Effects of Low and High Neuron Activation Gradients on the Dynamics of a Simple 3D Hopfield Neural Network

被引:24
|
作者
Isaac, Sami Doubla [1 ,2 ]
Njitacke, Z. Tabekoueng [3 ]
Kengne, J. [1 ]
机构
[1] Univ Dschang, Dept Elect Engn, IUT PV Bandjoun, Unite Rech Automat & Informat Appl URAIA, Dschang, Cameroon
[2] Univ Dschang, Dept Phys, Unite Rech Matiere Condensee Elect & Traitement S, POB 67, Dschang, Cameroon
[3] Univ Buea, Dept Elect & Elect Engn, Coll Technol COT, POB 63, Buea, Cameroon
来源
关键词
Hopfield neuronal network (HNN); activation gradient; electrical activity; multistability; PSpice simulation; COEXISTING MULTIPLE ATTRACTORS; SMOOTHLY ADJUSTABLE SYMMETRY; NUMERICAL-ANALYSES; JERK SYSTEM; NONLINEARITY CHAOS; STRANGE ATTRACTORS; COMPLEX DYNAMICS; HYPERCHAOS; CIRCUIT; MODEL;
D O I
10.1142/S021812742050159X
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
In this paper, the effects of low and fast response speeds of neuron activation gradient of a simple 3D Hopfield neural network are explored. It consists of analyzing the effects of low and high neuron activation gradients on the dynamics. By considering an imbalance of the neuron activation gradients, different electrical activities are induced in the network, which enable the occurrence of several nonlinear behaviors. The significant sensitivity of nontrivial equilibrium points to the activation gradients of the first and second neurons relative to that of the third neuron is reported. The dynamical analysis of the model is done in a wide range of the activation gradient of the second neuron. In this range, the model presents areas of periodic behavior, chaotic behavior and periodic window behavior through complex bifurcations. Interesting behaviors such as the coexistences of two, four, six and eight disconnected attractors, as well as the phenomenon of coexisting antimonotonicity, are reported. These singular results are obtained by using nonlinear dynamics analysis tools such as bifurcation diagrams and largest Lyapunov exponents, phase portraits, power spectra and basins of attraction. Finally, some analog results obtained from PSpice-based simulations further verify the numerical results.
引用
收藏
页数:26
相关论文
共 50 条
  • [41] 3D Object Detection by 3D Geometric Information and Deep Neural Network for Avoiding Unknown Low-height Obstacles
    Amemiya T.
    Tasaki T.
    IEEJ Transactions on Electronics, Information and Systems, 2021, 141 (12) : 1256 - 1264
  • [42] 3D Convolutional Neural Network for Action Recognition
    Zhang, Junhui
    Chen, Li
    Tian, Jing
    COMPUTER VISION, PT I, 2017, 771 : 600 - 607
  • [43] A 3D neural network for moving microorganism extraction
    Zhou, Fang
    Wu, Tin-Yu
    Liu, Jun
    Wang, Bing
    Obaidat, Mohammad S.
    NEURAL COMPUTING & APPLICATIONS, 2018, 30 (01): : 57 - 67
  • [44] A 3D shape classifier with neural network supervision
    Liu, Zhenbao
    Mitani, Jun
    Fukui, Yukio
    Nishihara, Seiichi
    INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2010, 38 (1-3) : 134 - 143
  • [45] Binocular 3D reconstruction based on neural network
    Lin, MX
    Zhao, YR
    Guan, ZG
    Ding, FH
    Xu, QX
    Wang, XH
    ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 2, PROCEEDINGS, 2005, 3497 : 765 - 771
  • [46] Neural network architecture for 3D object representation
    Cretu, AM
    Petriu, EM
    Patry, GG
    2ND IEEE INTERNATIONAL WORKSHOP ON HAPTIC, AUDIO AND VISUAL ENVIRONMENTS AND THEIR APPLICATIONS - HAVE 2003, 2003, : 31 - 36
  • [47] 3D reconstruction approach based on neural network
    Hu, Haifeng
    Yang, Zhi
    ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 2, PROCEEDINGS, 2007, 4492 : 630 - +
  • [48] Neural network for 3D point clouds alignment
    Voronin, Sergei
    Vasilyev, Alexander
    Kober, Vitaly
    Makovetskii, Artyom
    Voronin, Aleksei
    Zhernov, Dmitrii
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XLV, 2022, 12226
  • [49] Monolithic 3D stacking for neural network acceleration
    Bokyung Kim
    Hai Li
    Nature Electronics, 2023, 6 : 937 - 938
  • [50] A rigorous verification of chaos in a 3D neural network
    Yang, Fangyan
    Zhou, Ping
    Li, Qingdu
    2006 INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS PROCEEDINGS, VOLS 1-4: VOL 1: SIGNAL PROCESSING, 2006, : 2111 - +