Deep learning (DL) and direction-of-arrival (DOA) estimation are two highly regarded topics in the fields of signal processing and machine learning. DL technology has achieved tremendous success in areas such as image recognition, speech recognition, and natural language processing, while DOA estimation is of significant importance in sonar, radar, communications, medical detection, and electronic countermeasures. In recent years, the application of DL to DOA estimation has achieved great success. This chapter combines DL and DOA estimation to explore how to leverage the powerful feature extraction and pattern recognition capabilities of DL to improve the accuracy and robustness of DOA estimation. This chapter aims to provide comprehensive theoretical knowledge by introducing the basic principles and methods of DL and DOA estimation, followed by a detailed exposition of the application of DL in DOA estimation, focusing on fully connected neural network (FCNN), convolutional neural network (CNN), convolutional variational neural network (CVNN), cascaded neural network, transfer learning (TL), and deep unfolding (DU). This chapter also emphasizes the application of different types of neural networks in DOA estimation and the establishment of neural networks and discusses their advantages in feature extraction and signal localization. Finally, the applications of DL in DOA estimation were summarized, and an outlook on challenges and future directions was provided. This chapter aims to provide comprehensive theoretical knowledge and practical guidance for researchers, engineers, and students, helping them better understand and apply the relevant knowledge of DL and DOA estimation.