Knowledge tracking is an important cognitive diagnosis method, which is often used in digitalized education platforms such as online learning platforms and intelligent tutoring systems. By analyzing students' interactions with course assignments, knowledge tracing models can simulate their mastery level of knowledge concepts in courses in real time. The simulation results can be used to predict students' future learning performance and help them plan personalized learning paths. In the past 20 years, knowledge tracing models have been constructed based on theories of statistics and cognitive science. With the openness and application of educational big data, models based on deep neural networks, referred to as "deep knowledge tracing models", have gradually replaced traditional models due to their simple theoretical foundations and superior predictive performances, and become a new research hotspot in the field of knowledge tracing. According to the neural network architectures, the algorithm details of recent representative deep models for knowledge tracing are illustrated, and a comprehensive performance evaluation of the models on five publicly available datasets is conducted. Finally, some use cases and future research directions of deep knowledge tracing are discussed.