Invited Speech Title: Deep Learning for Physical Layer Wireless Communications

Speaker's Bio:
Guan Gui received the Dr. Eng degree in Information and Communication Engineering from University of Electronic Science and Technology of China (UESTC), Chengdu, China, in 2012. From October 2009 to March 2012, he joined the Department of Communications Engineering, Graduate School of Engineering, Tohoku University as for research assistant as well as postdoctoral research fellow, respectively. From September 2012 to March 2014, he was supported by Japan society for the promotion of science (JSPS) fellowship as postdoctoral research fellow at same laboratory. From April 2014 to October 2015, he was an Assistant Professor in Department of Electronics and Information System, Akita Prefectural University. Since November 2015, he has been a professor with Nanjing University of Posts and Telecommunications (NUPT), Nanjing, China.
He is currently engaged in research of deep learning and compressive sensing for advanced wireless techniques. He is an IEEE Senior Member. Dr. Gui has been an Editor for the Security and Communication Networks (2012~2016), Editor of Transactions on Vehicular Technology (2017~) and Editor of KSII Transactions on Internet and Information Systems (2017~). He has published more than 200 international journal/conference papers. Also he received several best papers awards: ICC2014, ICC2017, VTC2014-Spring, ICNC2018 and CSPS2018. He was also selected as for Jiangsu Special Appointed Professor, Jiangsu High-level Innovation and Entrepreneurial Talent and Nanjing Youth Award.

Invited Speech Abstract:
The new demands for high-reliability and ultra-high capacity wireless communication have led to extensive research into 5G communications, but the current communication systems, which were designed on the basis of conventional communication theories, significantly restrict further performance improvements and lead to severe limitations. Recently, the emerging deep learning technique has been recognized as an excellent candidate for handling such complicated systems, and its potential for optimizing wireless communications has been fully demonstrated. In this talk, we review the development of deep learning for 5G wireless communication and propose efficient schemes for deep learning-based 5G scenarios. Specifically, the key ideas for several important deep learning based communication methods are described, along with the research opportunities and challenges that remain. On this topic of prime interest, novel communication frameworks of non-orthogonal multiple access (NOMA), massive multiple-input multiple-output (MIMO), and millimeter wave (mmWave) have been well investigated, and their superior performance has been corroborated. We hope that the appealing deep learning based wireless physical layer frameworks can bring a new evolution communication theories and that this work will move us along this road.