Deniz Gündüz received the M.S. and Ph.D. degrees in electrical engineering from NYU Tandon School of Engineering (formerly Polytechnic University) in 2004 and 2007, respectively. After his PhD, he served as a postdoctoral research associate at Princeton University, and as a consulting assistant professor at Stanford University. From Sep. 2009 until Sep. 2012 he was a research associate at CTTC in Barcelona, Spain. In Sep. 2012, he joined the Electrical and Electronic Engineering Department of Imperial College London, UK, where he is currently a Professor in Information Processing, and leads the Information Processing and Communications Laboratory (IPC-Lab). He is also a part-time faculty member at the University of Modena and Reggio Emilia, and has held visiting positions at University of Padova (2018-2020) and Princeton University (2009-2012).
Dr. Gündüz has served in various editorial roles for the IEEE Transactions on Communications, IEEE Journal on Selected Areas in Communications (JSAC), IEEE Transactions on Wireless Communications, and IEEE Transactions on Green Communications and Networking. He is a Distinguished Lecturer for the IEEE Information Theory Society (2020-22). He is the recipient of the IEEE Communications Society – Communication Theory Technical Committee (CTTC) Early Achievement Award in 2017, a Starting Grant of the European Research Council (ERC) in 2016, and the IEEE Communications Society Best Young Researcher Award for the Europe, Middle East, and Africa Region in 2014. He coauthored papers that received Best Paper Awards at the 2019 IEEE GlobalSIP and 2016 IEEE WCNC, and Best Student Paper Awards at 2018 IEEE WCNC and 2007 IEEE ISIT. He served as a Symposium Co-Chair for the 2020 IEEE ICC, and as a General Co-chair of the 2019 London Symposium on Information Theory, 2018 International ITG Workshop on Smart Antennas, and 2016 IEEE Information Theory Workshop.
Invited Talk: Distributed AI at the Wireless Edge
Abstract: IoT devices collect significant amount of data at the wireless edge, opening up new potentials for AI applications. Current approach to edge intelligence is to offload all the collected data to a cloud server to be processed by advanced machine learning algorithms. This approach is not sustainable considering the expected growth in the number of IoT devices and the traffic they generate. Moreover, it creates significant privacy risks for the users, and introduces delays that cannot be tolerated by most applications. The alternative is to bring the intelligence to the edge, by distributing both the training and the inference tasks across edge devices and servers. In this talk, I will argue how coding and communication techniques need to be incorporated into the distributed learning paradigm to achieve efficient and seamless distributed edge intelligence that is robust against wireless channel impairments and resource limitations.