The delay-dependent H∞ state estimation problems for stochastic neural networks is considered in this paper. By constructing a suitable Lyapunov-Krasovskii functional, a delay-dependent condition is established to guarantee the estimation error systems to be asymptotical mean-square stable and achieve a prescribed H∞ performance index. Both delay-dependent and delay-independent sufficient conditions for the existence of desired state estimators are derived in terms of linear matrix inequalities(LMIs). Finally, a numerical example demonstrate that the proposed approaches are effective.