Finite-time stability of a class of non-autonomous neural networks with heterogeneous proportional delays

In this paper, the problem of finite-time stability analysis for a class of non-autonomous neural networks with heterogeneous proportional delays is considered. By introducing a novel constructive approach, we derive new explicit conditions in terms of matrix inequalities ensuring that the state trajectories of the system do not exceed a certain threshold over a pre-specified finite time interval. As a result, we also obtain conditions for the power-rate global stability of the system. Numerical examples are given to demonstrate the effectiveness and less restrictiveness of the results obtained in this paper.