Peng Cheng Laboratory

IEEE Fellow Prof. Zhi Ding’s Invited Talk on “When Massive MIMO Meets Deep Learning”

Date: 2019-07-12 Source:

Prof. Zhi Ding of the University of California, Davis, was invited to PCL to deliver a seminar at the “Expert Lecture” series co-organized by PCL’s Research Center for Artificial Intelligence and Network Communication.


丁峙1.jpg


Prof. Ding is a Fellow of IEEE. He was the General Chair of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) and Technical Program Chair of the 2006 IEEE Globecom. 


丁峙2.jpg


In the beginning of his talk entitled “When Massive MIMO Meets Deep Learning”, Prof. Ding illustrated that the proliferation of advanced wireless services, such as virtual reality, autonomous driving and Internet of Things, has generated increasingly intense pressure to develop intelligent wireless communication systems to meet networking needs posed by extremely high data rates, massive number of connected devices and ultra low latency. Based on that, he and his team applied deep learning (DL) as a design tool to advance the development of wireless communication system with some demonstrated success.


His team used DL to successfully estimate channel state information in MIMO wireless systems. In this talk, Prof. Ding specifically introduced the principles of applying DL for improving the performance of wireless networks by integrating the underlying characteristics of channels in practical massive MIMO deployment. They developed important insights derived from the physical RF channel properties and presented a comprehensive overview on the application of DL for accurately estimating channel state information of forward channels with low feedback overhead. 


丁峙3.jpg


During the Q&A session, Prof. Ding addressed the concerns from the audience, further explained the advantage of the research on model-driven DL approaches in physical layer communication, the portability of trained machine learning, and the feasibility of discovering the model pattern through neural networks.


丁峙4.jpg


Submit Message

Scan to Follow Up

Peng Cheng Laboratory | Disclaimer | 粤ICP备18066427号