Tipping prediction of a class of large-scale radial-ring neural networks

被引:0
作者
Lu, Yunxiang [1 ]
Xiao, Min [1 ]
Wu, Xiaoqun [2 ]
Karimi, Hamid Reza [3 ]
Xie, Xiangpeng [4 ]
Cao, Jinde [5 ]
Zheng, Wei Xing [6 ]
机构
[1] Nanjing Univ Posts & Telecommun, Coll Automat & Coll Artificial Intelligence, Nanjing 210023, Peoples R China
[2] Shen Zhen Univ, Coll Comp Sci & Software Engn, Shen Zhen 518060, Peoples R China
[3] Politecn Milan, Dept Mech Engn, I-20159 Milan, Italy
[4] Nanjing Univ Posts & Telecommun, Inst Adv Technol, Nanjing 210023, Peoples R China
[5] Southeast Univ, Sch Math, Nanjing 210096, Peoples R China
[6] Western Sydney Univ, Sch Comp Data & Math Sci, Sydney, NSW 2751, Australia
基金
中国国家自然科学基金;
关键词
Neural networks; Tipping; Hopf bifurcation; Large-scale; Coates' flow graph; BIFURCATION-ANALYSIS; STABILITY; DYNAMICS; ELEMENTS;
D O I
10.1016/j.neunet.2024.106820
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Understanding the emergence and evolution of collective dynamics in large-scale neural networks remains a complex challenge. This paper seeks to address this gap by applying dynamical systems theory, with a particular focus on tipping mechanisms. First, we introduce a novel ( n + mn )-scale radial-ring neural network and employ Coates' flow graph topological approach to derive the characteristic equation of the linearized network. Second, through deriving stability conditions and predicting the tipping point using an algebraic approach based on the integral element concept, we identify critical factors such as the synaptic transmission delay, the self-feedback coefficient, and the network topology. Finally, we validate the methodology's effectiveness in predicting the tipping point. The findings reveal that increased synaptic transmission delay can induce and amplify periodic oscillations. Additionally, the self-feedback coefficient and the network topology influence the onset of tipping points. Moreover, the selection of activation function impacts both the number of equilibrium solutions and the convergence speed of the neural network. Lastly, we demonstrate that the proposed large-scale radial-ring neural network exhibits stronger robustness compared to lower-scale networks with a single topology. The results provide a comprehensive depiction of the dynamics observed in large-scale neural networks under the influence of various factor combinations.
引用
收藏
页数:16
相关论文
共 56 条
[21]   Multi-node knowledge graph assisted distributed fault detection for large-scale industrial processes based on graph attention network and bidirectional LSTMs [J].
Li, Qing ;
Wang, Yangfan ;
Dong, Jie ;
Zhang, Chi ;
Peng, Kaixiang .
NEURAL NETWORKS, 2024, 173
[22]   A Novel Calibration System for Robot Arm via an Open Dataset and a Learning Perspective [J].
Li, Zhibin ;
Li, Shuai ;
Francis, Adam ;
Luo, Xin .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2022, 69 (12) :5169-5173
[23]   Diversified Regularization Enhanced Training for Effective Manipulator Calibration [J].
Li, Zhibin ;
Li, Shuai ;
Bamasag, Omaimah Omar ;
Alhothali, Areej ;
Luo, Xin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (11) :8778-8790
[24]   An overview of calibration technology of industrial robots [J].
Li, Zhibin ;
Li, Shuai ;
Luo, Xin .
IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2021, 8 (01) :23-36
[25]   Fuzzy-Model-Based Lateral Control for Networked Autonomous Vehicle Systems Under Hybrid Cyber-Attacks [J].
Lian, Zhi ;
Shi, Peng ;
Lim, Cheng-Chew ;
Yuan, Xin .
IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (04) :2600-2609
[26]   Neural Network-Based Information Transfer for Dynamic Optimization [J].
Liu, Xiao-Fang ;
Zhan, Zhi-Hui ;
Gu, Tian-Long ;
Kwong, Sam ;
Lu, Zhenyu ;
Duh, Henry Been-Lim ;
Zhang, Jun .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (05) :1557-1570
[27]   Spatiotemporal Evolution of Large-Scale Bidirectional Associative Memory Neural Networks With Diffusion and Delays [J].
Lu, Yunxiang ;
Xiao, Min ;
Liang, Jinling ;
Chen, Jing ;
Lin, Jinxing ;
Wang, Zhengxin ;
Cao, Jinde .
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, 54 (03) :1388-1400
[28]   Early warning of tipping in a chemical model with cross-diffusion via spatiotemporal pattern formation and transition [J].
Lu, Yunxiang ;
Xiao, Min ;
Huang, Chengdai ;
Cheng, Zunshui ;
Wang, Zhengxin ;
Cao, Jinde .
CHAOS, 2023, 33 (07)
[29]   Stability and Bifurcation Exploration of Delayed Neural Networks With Radial-Ring Configuration and Bidirectional Coupling [J].
Lu, Yunxiang ;
Xiao, Min ;
He, Jiajin ;
Wang, Zhengxin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (08) :10326-10337
[30]   Population dynamics: Variance and the sigmoid activation function [J].
Marreiros, Andre C. ;
Daunizeau, Jean ;
Kiebel, Stefan J. ;
Friston, Karl J. .
NEUROIMAGE, 2008, 42 (01) :147-157