In this paper recent research efforts in the field of the application of neural networks for the control of (semi-) autonomous underwater vehicles are reviewed. Based on a literature review a classification of neural network approaches to this control problem is proposed and the presented articles are categorized according to the identified categories. Based on practical results as described in the discussed literature a qualitative assessment regarding the performance of the control strategies is given. Per category, or control strategy, the major advantages and disadvantages are identified and discussed.