时滞忆阻回归神经网络在周期间歇控制下的指数同步（英文）  

Exponential synchronization of delayed memristor-based recurrent neural networks via periodically intermittent control

作　　者：刘梅 蒋海军[1] 胡成[1] LIU Mei;JIANG Haijun;HU Cheng(College of Mathematics and System Sciences,Xinjiang University,Urumqi 830046,Chin)

机构地区：[1]新疆大学数学与系统科学学院,乌鲁木齐830046

出　　处：《黑龙江大学自然科学学报》2018年第3期260-270,共11页Journal of Natural Science of Heilongjiang University

基　　金：Supported by the National Natural Science Foundation of China(61473244;61563048;11402223)

摘　　要：忆阻神经系统是制造人工大脑的一个很好的选项。研究一类带有时变时滞的忆阻回归神经网络在周期间歇控制下的指数同步。采用控制理论和非光滑分析处理右端不连续的忆阻回归神经网络,得到一些确保两个忆阻回归神经网络在周期间歇控制下指数同步的新条件。本结果很容易验证,并延伸了已有的结果。数值模拟验证了所得结果的有效性。Memristive neuromorphic system is a very good candidate for creating artificial brain.The exponential synchronization for a class of memristive recurrent neural networks with time-varying delays is studied via periodically intermittent control.Control theory and nonsmooth analysis are adopted to handle memristor-based recurrent neural networks with discontinuous right-hand side.Several new conditions ensuring exponential synchronization of two memristor-based recurrent neural networks are derived via periodically intermittent control.The proposed results here are easy to be verified,and they also extend the previous publications.Numerical simulations illustrate the effectiveness of the obtained results.

关 键 词：回归神经网络 指数同步 时变时滞 忆阻 周期间歇控制 

分 类 号：O175.7[理学—数学]