| 一类神经网络逼近可积函数 |
| |
| 引用本文： | 后敏,曹飞龙. 一类神经网络逼近可积函数[J]. 中国计量学院学报, 2007, 18(2): 155-158 |
| |
| 作者姓名： | 后敏 曹飞龙 |
| |
| 作者单位： | 中国计量学院,理学院,浙江,杭州,310018 |
| |
| 摘 要： | 用连续模刻画了实轴上Cardaliguet-Eurrard型神经网络算子逼近连续函数速度的上界估计,同时,对于Lebesgue可积函数的逼近,构造相应的神经网络算子,并且给出其逼近速度的Jackson型估计.
|
| 关 键 词： | 神经网络 算子 逼近 连续模 |
| 文章编号： | 1004-1540（2007）02-0155-04 |
| 修稿时间： | 2006-12-18 |
Approximation by a class of neural networks to integrable function |
| |
| HOU Min,CAO Fei-long. Approximation by a class of neural networks to integrable function[J]. Journal of China Jiliang University, 2007, 18(2): 155-158 |
| |
| Authors: | HOU Min CAO Fei-long |
| |
| Affiliation: | Department of Information and Mathematics Sciences, China Jiliang University, Hangzhou ,310018, China |
| |
| Abstract: | The estimates of approximation rate for Cardaliguet-Eurrarad type neural networks operators approximating the continuous functions over the real line were given by the modulus of continuity. At the same time, in the case of approximating Lebesgue integrable function, we construct the correspondent neural network operators, and use Jackson type inequality to determine its rate of approximation. |
| |
| Keywords: | neural networks operator approximation modulus of continuity |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
