Improved Stability Analysis of Generalized Neural Networks with Interval Time-Varying Delays

This paper proposes an improved stability analysis of generalized neural networks using the generalized integral inequality based on free matrices. The delay has the upper and lower bounds, but the information of delay's derivative is unknown. For the stability analysis of this system, main results use the Lyapunov-Krasovskii Functionals method which is most widely used. The generalized integral inequality based on free matrices can obtain more improved results, since this inequality uses both the single integral term and the higher-order multiple integral terms. Additionally, the negative definite conditions of the matrix valued cubic polynomials enable to form linear matrix inequalities. Using these inequalities and the reciprocally convex approach, sufficient stability conditions are derived in the linear-matrix inequalities form. Eventually, a well-known numerical example will show the effectiveness of the proposed approaches.