This paper considers the problem of adaptive neural control for a class of uncertain stochastic nonlinear
systems with input delay. By defining the design variable with the input integral term, the input delayed system is converted to the nondelayed systems. And then, an adaptive neural control scheme is presented by combining the neural network approximation, integral mean value theorem and the decoupled backstepping technique. It is shown that the proposed controller can guarantee the 4moment semiglobally uniformly ultimately boundedness for all the signals in the closedloop system. Moreover, the tracking error can converge to a small neighborhood around the origin. A numerical example is given to illustrate the effectiveness of the control scheme.