It is well known that the near wall velocity is closely related to the streaky structure in the wall bounded flow and it is a useful information for the control of the flow. In the present study, we construct an artificial neural network (ANN) to predict near wall velocity in turbulent channel flow. As an input for ANN, wall pressure distribution below the near wall velocity to be predicted is chosen. For the learning process to build this ANN, instantaneous flow data sets are obtained from direct numerical simulation of turbulent channel flow at Reτ = 178. The performance of ANN is examined according to the plane size of wall pressure as an input, number of hidden layer, number of hidden nodes, and etc. It is found that the present ANN based on wall pressure successfully predicts the near wall velocity. Also, we apply this ANN to the control of turbulent channel flow for the skin friction reduction, and its results will be given in the presentation.