Improved stability criteria of neural networks with time-varying delay based on the variable-augmented-based free-weighting-matrices

This paper discusses the stability problem of neural networks with time-varying delays. Firstly, a delay-product-type term is added to the Lyapunov-Krasovskii functionals(LKF) to take into account extra time-delay-related information. Then, by employing the variable-augmented-based free-weighting-matrices, the higher-order terms of the time-varying delay are successfully avoided in estimating the derivative of the LKF. Nextly, two stability criteria with less conservatism are established. Finally, two examples are used to illustrate the effectiveness of the presented criteria.