Improved delay-dependent stability criterion on neural networks with time-varying delay

In this paper, based on Lyapunov-Krasovskii functional approach and proper integral inequality, one novel sufficient condition is derived to guarantee the global stability for neural networks with interval time-varying delay, in which the general convex combination is employed. The LMI-based criterion heavily depends on the upper and lower bounds on both time delay and its derivative, which is different from those existent ones and has wider application fields than some present results. Finally, two numerical examples can illustrate the less conservatism of the proposed methods.