While in the past, performance has been the main focus of much work in AI, aspects of safety are increasingly recognised as similarly significant. This block seminar course on AI Safety will be held in English, towards the end of the 2023/2024 winter semester. Enrolment is restricted to 20 Master or senior Bachelor students, preferably with a background in AI (including methods from machine learning, optimisation, planning and scheduling, multi-agent systems and other areas of AI). Students will work in groups of two on a range of topics from AI Safety, which spans the robustness and verification of AI methods, including - but not restricted to - neural networks; the explainability and interpretability of the results obtained from AI algorithms; as well as bias and privacy issues in machine learning. Each group will be assigned recently published work from the research literature, which will serve as the starting point for an in-depth investigation of a specific topic; the results of this investigation will be presented in class and compiled into a report.
Preferably students should have a background in AI (including methods from machine learning, optimisation, planning and scheduling, multi-agent systems and other areas of AI).
Registration to the seminar is handled via the SuPra system.
Prof. Dr. Holger H. Hoos
Chair Holder, Alexander von Humboldt Professor
E-mail: hh[at]aim[dot]rwth-aachen[dot]de
Phone: +49 241 80 21451
Dr. Jakob Bossek
Assistant Professor (Akademischer Rat)
E-mail: bossek[at]aim[dot]rwth-aachen[dot]de
Phone: +49 241 80 21453
