Multiple asymptotical w-periodicity of fractional-order delayed neural networks under state-dependent switching?

被引：16

作者：

Ci, Jingxuan ^{[1
]}

Guo, Zhenyuan ^{[1
]}

Long, Han ^{[2
]}

Wen, Shiping ^{[3
]}

Huang, Tingwen ^{[4
]}

机构：

[1] Hunan Univ, Sch Math, Changsha 410082, Peoples R China

[2] Natl Univ Def Technol, Coll Sci, Changsha 410073, Peoples R China

[3] Univ Technol Sydney, Fac Engn Informat Technol, Ctr Artificial Intelligence, Ultimo, NSW 2007, Australia

[4] Texas A&M Univ Qatar, Sci Program, POB 23874, Doha, Qatar

来源：

NEURAL NETWORKS | 2023年 / 157卷

基金：

中国国家自然科学基金;

关键词：

Fractional-order neural network; Multiple asymptotical w-periodicity; Delay; State-dependent switching; GLOBAL EXPONENTIAL STABILITY; MITTAG-LEFFLER STABILITY; O(T(-ALPHA)) STABILITY; ACTIVATION FUNCTIONS; MULTISTABILITY; COEXISTENCE; EQUILIBRIA;

D O I：

10.1016/j.neunet.2022.09.034

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents theoretical results on multiple asymptotical w-periodicity of a state-dependent switching fractional-order neural network with time delays and sigmoidal activation functions. Firstly, by combining the geometrical properties of activation functions with the range of switching threshold, a partition of state space is given. Then, the conditions guaranteeing that the solutions can approach each other infinitely in each positive invariant set are derived. Furthermore, the S-asymptotical w -periodicity and the convergence of solutions in positive invariant sets are discussed. It is worth noting that the number of attractors increases to 3n from 2n in a neural network without switching. Finally, three numerical examples are given to substantiate the theoretical results.(c) 2022 Elsevier Ltd. All rights reserved.

引用

页码：11 / 25

页数：15

共 51 条

[1] Pattern recognition for electroencephalographic signals based on continuous neural networks [J].

Alfaro-Ponce, M. ;

Argueelles, A. ;

Chairez, I. .

NEURAL NETWORKS, 2016, 79 :88-96

[2] Global exponential periodicity and global exponential stability of a class of recurrent neural networks with various activation functions and time-varying delays [J].

Chen, Boshan ;

Wang, Jun .

NEURAL NETWORKS, 2007, 20 (10) :1067-1080

[3] Global O(t-α) stability and global asymptotical periodicity for a non-autonomous fractional-order neural networks with time-varying delays [J].

Chen, Boshan ;

Chen, Jiejie .

NEURAL NETWORKS, 2016, 73 :47-57

[4] Dynamical behaviors of a large class of general delayed neural networks [J].

Chen, TP ;

Lu, WL ;

Chen, GR .

NEURAL COMPUTATION, 2005, 17 (04) :949-968

[5]

Deng WH, 2007, NONLINEAR DYNAM, V48, P409, DOI 10.1007/s11071 -006-9094-0

[6] Finite-time Stability of Fractional-order Complex-valued Neural Networks with Time Delays [J].

Ding, Xiaoshuai ;

Cao, Jinde ;

Zhao, Xuan ;

Alsaadi, Fuad E. .

NEURAL PROCESSING LETTERS, 2017, 46 (02) :561-580

[7] Robust Finite-Time Stabilization of Fractional-Order Neural Networks With Discontinuous and Continuous Activation Functions Under Uncertainty [J].

Ding, Zhixia ;

Zeng, Zhigang ;

Wang, Leimin .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (05) :1477-1490

[8] Multistability of Switched Neural Networks With Gaussian Activation Functions Under State-Dependent Switching [J].

Guo, Zhenyuan ;

Ou, Shiqin ;

Wang, Jun .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (11) :6569-6583

[9] Multistability of switched neural networks with sigmoidal activation functions under state-dependent switching [J].

Guo, Zhenyuan ;

Ou, Shiqin ;

Wang, Jun .

NEURAL NETWORKS, 2020, 122 :239-252

[10] Multistability of Recurrent Neural Networks With Piecewise-Linear Radial Basis Functions and State-Dependent Switching Parameters [J].

Guo, Zhenyuan ;

Liu, Linlin ;

Wang, Jun .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2020, 50 (11) :4458-4471

← 1 2 3 4 5 6 →