State Key Laboratory of Superlattices and Microstructures, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China
Li-Ming Xu
Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
Xu-Min Lin
College of Mathematics and Physics, Beijing University of Chemical Technology, Beijing 100029, China
Xing Wei
State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
Wen-Jie Yu
State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
Yang Wang
Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China; Corresponding author at: State Key Laboratory of Superlattices and MicrostructuresInstitute of Semiconductors, Chinese Academy of Sciences, Beijing100083, China.
Zhong-Ming Wei
State Key Laboratory of Superlattices and Microstructures, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China; Corresponding author at: State Key Laboratory of Superlattices and MicrostructuresInstitute of Semiconductors, Chinese Academy of Sciences, Beijing100083, China.
Thanks to the increasingly high standard of electronics, the semiconductor material science and semiconductor manufacturing have been booming in the last few decades, with massive data accumulated in both fields. If analyzed effectively, the data will be conducive to the discovery of new semiconductor materials and the development of semicondulctor manufacturing. Fortunately, machine learning, as a fast-growing tool from computer science, is expected to significantly speed up the data analysis. In recently years, many researches on machine learning study of semiconductor materials and semiconductor manufacturing have been reported. This article is aimed to introduce these progress and present some prospects in this field.
