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

10-06-2025

Successful PhD Defense of Dr. Daniel Müllerklein

We are happy to celebrate the successful PhD defense of Daniel Müllerklein.

Under the supervision of Prof. Pirmin Fontaine, Daniel made significant contribution to the field of resilient supply chain management. He developed innovative data-driven solution approaches for strategic, tactical, and operational decision making. He applied advanced combinatorial optimization techniques, e.g. Benders decomposition, novel machine learning algorithms, and heuristics. His applications on real-world data showed the practicability of his methodological framework. Daniel is now continuing his career in the family-owned Borne Group as CEO. We wish him all the best for his future career and always a resilient supply chain in his business.

His PhD thesis resulted in four papers. One is already Published in the European Journal of Operational Research (VHB: A) and two are currently under review in two top-journals (both VHB: A):

Müllerklein, D., & Fontaine, P. (2025). Resilient transportation network design with disruption uncertainty and lead times. European Journal of Operational Research, 322(3), 827-840.
Müllerklein, D., Fontaine, P., & Ortmann, J. (2025). A Cost Focused Machine Learning framework for replenishment decisions under transportation cost uncertainty. Working Paper.
Müllerklein, D., & Fontaine, P., 2025. On product characteristics in a two-echelon resilient network design. Working Paper.
Müllerklein, D., 2025. A seven-step supply chain resilience framework for mitigating waterborne disruptions in transportation network design. Working Paper.

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.