## Constructive approximate interpolation by neural networks.(English)Zbl 1089.65012

An approximate interpolation net is a single-hidden layer feedforward neural network with sigmoidal nondecreasing activation function. These structures can be used to interpolate any set of distinct data, can uniformly approximate any continuous function of one variable and can be used to obtain uniform approximants of continuous functions of several variables.

### MSC:

 65D05 Numerical interpolation 41A05 Interpolation in approximation theory
Full Text:

### References:

 [1] M. Anthony, Function learning from interpolation, London School of Economics, -Mathematics Preprint Series-73, 1994.; M. Anthony, Function learning from interpolation, London School of Economics, -Mathematics Preprint Series-73, 1994. [2] Anthony, M.; Bartlett, P. L., Neural Network Learning: Theoretical Foundations (1999), Cambridge University Press: Cambridge University Press Cambridge · Zbl 0968.68126 [3] Barhen, J.; Cogswell, R.; Protopopescu, V., Single iteration training algorithm for multilayer feedforward neural networks, Neural Process. Lett., 11, 113-129 (2000) · Zbl 1147.68618 [4] Cardaliaguet, P.; Euvrard, G., Approximation of a function and its derivative with a neural network, Neural Networks, 5, 207-220 (1992) [5] T. Chen, H. Chen, R.-W. Liu, A constructive proof and an Extension of Cybenko’s approximation theorem, in: Computing Science and Statistics, Proceedings of the 22nd Symposium on the Interface, Springer, Berlin, 1991, pp. 163-168.; T. Chen, H. Chen, R.-W. Liu, A constructive proof and an Extension of Cybenko’s approximation theorem, in: Computing Science and Statistics, Proceedings of the 22nd Symposium on the Interface, Springer, Berlin, 1991, pp. 163-168. · Zbl 0746.41022 [6] Chui, C. K.; Li, X.; Mhaskar, H. N., Neural networks for localized approximation, Mathematics of Computation, 63, 607-623 (1994) · Zbl 0806.41020 [7] Chui, C. K.; Li, X.; Mhaskar, H. N., Limitations of the approximation capabilities of neural networks with one hidden layer, Adv. Comput. Math., 5, 233-243 (1996) · Zbl 0855.41026 [8] Debao, Ch., Degree of approximation by superpositions of a sigmoidal function, Approx. Theory & its Appl., 9, 17-28 (1993) · Zbl 0784.41011 [9] Duch, W.; Jankowski, N., Survey of neural transfer functions, Neural Computing Surveys, 2, 163-212 (1999) [10] Hornik, K.; Stinchcombe, M.; White, H., Multilayer feedforward networks are universal approximators, Neural Networks, 2, 359-366 (1989) · Zbl 1383.92015 [11] Huang, G. B.; Babri, H. A., Feedforward neural networks with arbitrary bounded nonlinear activation functions, IEEE Trans. Neural Networks, 9-1, 224-229 (1998) [12] Ito, Y., Nonlinearity creates linear independence, Adv. Comput. Math., 5, 189-203 (1996) · Zbl 0855.92007 [13] Ito, Y., Independence of unscaled basis functions and finite mappings by neural networks, Math. Sci., 26, 117-126 (2001) · Zbl 1052.68010 [14] Ito, Y.; Saito, K., Superposition of linearly independent functions and finite mappings by neural networks, Math. Sci., 21, 27-33 (1996) · Zbl 0852.68037 [15] Kress, R., Numerical Analysis (1998), Springer: Springer New York · Zbl 0913.65001 [16] Lascaux, P.; Theodor, T., Analyse Numerique Matricielle Apliquée a l’Art de l’Ingenieur (1986), Masson: Masson Paris · Zbl 0601.65016 [17] Li, X., Interpolation by ridge polynomials and its application in neural networks, J. Comput. Appl. Math., 144, 197-209 (2002) · Zbl 0999.41003 [18] H.N. Mhaskar, Neural networks for localized approximation of real functions, in: Neural Networks for Signal Processing, Proceedings of the 1993 IEEE-SP Workshop, 6-9 September 1993, IEEE, 1993, pp. 190-196.; H.N. Mhaskar, Neural networks for localized approximation of real functions, in: Neural Networks for Signal Processing, Proceedings of the 1993 IEEE-SP Workshop, 6-9 September 1993, IEEE, 1993, pp. 190-196. [19] Mhaskar, H. N.; Michelli, Ch. A., Approximation by superposition of sigmoidal and radial basis functions, Adv. Appl. Math., 13, 350-373 (1992) · Zbl 0763.41015 [20] A. Pinkus, Approximation theory of the MLP model in neural networks, Acta Numerica (1999) 143-195.; A. Pinkus, Approximation theory of the MLP model in neural networks, Acta Numerica (1999) 143-195. · Zbl 0959.68109 [21] Rivlin, Th. J., An Introduction to the Approximation of Functions (1981), Dover: Dover Mineola, New York · Zbl 0489.41001 [22] Sartori, M. A.; Antsaklis, P. J., A simple method to derive bounds on the size and to train multilayer neural networks, IEEE Trans. Neural Networks, 2-4, 467-471 (1991) [23] Y. Shristava, S. Dasgupta, Neural networks for exact matching of functions on a discrete domain, in: Proceedings of the 29th IEEE Conference on Decision and Control, Honolulu, 1990, pp. 1719-1724.; Y. Shristava, S. Dasgupta, Neural networks for exact matching of functions on a discrete domain, in: Proceedings of the 29th IEEE Conference on Decision and Control, Honolulu, 1990, pp. 1719-1724. [24] Sontag, E. D., Feedforward nets for interpolation and classification, J. Comp. Syst. Sci., 45, 20-48 (1992) · Zbl 0791.68141 [25] Stein, E. M.; Weiss, G., Introduction to Fourier Analysis on Euclidean Spaces (1975), Princeton University Press: Princeton University Press Princeton [26] Tamura, S.; Tateishi, M., Capabilities of a four-layered feedforward neural network, IEEE Trans. Neural Networks, 8-2, 251-255 (1997)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.