首页 | 本学科首页   官方微博 | 高级检索  
     

忆阻突触耦合Hopfield神经网络的初值敏感动力学
引用本文:陈墨, 陈成杰, 包伯成, 徐权. 忆阻突触耦合Hopfield神经网络的初值敏感动力学[J]. 电子与信息学报, 2020, 42(4): 870-877. doi: 10.11999/JEIT190858
作者姓名:陈墨  陈成杰  包伯成  徐权
作者单位:常州大学信息科学与工程学院 常州 213164
基金项目:国家自然科学基金(51777016, 61801054, 61601062),江苏省研究生科研与实践创新计划项目(KYCX19_1767)
摘    要:该文报道了3神经元Hopfield神经网络(HNN)在电磁感应电流作用下的初值敏感动力学。利用非理想忆阻突触,模拟由两个相邻神经元膜电位之差引起的电磁感应电流,构建了一种简单的4维忆阻Hopfield神经网络模型。借助理论分析和数值仿真,分析了不同忆阻突触耦合强度下的复杂动力学行为,揭示了与状态初值密切相关的特殊动力学行为。最后,设计了该忆阻HNN的模拟等效实现电路,并由PSIM电路仿真验证了MATLAB数值仿真的正确性。

关 键 词:非理想忆阻突触   Hopfield神经网络   状态初值   数值仿真
收稿时间:2019-11-01
修稿时间:2020-01-20

Initial Sensitive Dynamics in Memristor Synapse-coupled Hopfield Neural Network
Mo CHEN, Chengjie CHEN, Bocheng BAO, Quan XU. Initial Sensitive Dynamics in Memristor Synapse-coupled Hopfield Neural Network[J]. Journal of Electronics & Information Technology, 2020, 42(4): 870-877. doi: 10.11999/JEIT190858
Authors:Mo CHEN  Chengjie CHEN  Bocheng BAO  Quan XU
Affiliation:School of Information Science and Engineering, Changzhou University, Changzhou 213164, China
Abstract:The initial sensitive dynamics in a Hopfield Neural Network (HNN) with three neurons under the action of electromagnetic induction current is reported. A simple 4-D memristive HNN is constructed by using a non-ideal memristor synapse to imitate the electromagnetic induction current caused by membrane potential difference between two adjacent neurons. By means of theoretical analyses and numerical simulations, the complex dynamical behaviors under different coupling strengths of the memristor synapse are researched, and special phenomena closely related to the initial values are revealed. Finally, the analog equivalent realization circuit of the memristive HNN model is designed, and the correctness of MATLAB numerical simulation is verified by PSIM circuit simulations.
Keywords:Non-ideal memristor synapse  Hopfield Neural Network (HNN)  Initial condition  Numerical simulation
点击此处可从《电子与信息学报》浏览原始摘要信息
点击此处可从《电子与信息学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号