Constructive approximation to real function by wavelet neural networks

Original Article


We present a type of single-hidden layer feed-forward wavelet neural networks. First, we give a new and quantitative proof of the fact that a single-hidden layer wavelet neural network with n + 1 hidden neurons can interpolate + 1 distinct samples with zero error. Then, without training, we constructed a wavelet neural network Xa(x, A), which can approximately interpolate, with arbitrary precision, any set of distinct data in one or several dimensions. The given wavelet neural network can uniformly approximate any continuous function of one variable.


Wavelet neural networks Interpolation Uniform approximation 


  1. 1.
    Huang GB, Babri HA (1998) Feedforward neural networks with arbitrary bounded nonlinear activation functions. IEEE Trans Neural Netw 9(1):224–229CrossRefGoogle Scholar
  2. 2.
    Sartori MA, Antsaklis PJ (1991) A simple method to derive bounds on the size and to train multilayer neural networks. IEEE Trans Neural Netw 2(4):467–471CrossRefGoogle Scholar
  3. 3.
    Tamura S, Tateishi M (1997) Capabilities of a four-layered feedforward neural network. IEEE Trans Neural Netw 8(2):251–255CrossRefGoogle Scholar
  4. 4.
    Barhen J, Cogswell R, Protopopescu V (2000) Single iteration training algorithm for multilayer feedforward neural networks. Neural Process Lett 11:113–129CrossRefGoogle Scholar
  5. 5.
    Li X (2002) Interpolation by ridge polynomials and its application in neural networks. J Comput Appl Math 144:197–209MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Fei-Long CAO, Zong-Ben XU, Ji-Ye L (2003) Approximation of polynomial functions by neural network: construction of network and algorithm of approximation. Chin J Comput 26(8):906–912Google Scholar
  7. 7.
    Anthony M (1994) Function learning from interpolation, London School of Economics-Mathematics Preprint Series-73 (LSE-MPS-73)Google Scholar
  8. 8.
    Sontag ED (1992) Feedforward nets for interpolation and classification. J Comput Syst Sci 45:20–48MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Chui CK, Li X, Mhaskar HN (1994) Neural networks for localized approximation. Math Comput 63:607–623MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Chui CK, Li X, Mhaskar HN (1996) Limitations of the approximation capabilities of neural networks with one hidden layer. Adv Comput Math 5:233–243MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Cardaliaguet P, Euvrard G (1992) Approximation of a function and its derivative with a neural network. Neural Netw 5:207–220CrossRefGoogle Scholar
  12. 12.
    Llanas B, Sainz FJ (2006) Constructive approximate interpolation by neural networks. J Comput Appl Math 188:283–308MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Xuli H, Muzhou H (2007) Neural networks for approximation of real functions with the Gaussion functions. In: Proceedings of the third international conference on natural computation (ICNC’07), Haikou, China, vol 1. IEEE Computer Society Press, Los Alamitos, pp 601–605Google Scholar
  14. 14.
    Chui CK (1994) An introduction to wavelets. Academic Press, BostonGoogle Scholar
  15. 15.
    Shristava Y, Dasgupta S (1990) Neural networks for exact matching of functions on a discrete domain. In: Proceedings of the 29th IEEE conference on decision and control, Honolulu, 5–7 December 1990, pp 1719–1724Google Scholar

Copyright information

© Springer-Verlag London Limited 2008

Authors and Affiliations

  1. 1.School of Information Science and EngineeringCentral South UniversityChangshaChina
  2. 2.School of Mathematical Sciences and Computing TechnologyCentral South UniversityChangshaChina
  3. 3.State Key Laboratory of Petroleum Resource and ProspectingChina University of PetroleumBeijingChina

Personalised recommendations