Abstract
In this paper, we develop two algorithms for Chebyshev approximation of continuous functions on [0, 1]n using the modulus of continuity and the maximum norm estimated by a given finite data system. The algorithms are based on constructive versions of Kolmogorov's superposition theorem. One of the algorithms we apply to neural networks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
E.K. Blum and L.K. Li, Approximation theory and feedforward networks, Neural Networks 4(1991)511–515.
E.W. Cheney,Introduction to Approximation Theory, McGraw-Hill, New York, 1966.
G. Cybenko, Approximation by superposition of a sigmoidal function, Math. Control Signals Syst. 2:(1989)303–314.
H.L. Frisch, C. Borzi, G. Ord, J.K. Percus and G.O. Williams, Approximate representation of functions of several variables in terms of functions of one variable, Phys. Rev. Lett. 63(1989)927–929.
K. Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks 2(1989)183–192.
R. Hecht-Nielsen, Kolmogorov's mapping neural network existence theorem, in:Proceedings of the International Conference on Neural Networks, vol. III, IEEE Press, New York, 1987, pp. 11–14.
K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks 2(1989)359–366.
A.N. Kolmogorov, On the representation of continuous funtions of several variables by superposition of continuous functions of one variable and addition, Amer. Math. Soc. Transl. 28(1963)55–59.
V. Kurkova, Kolmogorov's theorem and multilayer neural networks, Neural Networks 5(1992)501–506.
G.G. Lorentz, Metric entropy, width, and superpositions of functions, Amer. Math. Monthly 69(1962)469–485.
G.G. Lorentz,Approximation of Functions, Holt, Rinehardt and Winston, New York, 1966.
H.N. Mhaskar and C.A. Micchelli, Approximation by superposition of sigmoidal and radial basis functions, Adv. Appl. Math. 13(1994)350–373.
M. Nees, Approximative versions of Kolmogorov's superposition theorem, proved contructively, J. Comput. Appl. Math. 54(1994)239–250.
D.A. Sprecher, On the structure of continuous functions of serveral variables, Trans. Amer. Math. Soc. 115(1965)340–355.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Nees, M. Chebyshev approximation by discrete superposition. Application to neural networks. Adv Comput Math 5, 137–151 (1996). https://doi.org/10.1007/BF02124739
Issue Date:
DOI: https://doi.org/10.1007/BF02124739