Prof. Xinping Yi
Prof. Xinping Yi has been a Lecturer at the Department of Electrical Engineering and Electronics of the University of Liverpool, United Kingdom, since July 2017. He received the Ph.D. degree in Electronics and Communications (2015) from Télécom ParisTech, Paris, France. Prior to Liverpool, he was a research associate at Technische Universität Berlin, Berlin, Germany (2014-2017), a research assistant at EURECOM, Sophia Antipolis, France (2011-2014), and a research engineer at Huawei Technologies, Shenzhen, China (2009-2011). His main research interests include information theory, graph theory, optimization and machine learning, as well as their applications in 5G wireless communications and artificial intelligence. In particular, his recent research activities lie in the theoretical understanding of deep learning via information theory. In the last five years, he has published over twenty peer-reviewed papers, mostly in IEEE Trans. Information Theory (TIT) and Int. Sym. Information Theory (ISIT). He is the Principal Investigator of an industrial (HIRP) project on optimization and machine learning for Beyond 5G systems.
The past few years have seen deep learning achieved human-level intelligence in several tasks, such as image processing and video game playing, and been applied to many application areas, including robotics control, healthcare, etc. While the empirical precision has been significantly improved, deep learning suffers from the problem of lacking certification and understanding. This twoday tutorial will introduce some recent progress aiming to open the black-box of the deep learning, from the perspectives of automated verification and information theory. The verification of deep learning, to be presented by Dr Xiaowei Huang, will focus on a few techniques including constraint-solving based methods, search-based methods, and methods based on functional approximation. The understanding of deep learning, to be presented by Dr Xinping Yi, will focus on the information-theoretic measure of the training dynamics through the lens of the information bottleneck method.