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

10-02-2026

MAS-TOB at the BMFTR Status Meeting “Mathematics for Innovation”

On October 1–2, 2026, the status meeting “Mathematics for Innovation” took place at the Federal Ministry of Research, Technology and Space (BMFTR) in Bonn. Among the projects represented was “MAS-TOB: Multiscale Analysis and Structural Optimization of Patient-Specific Therapeutic Orthoses and Bandages,” which started earlier this year and is funded for a period of three years.

The project team from the three participating institutions (Fraunhofer ITWM Kaiserslautern, RPTU Kaiserslautern-Landau, and KU Eichstätt-Ingolstadt) was represented by Anna Simon and Prof. Dr. Carolin Kreisbeck from the Chair of Analysis at KU, as well as Dr. Julia Orlik from Fraunhofer ITWM. Anna Simon presented MAS-TOB as part of the short presentation sessions. The subsequent poster session provided further opportunities for stimulating discussions and scientific exchange.

A central goal of MAS-TOB is to develop a methodology and, building on this, a software solution in the form of a digital twin that can predict how different knitted fabrics need to be printed to achieve targeted local stiffening and restrictions of movement. The project team works closely with the industry partner Sporlastic in this context.

A distinctive feature of the collaborative project is its interdisciplinary approach, bringing together different areas of mathematics and connecting them closely with applications:

from modeling and analysis through optimization, numerical methods, and simulation to their implementation in patient-specific products.

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.