离散时间型复值神经网络的全局指数周期性 |
| |
引用本文: | 胡进,宋乾坤.离散时间型复值神经网络的全局指数周期性[J].应用数学和力学,2013,34(9):929-940. |
| |
作者姓名: | 胡进 宋乾坤 |
| |
作者单位: | 重庆交通大学 理学院, 重庆 400074 |
| |
基金项目: | 国家自然科学基金资助项目(61273021); 重庆市自然科学基金(重点)资助项目(cstc2013jjB40008) |
| |
摘 要: | 复值神经网络是神经网络的一个分支,也是最近几年快速发展的一个领域,在图像处理、模式识别、联想记忆等方面有广泛的应用.目前,对于复值神经网络动力学方面的研究主要集中在稳定性上,对于离散时间型复值神经网络周期性的研究还几乎没有.首先将连续时间型复值神经网络模型离散化得到离散时间型复值神经网络模型,然后利用M矩阵理论、不等式技巧和Lyapunov方法,获得了全局指数周期性的一个充分条件,最后给出的具有仿真的数值例子验证了获得结果的有效性.
|
关 键 词: | 离散 复值神经网络 时滞 全局指数周期性 |
收稿时间: | 2013-06-13 |
Global Exponential Periodicity of Discrete-Time Complex-Valued Neural Networks With Time-Delays |
| |
Affiliation: | School of Science, Chongqing Jiaotong University, Chongqing 400074, P.R.China |
| |
Abstract: | Since the last decade, complex-valued neural networks have been rapidly developed and applied in various research areas, but few research has been done on the periodicity on discrete-time complex-valued neural networks.The periodicity of discrete-time complex-valued neural networks with time-delays was investigated.With the discretization technique, the discrete-time analogue of the continuous-time system with periodic input was formulated, and a sufficient condition for checking the global exponential periodicity of the considered neural networks was obtained. Numeric simulation verifieds validity of the analysis. |
| |
Keywords: | |
|
| 点击此处可从《应用数学和力学》浏览原始摘要信息 |
|
点击此处可从《应用数学和力学》下载全文 |
|