期刊文献+

神经网络对R^d上连续函数最佳逼近的一个注记(英文)

A NOTE ON NEURAL NETWORKS FOR OPTIMAL APPROXIMATION OF CONTINUOUS FUNCTIONS IN R^d
下载PDF
导出
摘要 本文构造了一类单隐层神经网络,使其逼近R^d上连续函数的速度达到最佳代数多项式逼近速度,并刻划了该类单隐层神经网络的逼近性质. In this paper, we construct a class of neural networks with single hidden layer, by which the approximation rate to continuous functions of d variables on any compact subset of Rd is the same as the case by the best algebraic polynomial. Fur- thermore, we characterize the approximation properties of this class of neural networks with single hidden laver.
出处 《南京大学学报(数学半年刊)》 CAS 2013年第1期34-39,共6页 Journal of Nanjing University(Mathematical Biquarterly)
基金 Supported by National Natural Science Foundation of China(11171137) Natural Science Foundation of Zhejiang Province(Y6110676)
关键词 神经网络 逼近速度 最佳逼近多项式 neural networks, approximation rate, the best algebraic polynomial ap-proximation
  • 相关文献

参考文献6

  • 1Cybenko G. Approximation by Superposition of Sigmoidal Functions. Mathematics of Control, Signal and Systems, 1989,2: 303-314.
  • 2Mhaskar H N. Neural Networks for Optimal Approximation of Smooth and Analytic Functions. Neural Computation, 1996,8: 164-177.
  • 3Mhaskar H N and Micchelli C A. Approximation by Superposition of a Sigmoidal Function and Radial Basis Functions. Advances in Applied Mathematicas, 1992, 13: 350-373.
  • 4Chui K K and Li X. Approximation by Ridge Function and Neural Networks with One hidden Layer. J. Approx. Thory, 1992,70: 131-141.
  • 5Leshno M, Lin V, Pinkus A and Schocken S. Multilayer Feedforward Networks with A nonpolynomail Activation Function can Approximate any F~nction. Neural Networks, 1973, 6: 861-867.
  • 6Xie T F and Zhou X L. Neural Networks for Optimal Approximation of Continuous Functions in R^d (to appear in Acta Mathematic Application Sinica, English Series).

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部