Virtual Seminar: Trainable Communication Systems: Concepts and Prototype

Friday, October 02, 2020
9:00am - 10:00am

We revisit the fundamental problem of physical layer communications, namely reproducing at one point a message selected at another point, to finally arrive at a trainable system that inherently learns to communicate and adapts to any channel environment. As such, we realize a data-driven system design, based on deep learning algorithms, leading to a universal framework that allows end-to-end optimization of the whole data-link without the need for prior mathematical modeling and analysis. A trainable communication system inherently tolerates and even exploits effects which are difficult to model, such as hardware imperfections and channel uncertainties. We show that such systems not only enjoy a competitive and in some cases even superior performance, but facilitate a simplified design flow due to their conceptual elegance and, hence, may trigger a paradigm shift of how we design future communication systems. We thus pose the seemingly simple, naive, yet in fact rather complicated and attractive research question: Can we learn to communicate?

The goal of this talk is to provide an introduction to the rapidly growing field of end-to-end learning of physical layer communications. For this, we reinterpret transceiver signal-processing blocks (e.g., quantization, coding, modulation, detection) as neural networks and show that this idea enables data-driven communication systems that perpetually learn and adapt to (m)any environment(s). Further, we show that the practical realization of end-to-end training of communication systems is fundamentally limited by its accessibility of the channel gradient. To overcome this major burden, the idea of generative adversarial networks (GANs) that learn to mimic the actual channel behavior has been recently proposed in the literature. Contrarily to handcrafted classical channel modeling, which can never fully capture the real world, GANs promise, in principle, the ability to learn any physical impairment, enabled by the data-driven learning algorithm. We verify the concept of GAN-based autoencoder training in actual over-the air (OTA) measurements.

In the second part of this talk, we show how training of autoencoder-based communication systems on the bit-wise mutual information allows seamless integration with practical bit metric decoding receivers, as well as joint optimization of constellation shaping and labeling. Additionally, we present a fully differentiable neural iterative demapping and decoding structure which achieves significant gains on additive white Gaussian noise channels. Going one step further, we show that careful code design can lead to further performance improvements. 


Access: Seminar was delivered live via Zoom on October 2; watch the recording here.


Photo: Sebastian Cammerer
University of Stuttgart, Germany

Sebastian Cammerer received the B.Sc. and M.Sc. degrees (Hons.) in electrical engineering and information technology from the University of Stuttgart, Germany, in 2013 and 2015, respectively, where he is currently pursuing the Ph.D. degree. During his years of study, he worked as a Research Assistant at multiple institutes of the University of Stuttgart. Since 2015, he has been a member of the research staff at the Institute of Telecommunications, University of Stuttgart. His main research topics are channel coding and machine learning for communications. Furthermore, his research interests are in the areas of modulation, parallelized computing for signal processing, and information theory. He is a recipient of the Best Publication Award of the University of Stuttgart 2019, the Anton- und Klara Röser Preis 2016, the Rohde&Schwarz Best Bachelor Award 2015, and the VDE-Preis 2016 for his master thesis.