Abstract

As an emerging sub-field of machine learning, deep learning has become a prominent and rapidly growing research topic within communications. Deep learning applications in communication systems hold the potential to transform wireless communication in an unforeseen manner. In this talk, we discuss how deep learning can be applied to address the challenging requirements of the sixth generation (6G) wireless networks, particularly those related to reducing latency and complexity, and spectral efficiency. Specifically, this talk will focus on precoding and power allocation in multiple-input and multiple-output (MIMO) networks. We first introduce generic rotation-based precoding that can be applied to any MIMO channel. This approach converts the ubiquitous covariance matrix constraints to simple linear constraints that are tackled more efficiently. In the second part of the talk, we illustrate how deep neural networks (DNNs) can be applied for concurrent optimization and resource allocation in several state-of-the-art MIMO systems, including wireless information transfer, energy harvesting, physical layer security, and multicasting. We show that the deep learning-based solutions can provide near-optimal rates while substantially surpassing existing solutions in terms of delay and on-the-fly complexity. We then discuss the potential of deep learning-based precoding in addressing more challenging problems, like interference management in real-world wireless networks.

 

Bio

Mojtaba Vaezi received his Ph.D. in Electrical Engineering from McGill University in 2014 and held several research positions at Princeton University from 2015 to 2018. Since 2018 he has been an Assistant Professor of ECE at Villanova University, PA. His research interests include the broad areas of wireless communications, signal processing, machine learning and information theory, with an emphasis on beyond 5G radio access technologies, data-driven communications, low-latency communication, physical layer security, and Internet of things (IoT). Among his publications in these areas is the book Multiple Access Techniques for 5G Wireless Networks and Beyond (Springer, 2019). Dr. Vaezi has served as a president of McGill IEEE Student Branch and the head of Mobile Radio Network Design and Optimization Group at Ericsson. He is/was an Editor of IEEE Transactions on Communications, IEEE Communications Letters, and IEEE Communications Magazine, and the lead co-organizer of six International workshops at IEEE VTC 2017-Spring, Globecom’17, 18, and ICC’18, 19, 20. Dr. Vaezi is a recipient of several academic, leadership, and research awards, including the McGill Engineering Doctoral Award, the 2013 IEEE Larry K. Wilson Regional Student Activities Award, the NSERC Postdoctoral Fellowship in 2014, IEEE Communications Letters Exemplary Editor Award in 2019, and the 2020 IEEE Communications Society Fred W. Ellersick Prize.

 

Host

Prof. Amy Reibman, reibman@purdue.edu, (765) 496-0405