Constructive approximate interpolation by neural networks in the metric space. (English) Zbl 1205.65033
Summary: We construct two types of feed-forward neural networks (FNNs) which can approximately interpolate, with arbitrary precision, any set of distinct data in the metric space. Firstly, for analytic activation function, an approximate interpolation FNN is constructed in the metric space, and the approximate error for this network is deduced by using Taylor formula. Secondly, for a bounded sigmoidal activation function, exact interpolation and approximate interpolation FNNs are constructed in the metric space. Also the error between the exact and approximate interpolation FNNs is given.
MSC:
| 65D05 | Numerical interpolation |
| 92B20 | Neural networks for/in biological studies, artificial life and related topics |
References:
| [1] | Ito, Y.; Saito, K., Superposition of linearly independent functions and finite mappings by neural networks, Math. Sci., 21, 27-33 (1996) · Zbl 0852.68037 |
| [2] | Ito, Y., Independence of unscaled basis functions and finite mappings by neural networks, Math. Sci., 26, 117-126 (2001) · Zbl 1052.68010 |
| [3] | Pinkus, A., Approximation theory of the MLP model in neural networks, Acta Numer., 143-195 (1999) · Zbl 0959.68109 |
| [4] | Y. Shrivatava, 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. Shrivatava, 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. |
| [5] | Sontag, E. D., Feedforward nets for interpolation and classification, J. Comput. System Sci., 45, 1, 20-48 (1992) · Zbl 0791.68141 |
| [6] | Li, X., Interpolation by ridge polynomials and its application in neural networks, J. Comput. Appl. Math., 144, 197-209 (2002) · Zbl 0999.41003 |
| [7] | Li, H. X.; Lee, E. S., Interpolation functions of feedfoward neural networks, Comput. Math. Appl., 46, 1861-1874 (2003) · Zbl 1045.92001 |
| [8] | Li, H. X.; Li, L. X.; Wang, J. Y., Interpolation representation of feedforward neural networks, Math. Comput. Model., 37, 829-847 (2003) · Zbl 1048.92003 |
| [9] | Llanas, B.; Sainz, F. J., Constructive approximate interpolation by nerual networks, J. Comput. Appl. Math., 188, 283-308 (2006) · Zbl 1089.65012 |
| [10] | Llanas, B.; Lantarón, S., Hermite interpolation by neural networks, Appl. Math. Comput., 191, 429-439 (2007) · Zbl 1193.41002 |
| [11] | Cao, F. L.; Zhang, Y. Q.; He, Z. R., Interpolation and rates of convergence for a class of neural networks, Appl. Math. Modelling, 33, 1441-1456 (2009) · Zbl 1168.41302 |
| [12] | T.F. Xie, F.L. Cao, The ridge function representation of polynomials and an application to neural networks. Acta Math. Sin. Eng. Ser. (2010) (in press).; T.F. Xie, F.L. Cao, The ridge function representation of polynomials and an application to neural networks. Acta Math. Sin. Eng. Ser. (2010) (in press). |
| [13] | P. Lascaux, T. Theodor, Analyse Numerique Matricielle Apliquée a l’Art de l’Ingenieur, Masson, Paris, 1986.; P. Lascaux, T. Theodor, Analyse Numerique Matricielle Apliquée a l’Art de l’Ingenieur, Masson, Paris, 1986. · Zbl 0601.65016 |
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.
