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

作　　者：谢林森[1] 陆文秀[2] 章莉[2] 

机构地区：[1]丽水学院数学系,丽水323000 [2]浙江师范大学数学系,金华321004

出　　处：《南京大学学报（数学半年刊）》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)

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.

关 键 词：神经网络 逼近速度 最佳逼近多项式 

分 类 号：O174.41[理学—数学]