Mean-square stability of stochastic quaternion-valued neural networks with variable coefficients and neutral delays

In this paper, the stochastic quaternion-valued neural networks model with variable coefficients and neutral delays is considered, and the mean-square stability criterion is provided via the method of mathematical analysis. In deriving stability criterion, the considered stochastic quaternion-valued neural networks model is implemented as an entirety form without separating the model into two complex-valued or four real-valued models. And the obtained result is valid for stochastic real-valued and complex-valued neural networks. A numerical simulation example is given to show the effectiveness of the obtained result.