Welcome to the website of the Chair of Reliable Machine Learning

Machine Learning Laptop — © colourbox.de

The research group "Reliable Machine Learning" studies the properties of machine learning algorithms.
In view of the recent success of deep learning methods in applications like image recognition, speech recognition, and automatic translation, the group especially focuses on properties of deep neural networks.

Although a neural network trained e.g. for an image classification task might work well on "real inputs", it has been repeatedly shown empirically that such networks are vulnerable to adversarial examples:
a minimal perturbation (impercetible to a human) of the input data can cause the network to misclassify the input.
Thus, an important research area of the group is to mathematically understand the reasons for the existence of such adversarial examples (i.e., the instability of trained neural networks),
and - building on that understanding - to develop improved methods that yield provably robust neural networks.

The research group is supported by the Emmy Noether project "Stability and Solvability in Deep Learning".

Content of Chair of reliable machine learning

About us

The Team

Publications

Contact

Math News

04-30-2026

Successful PhD Defense of Dr. Johannes Gückel

We are pleased about the successful PhD defense of Johannes Gückel.

Under the supervision of Prof. Pirmin Fontaine, Johannes made a significant contribution to the field of urban logistics and collaboration among logistics service providers. He developed innovative mathematical models, metaheuristics, and machine learning approaches to design efficient and fair cooperative city logistics systems. His work particularly addresses network design, fair cost allocation, and the practical implementation of collaboration concepts. The results demonstrate how efficiency and fairness can be jointly considered in urban freight systems. Johannes now continues his career as a Data Scientist at dm-drogerie markt. We wish him all the best for his future career.

His dissertation resulted in four scientific articles, which have been published or accepted for publication in renowned academic journals:

Gückel, J., Crainic, T.G., & Fontaine, P. (2026). A two-step large neighborhood search for a collaborative two-tier city logistics system. European Journal of Operational Research (VHB: A).
Gückel, J., Crainic, T.G., & Fontaine, P. (2025). Tactical planning in cooperative two-tier city logistics systems with fairness constraints. Sustainability Analytics and Modeling (VHB: B).
Gückel, J., & Fontaine, P. (2025). Fast Shapley Value Approximation Through Machine Learning With Application in Routing Problems. Networks (VHB: A).
Gückel, J. (2025). Approximating Shapley values with subcoalition Shapley values in routing problems. Transportation Research Procedia (VHB: C).

MIDS Seminar

Mathematical Institute for Machine Learning and Data Science

The Chair of Reliable Maschine Learning is part of the Mathematical Institute for Machine Learning and Data Science, MIDS.
Learn more about MIDS here.