Existence and exponential stability of piecewise pseudo almost periodic solution of neutral-type inertial neural networks with mixed delay and impulsive perturbations.

In this paper, the exponential stability of piecewise pseudo almost periodic solutions for neutral-type inertial neural networks with time-varying, infinite-time distributed delays (mixed delays) and impulses are investigated. First, by constructing a proper variable substitution, the original inertial neural networks can be rewritten as the first-order differential equation. Second, by using inequality techniques and Lyapunov method, some sufficient conditions which ensure the existence and exponential stability of piecewise pseudo almost periodic solutions of inertial neural networks are presented. Finally, an example with graphical illustration is given to illustrate the effectiveness of the theoretical results.