Direction-of-arrival (DOA) estimation is an important problem in many applications such as communication and navigation. Many methods have been presented for this problem. The Maximum Likelihood (ML) is one of the good solutions. But, in traditional algorithms for ML Nonetheless, the computational load is very heavy and multivariate nonlinear maximization problem is serious. To deal with these problems, this paper describes an application of neural network (NN) for obtaining the global optimal solution of ML DOA estimation. It overcomes the local optima problem existing in some ML DOA estimation algorithms and improves the estimation accuracy. The computation complexity is modest.