摘要

In this paper, a class of stochastic Cohen-Grossberg neural networks (SCGNNS) with continuous distributed delays of neutral type is considered. Firstly, some conditions are derived to ensure the existence and uniqueness of the almost periodic solution by means of contraction mapping principle and inequality techniques. Then by employing the nonnegative semi-martingale convergence theorem, the almost sure exponential stability of the SCGNNS is investigated, and some new results are established. Finally, one example is given to illustrate the obtained results.