Advertisement

Science in China Series F: Information Sciences

, Volume 47, Issue 1, pp 97–112 | Cite as

The essential order of approximation for neural networks

Article

Abstract

There have been various studies on approximation ability of feedforward neural networks (FNNs). Most of the existing studies are, however, only concerned with density or upper bound estimation on how a multivariate function can be approximated by an FNN, and consequently, the essential approximation ability of an FNN cannot be revealed. In this paper, by establishing both upper and lower bound estimations on approximation order, the essential approximation ability (namely, the essential approximation order) of a class of FNNs is clarified in terms of the modulus of smoothness of functions to be approximated. The involved FNNs can not only approximate any continuous or integrable functions defined on a compact set arbitrarily well, but also provide an explicit lower bound on the number of hidden units required. By making use of multivariate approximation tools, it is shown that when the functions to be approximated are Lipschitzian with order up to 2, the approximation speed of the FNNs is uniquely determined by modulus of smoothness of the functions.

Keywords

feedforward neural networks approximation order the modulus of smoonthness of a multivariate function 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cardaliaguet, P., Euvrard, G., Approximation of a function and its derivatives with a neural network, Neural Networks, 1992, 5: 207–220.CrossRefGoogle Scholar
  2. 2.
    Chen, T. P., Chen, H., Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical system, IEEE Transaction on Neural Networks, 1995, 6: 911–917.CrossRefGoogle Scholar
  3. 3.
    Chen, T. P., Approximation problems in system identification with neural networks, Science in China, Series A, 1994, 24(1): 1–7.Google Scholar
  4. 4.
    Chui, C. K., Li, X., Approximation by ridge functions and neural networks with one hidden layer, J. Approx. Theory, 1992, 70: 131–141.MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Chui, C. K., Li, X., Neural networks with one hidden layer, In: Multivariate Approximation: From CAGD to Wavelets (J. Jetter, F. I. Utreras, eds), pp. 77–89, Singapore: World Scientific Press, 1993.Google Scholar
  6. 6.
    Cybenko, G., Approximation by superpositions of sigmoidal function, Math.of Control Signals, and System, 1989, 2: 303–314.MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Funahashi, K. I., On the approximate realization of continuous mappings by neural networks, Neural Networks, 1989, 2: 183–192.CrossRefGoogle Scholar
  8. 8.
    Gallant, A. R., White, H., On learning the derivatives of an unknown mapping with multilayer feedforward networks, Neural Networks, 1992, 5: 129–138.CrossRefGoogle Scholar
  9. 9.
    Hornik, K., Stinchombe, M., White, H., Multilayer feedforward networks are universal approximation, Neural Networks, 1989, 2: 359–366.CrossRefGoogle Scholar
  10. 10.
    Hornik, K., Stinchombe, M., White, H., Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks, Neural Networks, 1990, 3: 551–560.CrossRefGoogle Scholar
  11. 11.
    Leshno, M., Lin, V. Y., Pinks, A., et al., Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural Networks, 1993, 6: 861–867.CrossRefGoogle Scholar
  12. 12.
    Mhaskar, H. N., Micchelli, C. A., Approximation by superposition of a sigmoidal function, Advances in Applied Mathematics, 1992, 13: 350–373.MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Attali, J. G., Pages, G., Approximation of functions by a multilayer perceptron: a new apprach, Neural Networks, 1997, 10: 1069–1081.CrossRefGoogle Scholar
  14. 14.
    Chen, X. H., White, H., Improved rates and asymptotic normality for nonparametric neural network estimators, IEEE Trans. on Information Theory, 1999, 45:682–691.MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Kurkova, V., Kainen, P. C., Kreinovich, V., Estimates of the number of hidden units and variation with respect to half-space, Neural Networks, 1997, 10: 1068–1078.CrossRefGoogle Scholar
  16. 16.
    Maiorov, V., Meir, R. S., Approximation bounds for smooth functions inC(R d) by neural and mixture networks, IEEE Trans. on Neural Networks, 1998, 9: 969–978CrossRefGoogle Scholar
  17. 17.
    Suzuki Shin, Constructive function approximation by three-layer artificial neural networks, Neural Networks, 1998, 11: 1049–1058.CrossRefGoogle Scholar
  18. 18.
    Ditzian, Z., Totik, V., Moduli of Smoothness, New York: Springer-Verlag, 1987.MATHGoogle Scholar
  19. 19.
    Berens, H., Xu, Y., K-moduli, moduli of smoothness, and Bernstein polynomials on a simplex, Indian Math (NS), 1991, 2: 411–421.MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Cao, F. L., Xiong, J. Y., Steckin-Marchaud-type inequality in connection withL p approximation for multivariate Bernstein-Durrmeyer operator, Chinese J. Contemporary Mathematics, 2001, 22(2): 137–142.MathSciNetGoogle Scholar
  21. 21.
    Mhaskar, H. N., Micchelli, C. A., Degree of approximation by neural networks with a single hidden layer, Advances in Applied Mathematics, 1995, 16: 151–183.MATHCrossRefMathSciNetGoogle Scholar
  22. 22.
    Derriennic, M. M., On multivariate approximation by Bernstein-type polynomials, J. Approx. Theory, 1985, 45: 155–166.MATHCrossRefMathSciNetGoogle Scholar
  23. 23.
    Berens, H., Schmid, H. J., Xu, Y., Bernstein-Durrmeyer operators on a simplex, J. Approx. Theory, 1992, 68: 247–261.MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Li, X., Simultaneous approximations of multivariate functions and their derivatives by neural networks with one hidden layer, Neuocomputing, 1996, 12: 327–343.MATHCrossRefGoogle Scholar

Copyright information

© Science in China Press 2004

Authors and Affiliations

  1. 1.Institute for Information and System SciencesXi’an Jiaotong UniversityXi’anChina

Personalised recommendations