This paper is concerned with the input-to-state stability problem of a class of neutral stochastic neural networks. The stochastic neural networks that we consider contain both neutral terms and mixed delays. By utilizing the Lyapunov-Krasovskii functional method, stochastic analysis techniques and It o ^ 's formula, some sufficient conditions are derived to ensure the mean-square exponential input-to-state stability of the addressed system. Two numerical examples and their simulations are given to illustrate the effectiveness of the derived results.