    Th. Feuring, J.J. Buckley, Y. Hayashi: Adjusting Fuzzy Weights in Fuzzy Neural Nets. 2. Intern. Conference on Knowledge-based Intelligent Electronic Systems, Adelaide, Australia, April, 21–23, 1998, Vol. II, pp. 402–406.Google Scholar
  17. 17.
    Th. Feuring, J.J. Buckley, Y. Hayashi: A Gradient Descent Learning Algorithm for Fuzzy Neural Networks. IEEE Int. Conf. on Fuzzy Systems, Anchorage, May 4–9, 1998, Vol. II, pp. 1136–1141.Google Scholar
  18. 18.
    Th. Feuring, W.-M. Lippe: Fuzzy Neural Networks are Universal Approximators. Proc. of IFSA World Congress, Sao Paulo, 1995, pp. 659–662.Google Scholar
  19. 19.
    Th. Feuring, W.-M. Lippe: The Fuzzy Neural Network Approximation Lemma. Fuzzy Sets and Systems, 1997, to appear.Google Scholar
  20. 20.
    Th. Feuring, W.-M. Lippe: Approximation Capacity of Fuzzy Neural Networks. 10. Intern. Symposium on Computer and Information Sciences, Izmir, Turkey, 1995, Vol. 1, pp. 427–434.Google Scholar
  21. 21.
    Th. Feuring, W.-M. Lippe: Learning Quality of Fuzzy Neural Networks. Proc. of World Congress on Neural Networks, Washington D.C., 1995, pp. 258–262.Google Scholar
  22. 22.
    Th. Feuring, W.-M. Lippe: Output Estimation of Fuzzy Neural Networks. Proc. of 4th International Conference on Soft Computing, Iizuka’96, Fukuoka, Japan, 1996, pp. 626–629.Google Scholar
  23. 23.
    Th. Feuring, W.-M. Lippe: Relations between the Training Set and the Output Behaviour of Fuzzy Neural Networks. Proc. of 14th IASTED International Conference on Applied Informatics, Innsbruck, Ed. M. H. Hamza, IASTED-Acta Press Anaheim, 1996, pp. 413–417.Google Scholar
  24. 24.
    Th. Feuring, W.-M. Lippe: Error Prediction for Neural Networks by Fuzzifica-tion. Intern. Journal of Intelligent Systems 13 (1998), pp. 495–502.CrossRefGoogle Scholar
  25. 25.
    Y. Hayashi and J.J. Buckley: Fuzzy I/O Controllers as Universal Approximators, Proc. World Congress on Neural Networks, July 11–15, Portland, OR, 1993, Vol. II, pp. 92–96.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • James J. Buckley
    • 1
  • Thomas Feuring
    • 2
  1. 1.Mathematics DepartmentUniversity of Alabama at BirminghamBirminghamUSA
  2. 2.Department of Electrical and Computer ScienceUniversity of SiegenSiegenGermany

Personalised recommendations