Multiple finite-time synchronization of delayed inertial neural networks via a unified control scheme

摘要

In this paper, a unified control framework is proposed to investigate the synchronization problem of inertial neural networks (INNs). Via the proposed framework, the finite-time, fixed-time and preassigned-time synchronization of INNs are realized. Firstly, by adopting a proper variable transformation, the reduced-order system and the error system of the drive and response INNs are obtained. Then, without designing synchronization controllers separately, the drive and response systems can be finite-/fixed-/preassigned-time synchronized and corresponding estimations of the settling time can be obtained by properly regulating the control parameters of the unified framework. Finally, the correctness of the derived theoretical results is proved by numerical simulations and an application example of image encryption.