A combined reciprocal convexity approach for stability analysis of static neural networks with interval time-varying delays

This paper proposes a novel approach called a combined reciprocal convexity approach for the stability analysis of static neural networks with interval time-varying delays. The proposed approach deals with all convex-parameter-dependent terms in the time derivative of the Lyapunov-Krasovskii functional non-conservatively by extending the idea of the conventional reciprocal convexity approach. Based on the proposed technique and a new Lyapunov-Krasovskii functional, two improved delay-dependent stability criteria are derived in terms of linear matrix inequalities(LMIs). Some numerical examples are given to demonstrate the proposed results.