This paper is concerned with the problem of delay-dependent H∞ control of discrete-time uncertain recurrent neural networks with time-varying delays. The neural network is subject to parameter uncertainty, and time-varying delay. For the robust H∞ stabilization problem, a state feedback controller is designed to ensure the global robust stability of the closed-loop system about its equilibrium point for all admissible uncertainties. By using the Laypunov-Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions. A simulation example is exploited to show the usefulness of the derived LMI-based stability conditions.