摘要
研究多元插值神经网络的收敛性问题,举例说明多元插值神经网络对连续函数并非一致收敛,回答了谢庭藩等所提出的问题.
This paper deals with the convergence of multidimensional interpolation neural networks. It is shown by a constructive example that the multidimensional interpolation neural networks are not sure to converge uniformly for any multivariate continuous function defined by a compact set. And a problem proposed by Xie Tingfan et al is answered.
出处
《高校应用数学学报（A辑）》
CSCD
北大核心
2009年第1期91-94,共4页
Applied Mathematics A Journal of Chinese Universities(Ser.A)
基金
国家自然科学基金(90818020
60873206)
浙江省自然科学基金(Y7080235)
浙江省教育厅重点项目基金(20060543)
关键词
神经网络
插值
逼近
误差估计
neural network
interpolation
approximation
estimation of error
