文献类型：期刊文献

英文题名：The Construction and Approximation of a Class of Neural Networks Operators with Ramp Functions

作者：Chen, Zhixiang[2];Cao, Feilong[1]

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

年份：2012

卷号：14

期号：1

起止页码：101

外文期刊名：JOURNAL OF COMPUTATIONAL ANALYSIS AND APPLICATIONS

收录：SCI-EXPANDED(收录号：WOS:000300529400009)、、Scopus(收录号：2-s2.0-84863018410)、WOS

基金：This research was supported by the National Natural Science Foundation of China (Nos. 90818020, 10871226)

语种：英文

外文关键词：neural network operators; modulus of continuity; order of approximation

外文摘要：Single hidden layer feedforward neural networks with ramp sigmoidal activation functions are constructed to approximate two-variable functions defined on compact interval. With the help of modulus of continuity and analysis techniques, two Jackson-type theorems are given respectively when the objective functions being continuous and having continuous partial derivatives of order N.