Exponential estimates and exponential stability for neutral-type neural networks with multiple delays

In this paper, exponential estimates and sufficient criteria for the exponential stability of neutral-type neural networks with multiple delays are given. First, because of the key role of the difference equation part of the neutral-type neural networks with multiple delays, some novel results concerning exponential estimates for non-homogeneous difference equations evolving in continuous time are derived. Then, by constructing several different Lyapunov–Krasovskii functionals combined with a descriptor transformation approach at some cases, several novel global and exponential stability conditions are presented and expressed in terms of linear matrix inequalities (LMIs), and the obtained results are less conservative and restrictive than the known results. Some numerical examples are also given to show their effectiveness and advantages over others.