| 时滞递归神经网络中神经抑制的作用 |
| |
| 引用本文： | 王占山,张化光. 时滞递归神经网络中神经抑制的作用[J]. 物理学报, 2006, 55(11): 5674-5680 |
| |
| 作者姓名： | 王占山 张化光 |
| |
| 作者单位： | (1)东北大学信息科学与工程学院，沈阳 110004; (2)东北大学信息科学与工程学院，沈阳 110004;沈阳理工大学信息学院，沈阳 110168 |
| |
| 基金项目： | 国家自然科学基金;教育部长江学者和创新团队发展计划 |
| |
| 摘 要： | 研究了具有时滞的二阶递归神经网络中抑制自连接的作用，给出了时滞依赖的全局渐近稳定的充分判据.研究结果表明：抑制自连接可镇定不稳定的网络并使其渐近稳定；抑制自连接的镇定作用受到网络传输时滞的制约.仿真示例验证了结果的有效性.关键词：递归神经网络时滞抑制神经元动态行为
|
| 关 键 词： | 递归神经网络 时滞 抑制神经元 动态行为 |
| 文章编号： | 1000-3290/2006/55(11)/5674-07 |
| 收稿时间： | 2005-12-23 |
| 修稿时间： | 2005-12-232006-03-28 |
The role of inhibitory neuron in a delayed neural network |
| |
| Wang Zhan-Shan,Zhang Hua-Guang. The role of inhibitory neuron in a delayed neural network[J]. Acta Physica Sinica, 2006, 55(11): 5674-5680 |
| |
| Authors: | Wang Zhan-Shan Zhang Hua-Guang |
| |
| Affiliation: | 1. School of Information Science and Engineering, Northeastern University, Shenyang 110004, China; 2. School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110168, China |
| |
| Abstract: | The role of inhibitory self-connection in a second order recurrent neural network with delays has been investigated. A sufficient condition is proposed to guarantee the global asymptotical stability of the equilibrium point for the delayed neural network. The results indicate that an unstable neural network without inhibitory interconnections can be asymptotically stabilized to a unique equilibrium point via embedding inhibitory self-connections with proper strengths, and the role of inhibitory self-connections will be restricted by the magnitude of transmission delays. Two simulation examples are used to show the effectiveness of the obtained result. |
| |
| Keywords: | recurrent neural network delay inhibitory neuron dynamics |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《物理学报》浏览原始摘要信息 |
|
点击此处可从《物理学报》下载免费的PDF全文 |
