[KSCI] Korea Science Citation Index Service

THE CAPABILITY OF PERIODIC NEURAL NETWORK APPROXIMATION

Hahm, Nahmwoo (Department of Mathematics University of Incheon)
Hong, Bum Il (Department of Applied Mathematics Kyung Hee University)

Publication Information

Korean Journal of Mathematics / v.18, no.2, 2010 , pp. 167-174 More about this Journal

Abstract

In this paper, we investigate the possibility of $2{\pi}$ -periodic continuous function approximation by periodic neural networks. Using the Riemann sum and the quadrature formula, we show the capability of a periodic neural network approximation.

Keywords

periodic function; neural network; approximation;

Citations & Related Records

Reference

1	E. W. Cheney, Introduction to Approximation Theory, Chelsea (1982).
2	R. A. Devore and G. G. Lorentz, Constructive Approximation, Springer-Verlag (1993).
3	Zhou Guanzhen, On the Order of Approximation by Periodic Neural Networks Based on Scattered Nodes, Appl. Math. J. Chinese Univ. Ser. B 20(3)(2005), 352-362. DOI ScienceOn
4	G. G. Lorentz, Approximaton of Functions, Chelsea(1986).
5	H. N. Mhaskar and C. A. Micchelli, Degree of Approximmation by Neural and Translation Networks with a Single Hidden Layer, Adv. in Appl. Math. 16(1995), 151-183. DOI ScienceOn
6	H. N. Mhaskar and C. A. Micchelli, Approximation by Superposition of a Sig- moidal Function, Univ. of Cambridge Num. Anal. Report (1991), 1-26.
7	I. P. Natanson, Constructive Function Theory-Uniform Approximation, Ungar Publ. (1964).
8	S. Suzuki, Constructive Function-Approximation by Three-Layer Artificial Neural Networks, Neural Networks 11(1998), 1049-1058. DOI ScienceOn
9	M. S. Vyazovskaya and N. S. Pupashenko, On the Normalizing Multiplier of the Generalized Jackson Kernel, Math. Notes 80(1)(2006), 19-26. DOI ScienceOn