Felix Friedrich
Machine Learning Group, Computer Science Department, TU Darmstadt. Hochschulstrasse 1, Room S1|03 075, 64289 Darmstadt, Germany
friedrich (at) cs (dot) tu-darmstadt (dot) de

Open Thesis/Hiwi. We developed an interactive and interpretable Language Model (see publication below) and now want to conduct further research on it. One central point is to conduct an extensive user study. Here we want the users to interact with explanations. So it would be helpful if you have knowledge in that area, but it is definitely not required. It could also be an option to develop a GUI for a study with multiple questions. Furthermore, we want to extend the model's capability for word-level explanations and some more. Here it is helpful if you are familiar with Python, PyTorch, and Deep Learning in general. In terms of workload, it rather looks like a bachelor thesis/Hiwi position, but we can also think about a master thesis. Please feel free to contact me in case of interest.

Mission. My research interests are centered around artificial intelligence (AI) and how we can make these AI systems socially acceptable. My focus is to improve the explainability (XAI) and interpretability of deep learning models. Inspiration for XAI solutions can come from cognitive science, since the exploration and consideration of human behavior is inevitable and possibly the best motivation for precisely this human-machine interaction (XIL). This not only offers a better understanding of machine learning models, but uses human capabilities to incorporate knowledge outside of the rigid range of purely data-driven approaches.

2021 - now: Ph.D. student at the Machine Learning Lab, CS Department, TU Darmstadt, Germany.
2020: Erasmus+ at Chalmers University of Technology in Gothenburg, Sweden.
2019 - 2021: M.Sc. in computer science with minor in psychology from TU Darmstadt, Germany.
2018 - 2021: M.Sc. (with honors) in autonomous systems from TU Darmstadt, Germany.
2017: Research internship on intelligent autonomous driving systems at IAV GmbH, Germany.
2014 - 2017: B.Sc. in electrical engineering from TU Dortmund, Germany.

Supervised Courses.
WS 2021/22 Prof. Dr. Kristian Kersting, Introduction in AI
SS 2021 Prof. Dr. Kristian Kersting, Deep Learning: Architectures and Methods
SS 2020 Prof. Dr. Kristian Kersting, Statistical Machine Learning


Publications can be found at DBLP, SemanticScholar