The rapid growth of data has brought valuable resources to many industries, and at the same time has brought severe challenges to many fields. The effective use of feature learning technology can discover the hidden rules in big data and tap the potential value of big data, thereby predicting future development, which will greatly promote the overall development of the global economy and society.

As a typical technique of feature learning, deep learning employs supervised or unsupervised strategies to automatically learn multi-layer representations of data and has been successfully applied to the fields of speech recognition, collaborative filtering, and image processing. Although deep learning has made some progress in data feature learning, it still faces many scientific challenges. For example, when the data have the characteristics of inaccuracy, incompleteness, imbalance, etc., the learning results of the algorithms and models will be seriously affected.

Therefore, this Special Issue aims to seek high-quality papers from academics and industry-related researchers of big data, machine learning, and artificial intelligence, who conduct research on the shortcomings of deep learning models in big data feature learning and present the most recently advanced methods and applications.

Potential topics include but are not limited to the following:

• Big Data theory and methods
• Feature learning
• Machine Learning and Deep Learning
• Knowledge discovery for Big Data
• Domain adaption and transfer learning
• Computer vision
• Virtual reality
• Natural language processing
• Big Data for healthcare
• Big Data analysis and applications in other fields