Improved delay-dependent stability criteria for time-delayed neural networks

This paper is concerned with the problem of stability for recurrent neural networks with time-delay. By choosing a new class of Lyapunov-Krasovskii functional, some new delay-dependent stability criteria are derived in terms of linear matrix inequalities. The obtained results are less conservative than the existing ones because of the introducing of the triple integral term and reciprocally convex approach. Then, a numerical example is carried out to demonstrate the applicability and effectiveness of the proposed work through simulations.