Master and Bachelor Thesis Supervision (public landing page)
General procedure
After the supervisor has been found (see below), the student must write a proposal that includes the research question and its context/motivation, related work, preliminary methodological and/or experimental results, and formalities such as time constraints. After Prof. Müller approves the proposal, the student can register the thesis, and the writing period begins (typically three months for BA and six months for MA). This implies that a thesis often requires more time than the official writing period. It might be possible to hand in the thesis early (check with the respective examination regulations for the student’s degree program). However, we encourage significant time between registration and submission.
Though our group tries to supervise as many students as possible, we typically do not have the capacity to supervise every interested student.
Finding a supervisor
Interested students should provide a curriculum vitae/resume. Among other relevant aspects, this document should inform about the grades in relevant modules. Prior knowledge of machine learning is mandatory, e.g., as acquired through the courses offered by our group. Students should also describe their research interests/ideas, including suitable and proven skills, e.g., in Python programming, mathematics, or scientific writing. Optionally, it is possible to suggest own topics.
Our senior researchers can identify suitable internally advertised topics or suggest suitable supervisors within our group:
ML for Quantum Chemistry: Stefan Chmiela (stefan@chmiela.com)
Kernel Learning: Stefan Chmiela (stefan@chmiela.com)
Explainable AI: Grégoire Montavon (gregoire.montavon@tu-berlin.de)
Anomaly detection/Unsupervised learning: Robert Vandermeulen (vandermeulen@tu-berlin.de)
Probabilistic modeling and inference: Shinichi Nakajima (nakajima@tu-berlin.de)
Time series analysis and signal processing: Andreas Ziehe (andreas.ziehe@tu-berlin.de)
Multimodal signal acquisition and analysis - neurotechnology + biomedical sensing: Alexander von Lühmann (vonluehmann@tu-berlin.de)
ML for Security & Privacy: Daniel Arp (d.arp@tu-berlin.de)
Alternatively, it is possible to contact junior researchers directly with specific ideas or inquiries:
- Learning with multiple modalities: Jannik Wolff (wolff [dot] jannik [at] icloud.com)
Robustness against spurious correlations in DNNs, neural cellular automata: Lorenz Linhardt (l.linhardt@campus.tu-berlin.de)
You can find further information about our group members, including their research, on our group's publication list and the BIFOLD website.
Open topics
Group members can find open topics in our internal wiki.