Global exponential stability for quaternion-valued recurrent neural networks with time-varying delays

In this paper, we employ a novel method for solving the problem of the global exponential stability of quaternion-valued recurrent neural networks (QVNNs) with time-varying delays. Theoretically, a QVNN can be separated into four real-valued systems, forming an equivalent real-valued system. From the view of matrix measure, based on Halanay inequality instead of Lyapunov function, some sufficient conditions are derived to guarantee the global exponential stability for QVNNs. Moreover, the activation functions are not assumed to be derivative any more, which makes the analytical procedure compact. Finally, a numerical example is provided to validate the advantage of the proposed method and to show the effectiveness of the main results.