New Sufficient Conditions on Global Exponential Stability of Delayed Inertial Neural Networks Based on a Direct Parameterized Method

In order to analyse the global exponential stability (GES) of inertial neural networks (INNs) with multiple time-varying transmission delays, a direct parameterized method in this article is proposed. First, the solution of the considered delayed INNs can be parameterized. Thereby, sufficient conditions on GES of the delayed INNs will be established. Then, a numerical example is given to confirm the feasibility and non-conservativeness of the stability criterions. There are two advantages for the direct parameterized method given in this work: (i) to avoid constructing the Lyapunov–Krasovskii functional (LKF), the GES is defined directly by using the inequality technique; (ii) the stability criterion contains are obtained by the theoretical results solve rapidly.