The construction and approximation of some neural networks operators

被引：0
作者：
Zhi-xiang Chen
Fei-long Cao
Jian-wei Zhao
机构：
[1] Shaoxing University,Department of Mathematics
[2] China Jiliang University,Department of Mathematics
来源：
Applied Mathematics-A Journal of Chinese Universities | 2012年 / 27卷
关键词：
approximation; sigmoidal function; neural network operator; Bochner-Riesz mean; 41A20; 41A25;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, the technique of approximate partition of unity is used to construct a class of neural networks operators with sigmoidal functions. Using the modulus of continuity of function as a metric, the errors of the operators approximating continuous functions defined on a compact interval are estimated. Furthmore, Bochner-Riesz means operators of double Fourier series are used to construct networks operators for approximating bivariate functions, and the errors of approximation by the operators are estimated.
引用
收藏
页码：69 / 77
页数：8
相关论文
共 24 条
  • [1] Chen D. B.(1993)Degree of approximation by superpositions of a sigmoidal function Approx Theory Appl 9 17-28
  • [2] Chen T. P.(1994)Approximation problems in system identification with neural networks (in Chinese) Sci China Ser A 24 1-7
  • [3] Chen T. P.(1995)Approximation capability in C(R) by multilayer feedforward networks and related problems IEEE Trans Neural Networks 6 25-30
  • [4] Chen H.(2009)The approximation operators with sigmoidal functions Comput Math Appl 58 758-765
  • [5] Liu R. W.(1989)Approximation by superpositions of a single function Math Control Signals Systems 2 303-314
  • [6] Chen Z. X.(1991)Approximation capabilities of multilayer feedforward networks Neural Networks 4 251-257
  • [7] Cao F. L.(1993)Multilayer feedforward networks with a nonpolynomial activation function can approximate any function Neural Networks 6 861-867
  • [8] Cybenko G.(2006)Constructive approximate interpolation by neural networks J Comput Appl Math 188 283-308
  • [9] Hornik K.(1992)Approximation by superposition of sigmoidal and radial basis functions Adv in Appl Math 13 350-373
  • [10] Leshno M.(1995)Degree of approximation by neural and translation networks with a single hidden layer Adv in Appl Math 16 151-183
123