| B样条神经网络的构造理论 |
| |
| 引用本文： | 於东军,王士同.B样条神经网络的构造理论[J].计算机研究与发展,1999,36(5):534-540. |
| |
| 作者姓名： | 於东军 王士同 |
| |
| 作者单位： | 华东船舶工业学院计算机科学系 |
| |
| 摘 要： | 文中首先讨论了Ｂ样条基函数的特性，在此基础上采用构造性的方法从理论上了Ｂ样条神经网络能够以任意精度逼近任意定义在致密区间上的连续实函数，最后给出了构造性算法，使用此算法，能在满足误差要求的条件下，构造出几乎最小的Ｂ样条基函数。
|
| 关 键 词： | B样条 神经网络 构造理论 函数逼近 |
CONSTRUCTIVE THEORY FOR B\|SPLINE NEURAL NETWORK |
| |
| YU Dong\|Jun and WANG Shi\|Tong.CONSTRUCTIVE THEORY FOR B\|SPLINE NEURAL NETWORK[J].Journal of Computer Research and Development,1999,36(5):534-540. |
| |
| Authors: | YU Dong\|Jun and WANG Shi\|Tong |
| |
| Affiliation: | YU Dong-Jun and WANG Shi-Tong;
(Department of Computer Science,East China Shipbuilding Institute,Zhenjiang |
| |
| Abstract: | The characteristics of B\|spline basis function is first discussed, based on which B\|spline neural network is proved to be a universal approximator. And then a constructive algorithm is presented. It is proved that this algorithm can be used to build a B\|spline neural network with minimum hidden units to approximate any continuous function defined on compact set to a prescribed accuracy. |
| |
| Keywords: | B\|spline neural network constructive theory |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
