Circuit Implementation and Quasi-Stabilization of Delayed Inertial Memristor-Based Neural Networks

被引：7
|
作者：
Xin, Youming [1 ]
Cheng, Zunshui [1 ]
Cao, Jinde [2 ,3 ,4 ]
Rutkowski, Leszek [5 ,6 ]
Wang, Yaning [1 ]
机构：
[1] Qingdao Univ Sci & Technol, Sch Math & Phys, Qingdao 266061, Peoples R China
[2] Southeast Univ, Frontiers Sci Ctr Mobile Informat Commun & Secur, Sch Math, Nanjing 210096, Peoples R China
[3] Purple Mt Labs, Nanjing 211111, Peoples R China
[4] Yonsei Univ, Yonsei Frontier Lab, Seoul 03722, South Korea
[5] Polish Acad Sci, Syst Res Inst, PL-01447 Warsaw, Poland
[6] AGH Univ Sci & Technol, Inst Comp Sci, PL-30059 Krakow, Poland
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2024年 / 35卷 / 01期
关键词：
Neural networks; Memristors; Mathematical models; Stability criteria; Circuit stability; Linear matrix inequalities; Integrated circuit modeling; Continuous model; inertial neural networks; matrix measure method; memristor; quasi-stability; EXPONENTIAL SYNCHRONIZATION; STABILITY ANALYSIS;
D O I：
10.1109/TNNLS.2022.3173620
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this brief, we consider the stability of inertial memristor-based neural networks with time-varying delays. First, delayed inertial memristor-based neural networks are modeled as continuous systems in the flux-current-voltage-time domain via the mathematical model of Hewlett-Packard (HP) memristor. Then, they are reduced to delayed inertial neural networks with interval parameters uncertainties. Quasi-equilibrium points and quasi-stability are proposed. Quasi-stability criteria of delayed inertial memristor-based neural networks are obtained by matrix measure method, the Halanay inequality, and uncertainty technologies. In the end, a numerical example is provided to show the validity of our results.
引用
收藏
页码：1394 / 1400
页数：7
相关论文
共 50 条
  • [41] Memristor-Based Binarized Spiking Neural Networks
    Eshraghian, Jason K.
    Wang, Xinxin
    Lu, Wei D.
    IEEE NANOTECHNOLOGY MAGAZINE, 2022, 16 (02) : 14 - 23
  • [42] Offline Training for Memristor-based Neural Networks
    Boquet, Guillem
    Macias, Edwar
    Morell, Antoni
    Serrano, Javier
    Miranda, Enrique
    Lopez Vicario, Jose
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 1547 - 1551
  • [43] Dynamic behaviors of memristor-based delayed recurrent networks
    Wen, Shiping
    Zeng, Zhigang
    Huang, Tingwen
    NEURAL COMPUTING & APPLICATIONS, 2013, 23 (3-4): : 815 - 821
  • [44] Dynamic behaviors of memristor-based delayed recurrent networks
    Shiping Wen
    Zhigang Zeng
    Tingwen Huang
    Neural Computing and Applications, 2013, 23 : 815 - 821
  • [45] Exponential stabilization of memristor-based neural networks with unbounded time-varying delays
    Jiemei Zhao
    Science China Information Sciences, 2021, 64
  • [46] Exponential stabilization of memristor-based neural networks with unbounded time-varying delays
    Jiemei ZHAO
    ScienceChina(InformationSciences), 2021, 64 (08) : 247 - 249
  • [47] Reliable stabilization for memristor-based recurrent neural networks with time-varying delays
    Mathiyalagan, K.
    Anbuvithya, R.
    Sakthivel, R.
    Park, Ju H.
    Prakash, P.
    NEUROCOMPUTING, 2015, 153 : 140 - 147
  • [48] Global Stabilization of Fractional-Order Memristor-Based Neural Networks With Time Delay
    Jia, Jia
    Huang, Xia
    Li, Yuxia
    Cao, Jinde
    Alsaedi, Ahmed
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (03) : 997 - 1009
  • [49] Robust Stabilization of Memristor-based Coupled Neural Networks with Time-varying Delays
    Qianhua Fu
    Jingye Cai
    Shouming Zhong
    International Journal of Control, Automation and Systems, 2019, 17 : 2666 - 2676
  • [50] Exponential stabilization of memristor-based neural networks with unbounded time-varying delays
    Zhao, Jiemei
    SCIENCE CHINA-INFORMATION SCIENCES, 2021, 64 (08)
12345