Using Bayesian Neural Networks in Communication Systems

Tutor: Tim Düe
Type of Thesis: Project (MSc), Master's thesis (MSc), Bachelor thesis (BSc.)
date of issue: 04/2024
Student: -
Status: available


Bayesian Neural Networks (BNNs) are a derivation of the traditional Neural Networks (NNs), represent parameters by distributions instead of singular values. This leads to BNNs being able to incorporate more system information and result in not only results but also the certainty of the results inherently. As communications has a probabilstic nature, BNNs may be a promissing approach for signal processing. The task in this thesis/project is to investigate the general applicability of BNNs for communications systems.


The final objectives will be agreed on together with the student, the following is only a suggestion.

  • Investigate the applicability of BNNs for communications scenarios
  • Compare the BNN based solutions with traditional NN based and not NN based solutions


Ideally you fullfill the following criteria. If your profile varies but you are still interested in the project, you may contact me anyways.

  • Solid programming skills in Python 
  • Ideally experience with Tensorflow 
  • Basic knowledge of ML 
  • Fundamental knowledge of baseband processing in communication systems

Further Information:

For further information feel free to contact me via E-Mail (
Last change on 15.04.2024 by T. Düe
AIT ieee GOC tzi ith Fachbereich 1
© Department of Communications Engineering - University of BremenImprint / Contact