论文信息 - Constructive approximate interpolation by neural networks in the metric space

Constructive approximate interpolation by neural networks in the metric space

In this paper, 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.

[1] Feilong Cao,et al. Interpolation and rates of convergence for a class of neural networks , 2009 .

[2] Allan Pinkus,et al. Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.

[3] Hong-xing Li,et al. Interpolation representation of feedforward neural networks , 2003 .

[4] F. J. Sainz,et al. Constructive approximate interpolation by neural networks , 2006 .

[5] Sagrario Lantarón,et al. Hermite interpolation by neural networks , 2007, Appl. Math. Comput..

[6] Eduardo D. Sontag,et al. Feedforward Nets for Interpolation and Classification , 1992, J. Comput. Syst. Sci..

[7] S. Dasgupta,et al. Neural networks for exact matching of functions on a discrete domain , 1990, 29th IEEE Conference on Decision and Control.

[8] Hong-Xing Li,et al. INTERPOLATION FUNCTIONS OF FEEDFORWARD NEURAL NETWORKS , 2003 .

[9] Xin Li. Interpolation by ridge polynomials and its application in neural networks , 2002 .

[10] F. Cao,et al. The ridge function representation of polynomials and an application to neural networks , 2011 .

[11] P. Lascaux,et al. Analyse numérique matricielle appliquée a l'art de l'ingénieur , 1987 .