文献类型：期刊文献

英文题名：Approximation by network operators with logistic activation functions

作者：Chen, Zhixiang[1];Cao, Feilong[2];Hu, Jinjie[1]

机构：[1]Shaoxing Univ, Dept Math, Shaoxing 312000, Zhejiang, Peoples R China;[2]China Jiliang Univ, Dept Math, Hangzhou 310018, Zhejiang, Peoples R China

年份：2015

卷号：256

起止页码：565

外文期刊名：APPLIED MATHEMATICS AND COMPUTATION

收录：SCI-EXPANDED(收录号：WOS:000349979300050)、、EI(收录号：20150700534932)、Scopus(收录号：2-s2.0-84922696007)、WOS

基金：The authors would like to thank the reviewers for their valuable comments and suggestions. This work was supported by the National Natural Science Foundation of China (Grant Nos. 61179041, 61272023, 91330118 and 11401388).

语种：英文

外文关键词：Neural networks; Sigmoidal function; Operator; Approximation; Modulus of continuity

外文摘要：This paper aims to study the construction and multivariate approximation of a class of network operators with logistic sigmoidal functions. First, a class of even and bell-shaped function with support on R is constructed by using appropriate translation and combination of the logistic function. Then, the constructed function is employed as activation function to construct a kind of so-called Cardaliaguet-Euvrard type network operators. Finally, these network operators are used to approximate bivariate functions in C-[-1,C-1]2, and a Jackson type theorem for the approximation errors is established. Crown Copyright (C) 2015 Published by Elsevier Inc. All rights reserved.