Am Freitag, den 14. Juli 2023, hat Dr.-Ing. Tanja Dorst im Rahmen ihres öffentlichen Promotionskolloquiums ihre Dissertation vorgestellt und erfolgreich verteidigt - herzlichen Glückwunsch vom ganzen LMT-Team!

Ein ganz besonderer Dank gilt Prof. Dr.-Ing. Rainer Tutsch, TU Braunschweig, der als Zweitgutachter die Promotion bewertet hat, leider nur online dabei sein konnte. Den Vorsitz der Promotionskommission hatte Prof. Dr. Romanus Dyczij-Edlinger übernommen, Dr. Amine Othmane wirkte als akademischer Beisitzer mit.

On Friday, July 14, 2023, Dr.-Ing. Tanja Dorst defended her PhD thesis in a public doctoral thesis defense - all the best from the team at LMT.

Titel / title:
Measurement uncertainty in machine learning - uncertainty propagationand influence on performance

This thesis combines measurement uncertainty based on the principles of the Guide to the Expression of Uncertainty in Measurement (GUM) and machine learning. To perform machine learning, a data pipeline that fuses raw data from different measurement systems and determines measurement uncertainties from dynamic calibration information is presented. Furthermore, a previously published automated toolbox for machine learning is extended to include uncertainty propagation based on the GUM and its supplements. Using this uncertainty-aware toolbox, the influence of measurement uncertainty on machine learning results is investigated, and approaches to improve these results are discussed.

Offizieller Aushang / official announcement