Robust convergence of Cohen–Grossberg neural networks with mode-dependent time-varying delays and Markovian jump

The robust stochastic convergence in mean square is investigated for a class of uncertain Cohen–Grossberg neural networks with both Markovian jump parameters and mode-dependent time-varying delays. By employing the Lyapunov method and a generalized Halanay-type inequality, a delay-dependent condition is derived to guarantee the state variables of the discussed neural networks to be globally uniformly exponentially stochastic convergent to a ball in the state space with a pre-specified convergence rate. After some parameters being fixed in advance, the proposed conditions are all in terms of linear matrix inequalities, which can be solved numerically by employing the LMI toolbox in Matlab. Finally, an illustrated example is given to show the effectiveness and usefulness of the obtained results.