| 多时滞Hopfield神经网络的鲁棒稳定性分析及吸引域的估计 |
| |
| 引用本文： | 张化光, 季策, 张铁岩. 多时滞Hopfield神经网络的鲁棒稳定性分析及吸引域的估计. 自动化学报, 2006, 32(1): 84-90. |
| |
| 作者姓名： | 张化光 季策 张铁岩 |
| |
| 作者单位： | 1.Key Laboratory of Process Industry Automation, Ministry of Education,Northeastern University, Shenyang 110004 |
| |
| 基金项目： | Supported by the National Natural Science Foundation of P.R.China （60274017, 60572070, 60325311）, the Natural Science Foundation of Liaoning Province （20022030） |
| |
| 摘 要： | The robust stability of a class of Hopfield neural networks with multiple delays and parameter perturbations is analyzed. The sufficient conditions for the global robust stability of equilibrium point are given by way of constructing a suitable Lyapunov functional. The conditions take the form of linear matrix inequality (LMI), so they are computable and verifiable efficiently. Furthermore, all the results are obtained without assuming the differentiability and monotonicity of activation functions. From the viewpoint of system analysis, our results provide sufficient conditions for the global robust stability in a manner that they specify the size of perturbation that Hopfield neural networks can endure when the structure of the network is given. On the other hand, from the viewpoint of system synthesis, our results can answer how to choose the parameters of neural networks to endure a given perturbation.
|
| 关 键 词： | Hopfield neural networks multiple delays parameter perturbations robust stability Lyapunov functional linear matrix inequality |
| 收稿时间： | 2004-03-26 |
| 修稿时间： | 2005-10-14 |
Analysis for Robust Stability of Hopfield Neural Networks with Multiple Delays |
| |
| ZHANG Hua-Guang JI Ce, ZHANG Tie-Yan, . Analysis for Robust Stability of Hopfield Neural Networks with Multiple Delays. ACTA AUTOMATICA SINICA, 2006, 32(1): 84-90. |
| |
| Authors: | ZHANG Hua-Guang JI Ce ZHANG Tie-Yan |
| |
| Affiliation: | 1. Key Laboratory of Process Industry Automation, Ministry of Education,Northeastern University, Shenyang 110004 |
| |
| Abstract: | The robust stability of a class of Hopfield neural networks with multiple delays and parameter perturbations is analyzed. The sufficient conditions for the global robust stability of equilibrium point are given by way of constructing a suitable Lyapunov functional. The conditions take the form of linear matrix inequality (LMI), so they are computable and verifiable efficiently. Furthermore, all the results are obtained without assuming the differentiability and monotonicity of activation functions. From the viewpoint of system analysis, our results provide sufficient conditions for the global robust stability in a manner that they specify the size of perturbation that Hopfield neural networks can endure when the structure of the network is given. On the other hand, from the viewpoint of system synthesis, our results can answer how to choose the parameters of neural networks to endure a given perturbation. |
| |
| Keywords: | Hoptield neural networks multiple delays parameter perturbations robust stability Lyapunov functional linear matrix inequality |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
