Autonomous driving is one of the three major innovations in automotive industry. Deep learning is a crucial method to improve automotive intelligence due to its outstanding abilities of data fitting, feature representation and model generalization. This paper reviews the technologies of deep neural network (DNN) for autonomous vehicles, which covers its history, main algorithms and key technical application. We first introduce the historical timeline of DNN, its “Unit-Layer-Network” architecture, and two representative models. We then summarize the training algorithms centered on back propagation (BP), labelled datasets and free-source frameworks for deep learning, followed by the introduction to computing platforms and model optimization technologies. Finally, we discuss the applications of DNN in autonomous vehicles, including object detection and semantic segmentation, hierarchical and end-to-end decision-making, longitudinal and lateral motion control, and point out the applicable methods and future works for different key problems of DNN in autonomous vehicles.