| Hopfield神经网络在扰动情况下的鲁棒性 |
| |
| 引用本文： | 李佰成,李德昌,廉诚雪,陈殿友. Hopfield神经网络在扰动情况下的鲁棒性[J]. 吉林大学学报(理学版), 2006, 44(6): 54-58 |
| |
| 作者姓名： | 李佰成 李德昌 廉诚雪 陈殿友 |
| |
| 作者单位： | 1. 吉林大学 软件学院, 长春 130012; 2. 吉林大学 计算机科学与技术学院, 长春 130012; 3. 上海交通大学 应用数学系， 上海 200030； 4. 吉林大学 数学学院, 长春 130012 |
| |
| 摘 要： | Hopfield神经网络在工程领域中应用广泛, 但在具体的实现过程中往往存在着扰动和时滞, 这些因素的存在影响了神经网络的动态性能, 并有可能导致网络失稳. 通过建立模型, 讨论了时滞递归神经网络的鲁棒性, 给出了有效的判定条件, 推广了有关文献中的结果.
|
| 关 键 词： | Hopfield神经网络 鲁棒性 故障模型 时滞网络 |
| 收稿时间： | 2006-05-31 |
Robustness of Hopfield Neural Networks in Discrete Perturbation |
| |
| LI Bai cheng,LI De chang,LIAN Cheng xue,CHEN Dian you. Robustness of Hopfield Neural Networks in Discrete Perturbation[J]. Journal of Jilin University: Sci Ed, 2006, 44(6): 54-58 |
| |
| Authors: | LI Bai cheng LI De chang LIAN Cheng xue CHEN Dian you |
| |
| Affiliation: | 1. College of Software, Jilin University, Changchun 130012, China; 2. College of Computer Science and Technology, Jilin University, Changchun 130012, China; 3. Department of Application Mathematics, Shanghai Jiaotong University, Shanghai 200030, China;4. College of Mathematics, Jilin University, Changchun 130012, China |
| |
| Abstract: | Hopfield neural networks are widely applied in picture identification and engineering field, but there are parameter perturbations and time delay in the neural network when it is implemented with the hardware. These factors will badly influence the dynamic performance of the neural network and even cause instability of the network. This paper discusses the robustness of neural networks with time delay by building a model. And the fairly general and easily verifiable criterion is presented. |
| |
| Keywords: | Hopfield neural networks robustness fault model time delayed networks |
|
| 点击此处可从《吉林大学学报(理学版)》浏览原始摘要信息 |
|
点击此处可从《吉林大学学报(理学版)》下载全文 |
|
