Il DIEF ha ospitato il prof. Deniz Gunduz dellImperial College London
Al Dipartimento di Ingegneria Enzo Ferrari di Unimore si è tenuto il seminario Learn to Communicate - Communicate to Learn del prof. Deniz Gunduz dellImperial College London, con la partecipazione del Rettore Angelo O. Andrisano.
Di seguito un abstract dellincontro:
In the first part of this talk I will explore how modern machine learning techniques, particularly deep neural networks, can be used to improve wireless communication systems. I will first introduce a novel uncoded "analog communication technique for wireless image transmission, and show its surprising performance both through simulations and practical implementation. This result will motivate leveraging unsupervised learning techniques for wireless image transmission. Surprisingly, the "deep joint source-channel encoder I will present behaves similarly to analog transmission; it not only improves upon state-of-the-art digital transmission techniques, but also achieves graceful degradation with channel quality, and performs exceptionally well under extreme delay constraints and over time-variant channels, making it particularly attractive for emerging applications such as the Internet of things, vehicular communications, and tactile Internet. In the second part of the talk, I will focus on distributed machine learning algorithms in the presence of straggling servers. I will show how ideas from coding theory can be leveraged to speed up distributed gradient descent, which is essential to implement large scale learning tasks over hundreds of machines in parallel.
Deniz Gunduz received his M.S. and Ph.D. degrees in electrical engineering from NYU Polytechnic 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. He was a research associate at CTTC in Barcelona, Spain until 2012, when he joined the Electrical and Electronic Engineering Department of Imperial College London, UK, where he is currently a Reader (Associate Professor) in information theory and communications, and leads the Information Processing and Communications Lab (http://www.imperial.ac.uk/ipc-lab).
His research interests lie in the areas of information theory, machine learning, communications and privacy. Dr. Gunduz is an Editor of the IEEE Transactions on Green Communications and Networking, and served as an Editor of the IEEE Transactions on Communications (2013-2018). 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, IEEE Communications Society Best Young Researcher Award for the Europe, Middle East, and Africa Region in 2014, Best Paper Award at the 2016 IEEE Wireless Communications and Networking Conference (WCNC), and the Best Student Paper Awards at the 2018 IEEE Wireless Communications and Networking Conference (WCNC) and the 2007 IEEE International Symposium on Information Theory (ISIT). He served as the General Co-chair of the 2018 International ITG Workshop on Smart Antennas, 2016 IEEE Information Theory Workshop, and the 2012 IEEE European School of Information Theory.