- This event has passed.
Deep Learning for the Physical Layer with Sionna
November 16 @ 5:00 pm - 6:00 pm
Deep Learning for the Physical Layer with Sionna By: Dr. Sebastian Cammerer ZOOM LINK INFORMATION https://uqtr.zoom.us/j/82531800033?pwd=QmxCZHorRzlieUxyUHhsY1dQTHdaQT09 ID de réunion : 825 3180 0033 Mot de passe : 550807 Abstract Machine learning for wireless communications has become an omnipresent tool in wireless communications research and it is foreseeable that it will play an increasingly important role in the future evolution of 5G as well as the development of 6G. This trend is supported by the recent 3GPP announcement to promote AI/ML as a new study item for the upcoming Release 18. To support these efforts, we present Sionna, a new open-source software library for GPU-accelerated link-level simulations and 6G research. Sionna enables rapid prototyping of complex communication system architectures and provides native support for the integration of neural networks. In the second part of the talk, we demonstrate AI/ML use-cases for the PHY layer and showcase the benefits of a data-driven system design which does not need to rely on any prior mathematical modelling and analysis of the channel. Biography Dr. Sebastian Cammerer is a Research Scientist at NVIDIA. Before joining NVIDIA, he received his PhD in electrical engineering and information technology from the University of Stuttgart, Germany, in 2021. He is one of the maintainers and core developers of the Sionna open-source link-level simulator. His main research topics are machine learning for wireless communications and channel coding. Further research interests include modulation, parallel computing for signal processing, and information theory. He is recipient of the VDE ITG Dissertationsaward 2022, the IEEE SPS Young Author Best Paper Award 2019, the Best Paper Award of the University of Stuttgart 2018, the Anton- und Klara Röser Preis 2016, the Rohde&Schwarz Best Bachelor Award 2015, and third prize winner of the Nokia Bell Labs Prize 2019 Virtual: https://events.vtools.ieee.org/m/328923