Exponential and adaptive synchronization of inertial complex-valued neural networks: A non-reduced order and non-separation approach

被引：93

作者：

Yu, Juan ^{[1
]}

Hu, Cheng ^{[1
]}

Jiang, Haijun ^{[1
]}

Wang, Leimin ^{[2
]}

机构：

[1] Xinjiang Univ, Coll Math & Syst Sci, Urumqi 830046, Peoples R China

[2] China Univ Geosci, Sch Automat, Wuhan 430074, Peoples R China

来源：

NEURAL NETWORKS | 2020年 / 124卷

基金：

中国国家自然科学基金;

关键词：

Adaptive design; Complex-valued neural network; Exponential synchronization; Inertial model; GENERAL DECAY SYNCHRONIZATION; FIXED-TIME SYNCHRONIZATION; VARYING DELAYS; LEAKAGE DELAY; STABILITY; DYNAMICS; PERIODICITY; CRITERIA;

D O I：

10.1016/j.neunet.2020.01.002

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 mainly deals with the problem of exponential and adaptive synchronization for a type of inertial complex-valued neural networks via directly constructing Lyapunov functionals without utilizing standard reduced-order transformation for inertial neural systems and common separation approach for complex-valued systems. At first, a complex-valued feedback control scheme is designed and a nontrivial Lyapunov functional, composed of the complex-valued state variables and their derivatives, is proposed to analyze exponential synchronization. Some criteria involving multi-parameters are derived and a feasible method is provided to determine these parameters so as to clearly show how to choose control gains in practice. In addition, an adaptive control strategy in complex domain is developed to adjust control gains and asymptotic synchronization is ensured by applying the method of undeterminated coefficients in the construction of Lyapunov functional and utilizing Barbalat Lemma. Lastly, a numerical example along with simulation results is provided to support the theoretical work. (C) 2020 Elsevier Ltd. All rights reserved.

引用

页码：50 / 59

页数：10

共 66 条

[1] Nonlinear output control scheme for general decay synchronization of delayed neural networks with inertial term [J].

Abdurahman, Abdujelil ;

Jiang, Haijun ;

Sader, Malika .

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2019, 29 (13) :4366-4383

[2] New results on exponential synchronization of memristor-based neural networks with discontinuous neuron activations [J].

Abdurahman, Abdujelil ;

Jiang, Haijun .

NEURAL NETWORKS, 2016, 84 :161-171

[3] CHAOTIC NEURAL NETWORKS [J].

AIHARA, K ;

TAKABE, T ;

TOYODA, M .

PHYSICS LETTERS A, 1990, 144 (6-7) :333-340

[4]

Aizenberg I, 2017, STUD FUZZ SOFT COMP, V349, P153, DOI 10.1007/978-3-319-48317-7_10

[5] Finite-time and fixed-time synchronization of a class of inertial neural networks with multi-proportional delays and its application to secure communication [J].

Alimi, Adel M. ;

Aouiti, Chaouki ;

Assali, El Abed .

NEUROCOMPUTING, 2019, 332 :29-43

[6] Single-layered complex-valued neural network for real-valued classification problems [J].

Amin, Md. Faijul ;

Murase, Kazuyuki .

NEUROCOMPUTING, 2009, 72 (4-6) :945-955

[7] MODELS OF MEMBRANE RESONANCE IN PIGEON SEMICIRCULAR CANAL TYPE-II HAIR-CELLS [J].

ANGELAKI, DE ;

CORREIA, MJ .

BIOLOGICAL CYBERNETICS, 1991, 65 (01) :1-10

[8] STABILITY AND DYNAMICS OF SIMPLE ELECTRONIC NEURAL NETWORKS WITH ADDED INERTIA [J].

BABCOCK, KL ;

WESTERVELT, RM .

PHYSICA D, 1986, 23 (1-3) :464-469

[9] DYNAMICS OF SIMPLE ELECTRONIC NEURAL NETWORKS [J].

BABCOCK, KL ;

WESTERVELT, RM .

PHYSICA D, 1987, 28 (03) :305-316

[10] Adaptive synchronization of neural networks with or without time-varying delay [J].

Cao, JD ;

Lu, JQ .

CHAOS, 2006, 16 (01)

← 1 2 3 4 5 6 7 →