Synchronization of Non-Identical Unknown Chaotic Delayed Neural Networks Based on Adaptive Sliding Mode Control

Authors:
Qintao Gan;Yuhua Liang
Affiliations:
Department of Basic Science, Shijiazhuang Mechanical Engineering College, Shijiazhuang, People's Republic of China 050003;Department of Basic Science, Shijiazhuang Mechanical Engineering College, Shijiazhuang, People's Republic of China 050003
Venue:
Neural Processing Letters
Year:
2012

Citing 7
Cited 0

Neural networks letter: Synchronization of nonidentical chaotic neural networks with time delays

Neural Networks
Improved robust stability criteria for delayed cellular neural networks via the LMI approach

IEEE Transactions on Circuits and Systems II: Express Briefs
New results for robust stability of dynamical neural networks with discrete time delays

Expert Systems with Applications: An International Journal
Sliding mode control for a class of nonlinear discrete-time networked systems with multiple stochastic communication delays

International Journal of Systems Science
Stability analysis of stochastic fuzzy cellular neural networks with time-varying delays

Neurocomputing
Anti-periodic solutions for a class of Cohen-Grossberg neural networks with time-varying delays on time scales

International Journal of Systems Science
Controller design for synchronization of an array of delayed neural networks using a controllable probabilistic PSO

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The synchronization problem is studied in this paper for non-identical chaotic neural networks with time delays and fully unknown parameters, where the mismatched parameters, activation functions and neural network architectures are taken into account. To overcome the difficulty that complete synchronization of non-identical chaotic neural networks cannot be achieved only by utilizing output feedback control, we design an adaptive sliding mode controller to realize the synchronization. Our synchronization criteria are easily verified and do not need to solve any linear matrix inequality. These results generalize a few previous known results and remove some restrictions on the parameters, activation functions and neural network architectures. This paper also presents an illustrative example and uses simulated results of this example to show the feasibility and effectiveness of the proposed scheme.