Adaptive state estimation of Markov switched neural networks driven by Lévy noise

2019 ◽  
Vol 42 (2) ◽  
pp. 330-336
Author(s):  
Dongbing Tong ◽  
Qiaoyu Chen ◽  
Wuneng Zhou ◽  
Yuhua Xu
Keyword(s):  
Neural Networks ◽  
State Estimation ◽  
Sufficient Conditions ◽  
Lyapunov Stability Theory ◽  
Lévy Noise ◽  
Linear Matrix ◽  
Delayed Neural Networks ◽  
Switched Neural Networks ◽  
Inequality Technique ◽  
Levy Noise

This paper proposes the [Formula: see text]-matrix method to achieve state estimation in Markov switched neural networks with Lévy noise, and the method is very distinct from the linear matrix inequality technique. Meanwhile, in light of the Lyapunov stability theory, some sufficient conditions of the exponential stability are derived for delayed neural networks, and the adaptive update law is obtained. An example verifies the condition of state estimation and confirms the effectiveness of results.

Dynamical Behaviors of Delayed Neural Network Systems with Discontinuous Activation Functions

2006 ◽  
Vol 18 (3) ◽  
pp. 683-708 ◽  
Author(s):  
Wenlian Lu ◽  
Tianping Chen
Keyword(s):  
Neural Networks ◽  
Sufficient Conditions ◽  
Linear Matrix ◽  
Activation Functions ◽  
Network Systems ◽  
Delayed Neural Networks ◽  
Discontinuous Activation ◽  
Feedback Matrix ◽  
Inequality Technique ◽  
Discontinuous Activation Functions

In this letter, without assuming the boundedness of the activation functions, we discuss the dynamics of a class of delayed neural networks with discontinuous activation functions. A relaxed set of sufficient conditions is derived, guaranteeing the existence, uniqueness, and global stability of the equilibrium point. Convergence behaviors for both state and output are discussed. The constraints imposed on the feedback matrix are independent of the delay parameter and can be validated by the linear matrix inequality technique. We also prove that the solution of delayed neural networks with discontinuous activation functions can be regarded as a limit of the solutions of delayed neural networks with high-slope continuous activation functions.

scholarly journals Robust State Estimation for Delayed Neural Networks with Stochastic Parameter Uncertainties

2015 ◽  
Vol 2015 ◽  
pp. 1-18 ◽  
Author(s):  
M. J. Park ◽  
O. M. Kwon ◽  
Ju H. Park ◽  
S. M. Lee ◽  
E. J. Cha
Keyword(s):  
Neural Networks ◽  
State Estimation ◽  
Linear Matrix ◽  
Parameter Uncertainties ◽  
Delayed Neural Networks ◽  
Stochastic Parameter ◽  
Mean And Variance ◽  
Delay Dependent ◽  
Designing Method ◽  
Dependent State

This paper considers the problem of delay-dependent state estimation for neural networks with time-varying delays and stochastic parameter uncertainties. It is assumed that the parameter uncertainties are affected by the environment which is changed with randomly real situation, and its stochastic information such as mean and variance is utilized in the proposed method. By constructing a newly augmented Lyapunov-Krasovskii functional, a designing method of estimator for neural networks is introduced with the framework of linear matrix inequalities (LMIs) and a neural networks model with stochastic parameter uncertainties which have not been introduced yet. Two numerical examples are given to show the improvements over the existing ones and the effectiveness of the proposed idea.

scholarly journals Delay-Dependent Guaranteed Cost Controller Design for Uncertain Neural Networks with Interval Time-Varying Delay

2012 ◽  
Vol 2012 ◽  
pp. 1-16 ◽  
Author(s):  
M. Rajchakit ◽  
P. Niamsup ◽  
T. Rojsiraphisal ◽  
G. Rajchakit
Keyword(s):  
Neural Networks ◽  
State Feedback ◽  
Closed Loop ◽  
Controller Design ◽  
Sufficient Conditions ◽  
Performance Measure ◽  
State Feedback Control ◽  
Linear Matrix ◽  
Delayed Neural Networks ◽  
Guaranteed Cost

This paper studies the problem of guaranteed cost control for a class of uncertain delayed neural networks. The time delay is a continuous function belonging to a given interval but not necessary to be differentiable. A cost function is considered as a nonlinear performance measure for the closed-loop system. The stabilizing controllers to be designed must satisfy some exponential stability constraints on the closed-loop poles. By constructing a set of augmented Lyapunov-Krasovskii functionals combined with Newton-Leibniz formula, a guaranteed cost controller is designed via memoryless state feedback control, and new sufficient conditions for the existence of the guaranteed cost state feedback for the system are given in terms of linear matrix inequalities (LMIs). Numerical examples are given to illustrate the effectiveness of the obtained result.

Synchronization of delayed neural networks with Lévy noise and Markovian switching via sampled data

2015 ◽  
Vol 81 (3) ◽  
pp. 1179-1189 ◽  
Author(s):  
Jun Yang ◽  
Wuneng Zhou ◽  
Peng Shi ◽  
Xueqing Yang ◽  
Xianghui Zhou ◽  
...  
Keyword(s):  
Neural Networks ◽  
Markovian Switching ◽  
Lévy Noise ◽  
Sampled Data ◽  
Delayed Neural Networks ◽  
Levy Noise

scholarly journals Robust Stabilization andH∞Control for Uncertain Neural Networks with Mixed Time Delays

2015 ◽  
Vol 2015 ◽  
pp. 1-13
Author(s):  
Bin Wen ◽  
Hui Li ◽  
Li Liang
Keyword(s):  
Neural Networks ◽  
Robust Stability ◽  
Time Delays ◽  
Convex Combination ◽  
Robust Stabilization ◽  
Sufficient Conditions ◽  
Lyapunov Stability Theory ◽  
Linear Matrix ◽  
Mixed Time Delays ◽  
Uncertain Neural Networks

This paper is concerned with the problem of robust stabilization andH∞control for a class of uncertain neural networks. For the robust stabilization problem, sufficient conditions are derived based on the quadratic convex combination property together with Lyapunov stability theory. The feedback controller we design ensures the robust stability of uncertain neural networks with mixed time delays. We further design a robustH∞controller which guarantees the robust stability of the uncertain neural networks with a givenH∞performance level. The delay-dependent criteria are derived in terms of LMI (linear matrix inequality). Finally, numerical examples are provided to show the effectiveness of the obtained results.

scholarly journals Synchronization of Chaotic Delayed Neural Networks via Impulsive Control

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Yang Fang ◽  
Kang Yan ◽  
Kelin Li
Keyword(s):  
Neural Networks ◽  
Impulsive Control ◽  
Sufficient Conditions ◽  
Stability Theorem ◽  
Linear Matrix ◽  
Matrix Inequality ◽  
Lyapunov Stability Theorem ◽  
Delayed Neural Networks ◽  
Impulsive Synchronization ◽  
Synchronization Problem

This paper is concerned with the impulsive synchronization problem of chaotic delayed neural networks. By employing Lyapunov stability theorem, impulsive control theory and linear matrix inequality (LMI) technique, several new sufficient conditions ensuring the asymptotically synchronization for coupled chaotic delayed neural networks are derived. Based on these new sufficient conditions, an impulsive controller is designed. Moreover, the stable impulsive interval of synchronized neural networks is objectively estimated by combining the MATLAB LMI toolbox and one of the two given equations. Two examples with numerical simulations are given to illustrate the effectiveness of the proposed method.

scholarly journals LMI-Based Stability Criteria for Discrete-Time Neural Networks with Multiple Delays

2013 ◽  
Vol 2013 ◽  
pp. 1-6 ◽  
Author(s):  
Hui Xu ◽  
Ranchao Wu
Keyword(s):  
Neural Networks ◽  
Continuous Time ◽  
Discrete Model ◽  
Sufficient Conditions ◽  
Lyapunov Stability Theory ◽  
Linear Matrix ◽  
Multiple Delays ◽  
Matrix Inequalities ◽  
Stability Criteria ◽  
Neural Models

Discrete neural models are of great importance in numerical simulations and practical implementations. In the current paper, a discrete model of continuous-time neural networks with variable and distributed delays is investigated. By Lyapunov stability theory and techniques such as linear matrix inequalities, sufficient conditions guaranteeing the existence and global exponential stability of the unique equilibrium point are obtained. Introduction of LMIs enables one to take into consideration the sign of connection weights. To show the effectiveness of the method, an illustrative example, along with numerical simulation, is presented.

scholarly journals Quantized passive filtering for switched delayed neural networks

2021 ◽  
Vol 26 (1) ◽  
pp. 93-112
Author(s):  
Youmei Zhou ◽  
Yajuan Liu ◽  
Jianping Zhou ◽  
Zhen Wang
Keyword(s):  
Neural Networks ◽  
Filter Design ◽  
Sufficient Conditions ◽  
Linear Matrix ◽  
Passive Filter ◽  
Delayed Neural Networks ◽  
Noise Interference ◽  
Exponentially Stable ◽  
Error System ◽  
Inequality Techniques

The issue of quantized passive filtering for switched delayed neural networks with noise interference is studied in this paper. Both arbitrary and semi-Markov switching rules are taken into account. By choosing Lyapunov functionals and applying several inequality techniques, sufficient conditions are proposed to ensure the filter error system to be not only exponentially stable, but also exponentially passive from the noise interference to the output error. The gain matrix for the proposed quantized passive filter is able to be determined through the feasible solution of linear matrix inequalities, which are computationally tractable with the help of some popular convex optimization tools. Finally, two numerical examples are given to illustrate the usefulness of the quantized passive filter design methods.

scholarly journals Passivity analysis of multiple time-varying time delayed complex variable neural networks in finite-time

2021 ◽  
Vol 8 (4) ◽  
pp. 842-854
Author(s):  
N. Jayanthi ◽  
◽  
R. Santhakumari ◽  
Keyword(s):  
Neural Networks ◽  
Finite Time ◽  
Sufficient Conditions ◽  
Lyapunov Stability Theory ◽  
Linear Matrix ◽  
Multiple Time ◽  
Time Varying ◽  
Matrix Inequalities ◽  
Complex Valued ◽  
Theoretical Results

In this article, we investigate the problem of finite-time passivity for the complex-valued neural networks (CVNNs) with multiple time-varying delays. To begin, many definitions relevant to the finite-time passivity of CVNNs are provided; then the suitable control inputs are designed to guarantee the class of CVNNs are finite-time passive. In the meantime, some sufficient conditions of linear matrix inequalities (LMIs) are derived by using inequalities techniques and Lyapunov stability theory. Finally, a numerical example is presented to illustrate the usefulness of the theoretical results.

Sign in / Sign up

Export Citation Format

Share Document