In the last years machine learning methods had a high impact in academic and daily live. They already outperform several classical applications and gain rapidly of importance. Also in several safety critical systems machine learning methods would be beneficial to use. To guaranty save deployment the residual risk should be under an acceptable level. In classical systems there are several proceedings to determine this risk. But for a lot of machine learning components the safety engineering methods are not applicable.

My research is focused on Residual Risk Analysis for Systems with Machine Learning Components. I try to develop new methods and models which capture the risk and uncertainty inside such systems.

Winter Term 2023/ 2024:

• Quality Management and Quality Assurance of Software (QMQA)

Sommer Term 2023:

• Modellierung von Software-Systemen

Winter Term 2022/ 2023:

• Software Engineering Project, Bachelor and Master Project
• Quality Management and Quality Assurance of Software (QMQA)
• Safety and Reliability of Embedded Systems (SRES)