| 混沌时间序列神经网络拓扑结构的选取方法 |
| |
| 引用本文： | 李擎,郑德玲.混沌时间序列神经网络拓扑结构的选取方法[J].北京科技大学学报,1999,21(1):90-93. |
| |
| 作者姓名： | 李擎 郑德玲 |
| |
| 作者单位： | 北京科技大学信息工程学院,北京,100083 |
| |
| 基金项目： | 国家自然科学基金;69772014; |
| |
| 摘 要： | 采用３层前向神经网络描述混沌时间序列的动力学模型，给出了该网络拓扑结构的确定方法。以及使网络泛化误差达到最小为依据确定网络的输入节点和隐含节点个数。仿真结果表明：该方法不仅优化了网络的结构，而且大大减少了网络的泛化误差。
|
| 关 键 词： | 混沌时间序列 神经网络 拓扑结构 泛化误差 |
Determining Topology Architecture for Chaotic Time Series Neural Network |
| |
| Li Qing,Zheng Deling.Determining Topology Architecture for Chaotic Time Series Neural Network[J].Journal of University of Science and Technology Beijing,1999,21(1):90-93. |
| |
| Authors: | Li Qing Zheng Deling |
| |
| Abstract: | Three-layered feed-forward neural network is used to establish the model for chaotictime series dynamic systems. Determination method of topology architecture for network is given.The size of the input node and hidden node is determined by the minimization the generalizationerror of the network. The simulation results show that the network architecture is optimized and thegeneralization error is dramatically decreased when this method is used. |
| |
| Keywords: | chaotic time series neural network topology architecture generalization error |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
