… In recent years, deep learning technology has … ing methods are combed, categorized and
reviewed as well, including traditional methods and recent methods based on deep learning. …

… In addition, it also achieved state-of-the-art performance in time series data applications,
like stock trend prediction, weather forecast, abnormal climate and extreme geological disaster …

… This paper summarizes the research status of recommendation system, presents an overview
of the field of recommender systems, describes the classical recommendation methods …

… , which is significantly higher than the state-of-the-art human action recognition algorithms. …
A review of human action recognition based on deep learning. Acta Automatica Sinica, 2016…

… 而 随着深度学习的快速发展[14], 借助深度神经网络 (Deep neural network, DNN) 在高维连续
数据处理 方面的优势, 近期一些研究成果… Deep learning for control: the state of the art and pro- …

… Snow and ice melting techniques of pavement:State of the art and development tendency[J].…
Effective prediction of thermal conductivity of concrete using neural network method[J].…

… Pedestrian detection: an evaluation of the state of the art[J]. IEEE Transactions on Pattern
Analysis and Machine … Survey of pedestrian detection for advanced driver assistance …

… methods from machine learning, approximation theory and various heuristics. Recommender
systems … will provide a survey of different types of recommender systems. The commonly …

… of the recommendation systems. [Conclusions] The knowledge graph and machine learning
… Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and …