[1]李梁晨,甘勤涛,蔺佳哲.参数扰动下时滞忆阻神经网络的Lagrange稳定性[J].东南大学学报(自然科学版),2021,51(3):511-520.[doi:10.3969/j.issn.1001-0505.2021.03.021]
 Li Liangchen,Gan Qintao,Lin Jiazhe.Lagrange stability of delayed memristive neural networks with parameter perturbations[J].Journal of Southeast University (Natural Science Edition),2021,51(3):511-520.[doi:10.3969/j.issn.1001-0505.2021.03.021]
点击复制

参数扰动下时滞忆阻神经网络的Lagrange稳定性()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
51
期数:
2021年第3期
页码:
511-520
栏目:
自动化
出版日期:
2021-05-20

文章信息/Info

Title:
Lagrange stability of delayed memristive neural networks with parameter perturbations
作者:
李梁晨12甘勤涛1蔺佳哲13
1陆军工程大学石家庄校区, 石家庄 050000; 2盲信号处理国家级重点实验室, 成都 610000; 3中国空气动力研究与发展中心计算空气动力研究所, 绵阳 621000
Author(s):
Li Liangchen12 Gan Qintao2 Lin Jiazhe3
1Army Engineering University Shijiazhuang Campus, Shijiazhuang 050003, China
2National Key Laboratory of Blind Signal Processing, Chengdu 610000, China
3Computational Aerodynamics Research Institute, China Aerodynamics Research and Development Center, Mianyang 621000, China
关键词:
忆阻神经网络 Lagrange稳定性 参数扰动 线性矩阵不等式
Keywords:
memristive neutral networks Lagrange stability parameter perturbations linear matrix inequalities
分类号:
TP183
DOI:
10.3969/j.issn.1001-0505.2021.03.021
摘要:
根据忆阻器物理特性,建立了一类荷控忆阻神经网络模型,模型中忆阻器的记忆特性被保留.针对实际忆阻器阻值与理想模型存在差异造成忆阻神经网络中参数不确定的问题,研究参数扰动下时滞忆阻神经网络的Lagrange稳定性.将模型重构为双重扰动形式以处理忆阻器忆阻值变化造成的模型中的参数变化.通过构造Lyapunov函数和应用线性矩阵不等式方法,以线性矩阵不等式形式给出了网络Lagrange稳定的充分条件,并给出了相应的全局指数吸引集的估计.最后,通过与现有模型的仿真结果对比,展示了所建立模型的优势.利用数值算例展示了参数扰动造成忆阻神经网络周期解的偏移,说明了研究参数扰动对忆阻神经网络稳定性影响的必要性,并验证了理论所得稳定性判据的可行性.
Abstract:
Based on the physical property of memristors, a kind of charge controlled memristive neural network model is established. Considering the effects of parameter uncertainties caused by the difference between the actual memristance and the ideal model, the Lagrange stability of the delayed memristive neural network with parameter perturbations is investigated. To handle the parameters variety in the model, the model is reconstructed to a form with double parameter perturbations. By using Lyapunov functions and linear matrix inequality technique, a sufficient condition is given to ascertain the network to be stable in Lagrange sense. Meanwhile, the estimation of the corresponding globally attractive set is given. Compared with the simulation results of the existing models, the advantages of the proposed model are illustrated. Also, a numerical example reveals the shift of the periodic solution of the memristive neural network caused by parameter perturbations, which shows the necessity of studying the effects of parameter perturbations on the stability of the memristive neural network, and the feasibility of the stability criterion obtained is verified.

参考文献/References:

[1] Chua L. Memristor—The missing circuit element[J].IEEE Transactions on Circuit Theory, 1971, 18(5): 507-519. DOI:10.1109/TCT.1971.1083337.
[2] Chua L. Everything you wish to know about memristors but are afraid to ask[J]. Radioengineering, 2015, 24(2): 319-368.
[3] Strukov D B, Snider G S, Stewart D R, et al. The missing memristor found[J].Nature, 2008, 453(7191): 80-83. DOI:10.1038/nature06932.
[4] Borghetti J, Snider G S, Kuekes P J, et al. ‘Memristive’ switches enable ‘stateful’ logic operations via material implication[J].Nature, 2010, 464(7290): 873-876. DOI:10.1038/nature08940.
[5] Hu J, Wang J. Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays[C]//The 2010 International Joint Conference on Neural Networks(IJCNN). Barcelona, Spain, 2010: 1-8. DOI:10.1109/IJCNN.2010.5596359.
[6] Duan S K, Hu X F, Wang L D, et al. Hybrid memristor/RTD structure-based cellular neural networks with applications in image processing[J].Neural Computing and Applications, 2014, 25(2): 291-296. DOI:10.1007/s00521-013-1484-x.
[7] Pershin Y V, di Ventra M. Experimental demonstration of associative memory with memristive neural networks[J].Neural Networks, 2010, 23(7): 881-886. DOI:10.1016/j.neunet.2010.05.001.
[8] Wang X, Li C D, Huang T W, et al. A weakly connected memristive neural network for associative memory[J].Neural Processing Letters, 2014, 40(3): 275-288. DOI:10.1007/s11063-013-9328-3.
[9] Wu A L, Wen S P, Zeng Z G. Synchronization control of a class of memristor-based recurrent neural networks[J].Information Sciences, 2012, 183(1): 106-116. DOI:10.1016/j.ins.2011.07.044.
[10] Wang F, Chen Y L, Liu M C. Pth moment exponential stability of stochastic memristor-based bidirectional associative memory(BAM)neural networks with time delays[J].Neural Networks, 2018, 98: 192-202. DOI:10.1016/j.neunet.2017.11.007.
[11] Yang W G, Yu W W, Ji D C, et al. Global exponential stability and lag synchronization for delayed memristive fuzzy Cohen-Grossberg BAM neural networks with impulses[J].Neural Networks, 2018, 98: 122-153. DOI:10.1016/j.neunet.2017.11.001.
[12] Yuan M M, Wang W P, Luo X, et al. Finite-time anti-synchronization of memristive stochastic BAM neural networks with probabilistic time-varying delays[J].Chaos, Solitons & Fractals, 2018, 113: 244-260. DOI:10.1016/j.chaos.2018.06.013.
[13] Yang Z Y, Luo B, Liu D R, et al. Pinning synchronization of memristor-based neural networks with time-varying delays[J].Neural Networks, 2017, 93: 143-151. DOI:10.1016/j.neunet.2017.05.003.
[14] Chen W Z, Huang Y L, Ren S Y. Passivity of coupled memristive delayed neural networks with fixed and adaptive coupling weights[J].Neurocomputing, 2018, 313: 346-363. DOI:10.1016/j.neucom.2018.06.019.
[15] Li R X, Ji D C, Tu Z W. Passivity analysis of memristive neural networks with probabilistic time-varying delays[J].Neurocomputing, 2016, 191: 249-262. DOI:10.1016/j.neucom.2016.01.035.
[16] Tu Z W, de Cao J, Alsaedi A, et al. Global dissipativity of memristor-based neutral type inertial neural networks[J].Neural Networks, 2017, 88: 125-133. DOI:10.1016/j.neunet.2017.01.004.
[17] Zhang G D, Zeng Z G, Hu J H. New results on global exponential dissipativity analysis of memristive inertial neural networks with distributed time-varying delays[J].Neural Networks, 2018, 97: 183-191. DOI:10.1016/j.neunet.2017.10.003.
[18] Pershin Y V, di Ventra M. On the validity of memristor modeling in the neural network literature[J].Neural Networks, 2020, 121: 52-56. DOI:10.1016/j.neunet.2019.08.026.
[19] Tu Z W, Wang L W. Global Lagrange stability for neutral type neural networks with mixed time-varying delays[J].International Journal of Machine Learning and Cybernetics, 2018, 9(4): 599-609. DOI:10.1007/s13042-016-0547-6.
[20] Zhang G, Shen Y, Xu C. Global exponential stability in a Lagrange sense for memristive recurrent neural networks with time-varying delays[J]. Neurocomputing, 2015, 149: 1330-1336.DOI: 10.1016/j.neucom.2014.08.064.
[21] Lin D H, Wu J, Li J N. Less conservative stability condition for uncertain discrete-time recurrent neural networks with time-varying delays[J].Neurocomputing, 2016, 173: 1578-1588. DOI:10.1016/j.neucom.2015.09.030.
[22] Halanay A. Differential equations: Stability, oscillations, time lags[M]. New York: Academic Press, 1966.
[23] Li R X, de Cao J. Stability analysis of reaction-diffusion uncertain memristive neural networks with time-varying delays and leakage term[J].Applied Mathematics and Computation, 2016, 278: 54-69. DOI:10.1016/j.amc.2016.01.016.
[24] Li L C, Xu R, Lin J Z. Lagrange stability for uncertain memristive neural networks with Lévy noise and leakage delay[J].Physica A: Statistical Mechanics and Its Applications, 2020, 549: 124167. DOI:10.1016/j.physa.2020.124167.
[25] Rakkiyappan R, Velmurugan G, Li X D, et al. Global dissipativity of memristor-based complex-valued neural networks with time-varying delays[J].Neural Computing and Applications, 2016, 27(3): 629-649. DOI:10.1007/s00521-015-1883-2.

备注/Memo

备注/Memo:
收稿日期: 2020-09-16.
作者简介: 李梁晨(1990—),男,博士,llc0610@126.com.
基金项目: 国家自然科学基金资助项目(11871316, 11371368).
引用本文: 李梁晨,甘勤涛,蔺佳哲.参数扰动下时滞忆阻神经网络的Lagrange稳定性[J].东南大学学报(自然科学版),2021,51(3):511-520. DOI:10.3969/j.issn.1001-0505.2021.03.021.
更新日期/Last Update: 2021-05-20