The robust stability of uncertain neural network with time-varying delay was investigated. The norm-bounded un-certainties are included in the system matrices. The constraint on time-varying delays is removed, which means that a fast time-varying delay is admissible. Some new delay-dependent stability criteria were presented by using Lyapunov-Krasovskii functional and linear matrix inequalities (LMIs) approaches. Finally, a numerical example was given to illustrate the effec-tiveness and innovation nature of the developed techniques.