Boui A Boya Bertrand Frederick, Ramakrishnan Balamurali, Effa Joseph Yves, Kengne Jacques, Rajagopal Karthikeyan
Unité de Recherche d'Automatique et d'Informatique Appliquée (UR-AIA), IUT-FV Bandjoun, University of Dschang, P.O. Box 134, Bandjoun, Cameroon.
Unité de Recherche de Matière Condensée, d'Electronique et de Traitement Du Signal (UR-MACETS), Department of Physics, University of Dschang, PO Box 67, Dschang, Cameroon.
Heliyon. 2023 Jan 20;9(2):e13034. doi: 10.1016/j.heliyon.2023.e13034. eCollection 2023 Feb.
This work studies the dynamics of a three dimensional Hopfield neural network focusing on the impact of bias terms. In the presence of bias terms, the models displays an odd symmetry and experiences typical behaviors including period doubling, spontaneous symmetry breaking, merging crisis, bursting oscillation, coexisting attractors and coexisting period-doubling reversals as well. Multistability control is investigated by employing the linear augmentation feedback strategy. We numerically prove that the multistable neural system can be adjusted to experience only a single attractor behavior when the coupling coefficient is gradually monitored. Experimental results from a microcontroller based realization of the underlined neural system are consistent with the theoretical analysis.
这项工作研究了三维霍普菲尔德神经网络的动力学，重点关注偏置项的影响。在存在偏置项的情况下，模型呈现出奇对称性，并表现出典型行为，包括倍周期分岔、自发对称性破缺、合并危机、爆发振荡、共存吸引子以及共存倍周期反转。通过采用线性增强反馈策略来研究多稳定性控制。我们通过数值证明，当耦合系数逐渐受到监测时，多稳定神经系统可以被调整为仅呈现单一吸引子行为。基于微控制器实现的上述神经网络系统的实验结果与理论分析一致。
