New approaches on stability criteria for neural networks with two additive time-varying delay components

In this paper, we study the stability problem for neural networks with two additive time-varying delay components. By constructing the Lyapunov–Krasovskii functional and considering the relationship between time-varying delays and their upper delay bounds, delay-dependent stability criteria are obtained by using reciprocally convex method and convex polyhedron method, respectively. More information of the lower and upper delay bounds of time-varying delays is used to derive the stability criteria, which can lead less conservative results. All the obtained criteria are in terms of Linear Matrix Inequalities (LMIs). Numerical examples are given to show the effectiveness and less conservativeness of the proposed method.