Predefined-Time Synchronization of Competitive Neural Networks via Continuous Time-Varying Control

This paper presents the drive-response synchronization problem for competitive neural networks (CNNs) in predefined time. The CNN response system is considered in presence of deterministic disturbances satisfying Lipschitz conditions and in presence of both stochastic white noises and deterministic disturbances satisfying Lipschitz conditions. The effect of deterministic disturbances and stochastic noises is suppressed by designing a time-varying continuous control input driving the CNN synchronization error at the origin for an a priori predefined time, independently of the CNN initial conditions, deterministic disturbances, and stochastic noises. Finally, numerical simulations are conducted to demonstrate validity of the obtained theoretical results and effectiveness of the presented synchronization scheme.