|
|||||
|
|
| 球面神经网络的构造与逼近 | |
| 引用本文： | 陈志祥,曹飞龙. 球面神经网络的构造与逼近[J]. 数学学报, 2012, 0(4): 689-700 |
| 作者姓名： | 陈志祥 曹飞龙 |
| 作者单位： | 绍兴文理学院数学系;中国计量学院数学系 |
| 基金项目： | 国家自然科学基金资助项目(61179041,60873206) |
| 摘 要： | 研究球面神经网络的构造与逼近问题.利用球面广义的de la Vallee Poussin平均、球面求积公式及改进的单变量Cardaliaguet-Euvrard神经网络算子,构造具logistic激活函数的单隐层前向网络,并给出了Jackson型误差估计. |
| 关 键 词： | 神经网络 球面调和 算子 逼近 |
Construction and Approximation of Spherical Neural Networks |
|
| Zhi Xiang CHEN. Construction and Approximation of Spherical Neural Networks[J]. Acta Mathematica Sinica, 2012, 0(4): 689-700 | |
| Authors: | Zhi Xiang CHEN |
| Affiliation: | Department of Mathematics,China Jiliang University,Hangzhou 310018,P.R.China |
| Abstract: | This paper studies the problem of the construction and approximation of spherical neural networks.Using generalized de la Vallee Poussin means of sphere, spherical quadrature rules and modified univariate Cardaliaguet-Euvrard neural network operators,we construct feed-forward networks of one hidden layer with logistic activation function,and give the error estimates of Jackson type. |
| Keywords: | neural networks spherical harmonics operator approximation |
| 本文献已被 CNKI 等数据库收录！ | |