This image shows Jannis Clausius, M.Sc.

Jannis Clausius, M.Sc.

Research Assistant
Institute of Telecommunications

Contact

+49 711 685 67929

Business card (VCF)

Pfaffenwaldring 47
70569 Stuttgart
Deutschland

Subject

My research interests focus on deep learning for communications, channel coding and in particular the combination of both. In the recent years, the application of deep neural networks in digital communication systems has been a hot topic. While it has been successful to exchange or support individual components of a system with deep learning, it remains an open problem to build a complete transmitter-receiver-pair based on neural networks that achieves state-of-the-art performance. I believe that a solution has to be approached in small steps, therefore I look into the joint optimization of several system components.

Moreover, a particulary appealing topic for me is deep learning based channel coding. I find the idea of extending the black box approach of Deep Learning to a field that relies so heavily on a mathematical backbone and the ingenuity of humans especially interesting. 

 

My current research interests are:

  • Combining deep learning based components of a digital communication system and joint optimization
  • Deep learning based channel codes
  1. 2023

    1. J. Clausius, M. Geiselhart, and S. ten Brink, “Component Training of Turbo Autoencoders.” 2023 [Online]. Available: https://arxiv.org/abs/2305.09216
    2. J. Clausius, M. Geiselhart, and S. ten Brink, “Optimizing Serially Concatenated Neural Codes with Classical Decoders.” 2023 [Online]. Available: https://arxiv.org/abs/2212.10355
  2. 2022

    1. J. Clausius, S. Dörner, S. Cammerer, and S. ten Brink, “On End-to-End Learning of Joint Detection and Decoding for Short-Packet Communications,” in 2022 IEEE Globecom Workshops (GC Wkshps), 2022, pp. 377–382 [Online]. Available: https://ieeexplore.ieee.org/document/10008594
  3. 2021

    1. J. Clausius, S. Dörner, S. Cammerer, and S. ten Brink, “Serial vs. Parallel Turbo-Autoencoders and Accelerated Training for  Learned Channel Codes.” 2021 [Online]. Available: http://arxiv.org/abs/2104.14234

Summer term 2021:

Winter term 2021/2022

Summer term 2022:

Jannis Clausius is a reserch staff memeber at the Institute of Telecommunications at the University of Stuttgart since March 2021. He received a B.Sc. degree in 2018 and a M.Sc. degree in 2021 in electrical engineering and information technology from the University of Stuttgart. His research focuses the application of deep learning in digital communication systems and channel coding.

To the top of the page