Abstract
Sharp conditions are given under which real-valued functions of several real variables can be approximated arbitrarily well by finite linear combinations of elliptic basis functions. Also given is a related result concerning the representation of functions as a limit in the mean of integrals involving elliptic basis functions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. Park and I. W. Sandberg, Universal approximation using radial-basis-function networks,Neural Computation, 3(2), (1991), 246–257.
J. Park and I. W. Sandberg, Approximation and radial-basis-function networks. To appear inNeural Computation, 5(2), (1993), 305–316.
C. K. Chui, An overview of wavelets. In:Approximation Theory and Functional Analysis, C. K. Chui, ed., pp. 47–71, Boston: Academic Press, 1991.
O. Rioul and M. Vetterli, Wavelets and signal processing,IEEE Signal Processing Magazine, 8(10), (1991), 14–38.
E. M. Stein and G. Weiss,Introduction to Fourier Analysis on Euclidean Spaces, Princeton: Princeton University Press, 1971.
S. V. Chakravarthy, Capabilities of Adaptive Networks with Gaussian Basis Functions. Master's thesis, The University of Texas at Austin, 1991.
N. Weymaere and J. Martens, A fast and robust learning algorithm for feedforward neural networks,Neural Networks, 4(3), (1991), 361–370.
W. Rudin,Real and Complex Analysis, New York: McGraw-Hill, third edition, 1987.
W. Rudin,Fourier Analysis on Groups, New York: Interscience Publishers, 1962.
B. E. Petersen,Introduction to the Fourier Transform and Pseudo-Differential Operators, Marshfield, Massachusetts: Pitman Publishing Inc., 1983.
C. K. Chui,An Introduction to Wavelets, Wavelets Analysis and Its Applications, Boston: Academic Press, 1992.
A. Grossmann and J. Morlet, Decomposition of Hardy functions into square integrable wavelets of constant shape,SIAM Journal of Mathematical Analysis, 15(4), (1984), 723–736.
I. Daubechics, The wavelet transform, time-frequency localization and signal analysis.IEEE Transactions on Information Theory, 36(5), (1990), 961–1005.
D. C. Champeney,A Handbook of Fourier Theorems, UK: Cambridge University Press, 1987.
G. Cybenko, Approximation by superpositions of a sigmoidal function,Mathematics of Control, Signals, and Systems, 2(4), (1989), 303–314.
J. Morlet, G. Arens, I. Fourgeau, and D. Giard, Wavelet propagation and sampling theory,Geophysics, 47(2), (1982), 203–236.
R. Murenzi, Wavelet transforms associated to the n-dimensional Euclidean group with dilations: Signal in more than one dimension. In:Wavelets: Time-Frequency Methods and Phase Space, M. Combes, A. Grossmann, and Ph. Tchamitchian, eds. New York: Springer-Verlag, 1989.
C. E. Heil and D. F. Walnut, Continuous and discrete wavelet transforms,SIAM Review, 31(4), (1989), 628–666.
I. Daubechies,Ten Lectures on Wavelets, The Society for Industrial and Applied Mathematics, Philadelphia, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Park, J., Sandberg, I.W. Nonlinear approximations using elliptic basis function networks. Circuits Systems and Signal Process 13, 99–113 (1994). https://doi.org/10.1007/BF01183843
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01183843