Stability analysis for delayed quaternion-valued neural networks via nonlinear measure approach

摘要

In this paper, the existence and stability analysis of the quaternion-valued neural networks(QVNNs) with time delay are considered. Firstly, the QVNNs are equivalently transformedinto four real-valued systems. Then, based on the Lyapunov theory, nonlinear measure approach,and inequality technique, some sufficient criteria are derived to ensure the existence and uniquenessof the equilibrium point as well as global stability of delayed QVNNs. In addition, the providedcriteria are presented in the form of linear matrix inequality (LMI), which can be easily checkedby LMI toolbox in MATLAB. Finally, two simulation examples are demonstrated to verify theeffectiveness of obtained results. Moreover, the less conservatism of the obtained results is alsoshowed by two comparison examples.