Exponential Synchronization of Markovian Jump Neural Networks Based on Asynchronous Delayed-Feedback Controller With Uncertain Hidden Information
针对反馈信息延迟问题，设计了一种新的异步延迟反馈控制器，实现了马尔可夫跳跃神经网络的指数同步，并推导了延迟边界，适用于同步和异步情形。
Due to the complex network environment, the feedback information cannot be timely received by the controller. This article proposes a method on the exponential synchronization for the Markovian jump neural networks, which is achieved by designing a new asynchronous delayed-feedback controller, with its feedback delay taken into account. The quantized relationship between the exponential synchronization and the feedback delay is derived from a new designed Lyapunov functional, to acquire delay boundaries. With the help of a hidden-Markov process, the designed controller shows asynchrony, which allows controller modes to run free. In particular, the detection probability is assumed to be bounded known, marking a breakthrough over existing results. Moreover, the proposed method proves to be applicable in both synchronous and asynchronous cases. By using the proposed method, the computation freedom of the controller gain matrix can be substantially augmented. Further, comparative numerical studies are implemented to validate the effectiveness and superiority of the proposed method.