M.Sc. Francesca Diedolo
Technical University of Munich
Chair of Communications Engineering (Prof. Kramer)
Postal address
Postal:
Theresienstr. 90
80333 München
Biography
- Doctoral researcher at the Chair of Communications Engineering at TUM since February 2021
- M.Sc. in Communications Engineering at TUM, 2018-2020
- B.Sc. in Electrical Engineering and Information Technology at Università degli Studi di Padova, 2015-2018
Theses in Progress
Geometric and Probabilistic Constellation Shaping via end-to-end Learning
Description
Prerequisites
Information Theory
Coded Modulation
Machine Learning
Supervisor:
Geometric and Probabilistic Constellation Shaping via end-to-end Learning
Description
When designing constellations, both the locations and probability of occurrence of the points can be optimized. These approaches are referred to as geometric and probabilistic shaping, respectively.
The papers [1], [2], [3] explain how this optimization can be performed with a trainable autoencoder structure.
The seminar consists in understanding and summarizing the history of this topic.
When designing constellations, both the locations and probability of occurrence of the points can be optimized. These approaches are referred to as geometric and probabilistic shaping, respectively.
The papers [1], [2], [3] show how this optimization can be performed with a trainable autoencoder structure.
The seminar consists in understanding and summarizing the history of this topic.
[1] https://arxiv.org/abs/2112.05050
[2] https://ieeexplore.ieee.org/abstract/document/9024567
[3] https://ieeexplore.ieee.org/abstract/document/9348032
Prerequisites
Information Theory
Coded Modulation
Machine Learning
Supervisor:
2022
2021
- Label Extension for 32QAM: The Extra Bit for a Better FEC Performance-Complexity Tradeoff. 2020 European Conference on Optical Communications (ECOC), IEEE, 2021 more… BibTeX Full text ( DOI )