Initial Sensitive Dynamics in Memristor Synapse-coupled Hopfield Neural Network

被引：8

作者：

Chen, Mo ^{[1
]}

Chen Chengjie ^{[1
]}

Bao Bocheng ^{[1
]}

Xu Quan ^{[1
]}

机构：

[1] Changzhou Univ, Sch Informat Sci & Engn, Changzhou 213164, Jiangsu, Peoples R China

来源：

JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY | 2020年 / 42卷 / 04期

基金：

中国国家自然科学基金;

关键词：

Non-ideal memristor synapse; Hopfield Neural Network (HNN); Initial condition; Numerical simulation; MULTIPLE ATTRACTORS; CHAOTIC DYNAMICS; NEURONS; BRAIN;

D O I：

10.11999/JEIT190858

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：870 / 877

页数：8

共 23 条

[1] Dynamical Effects of Neuron Activation Gradient on Hopfield Neural Network: Numerical Analyses and Hardware Experiments [J].

Bao, Bocheng ;

Chen, Chengjie ;

Bao, Han ;

Zhang, Xi ;

Xu, Quan ;

Chen, Mo .

INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2019, 29 (04)

[2] Coexisting Behaviors of Asymmetric Attractors in Hyperbolic-Type Memristor based Hopfield Neural Network [J].

Bao, Bocheng ;

Qian, Hui ;

Xu, Quan ;

Chen, Mo ;

Wang, Jiang ;

Yu, Yajuan .

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2017, 11

[3] Hidden Bursting Firings and Bifurcation Mechanisms in Memristive Neuron Model With Threshold Electromagnetic Induction [J].

Bao, Han ;

Hu, Aihuang ;

Liu, Wenbo ;

Bao, Bocheng .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (02) :502-511

[4] Coexisting multiple firing patterns in two adjacent neurons coupled by memristive electromagnetic induction [J].

Bao, Han ;

Liu, Wenbo ;

Hu, Aihuang .

NONLINEAR DYNAMICS, 2019, 95 (01) :43-56

[5] Dynamic models of large-scale brain activity [J].

Breakspear, Michael .

NATURE NEUROSCIENCE, 2017, 20 (03) :340-352

[6] Non-ideal memristor synapse-coupled bi-neuron Hopfield neural network: Numerical simulations and breadboard experiments [J].

Chen, Chengjie ;

Bao, Han ;

Chen, Mo ;

Xu, Quan ;

Bao, Bocheng .

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS, 2019, 111

[7] Coexisting multi-stable patterns in memristor synapse-coupled Hopfield neural network with two neurons [J].

Chen, Chengjie ;

Chen, Jingqi ;

Bao, Han ;

Chen, Mo ;

Bao, Bocheng .

NONLINEAR DYNAMICS, 2019, 95 (04) :3385-3399

[8] Hidden chaotic sets in a Hopfield neural system [J].

Danca, Marius-F. ;

Kuznetsov, Nikolay .

CHAOS SOLITONS & FRACTALS, 2017, 103 :144-150

[9]

Fotsin HB., 2019, INT J DYNAM CONTROL, V7, P823, DOI DOI 10.1007/S40435-019-00509-W

[10] Robust Exponential Memory in Hopfield Networks [J].

Hillar, Christopher J. ;

Tran, Ngoc M. .

JOURNAL OF MATHEMATICAL NEUROSCIENCE, 2018, 8

← 1 2 3 →