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

06-02-2026

Participation in Digi:Werk10

The Mathematical Institute for Machine Learning and Data Science (MIDS) at the Catholic University of Eichstätt-Ingolstadt was also represented at DigiWerk10, a networking event organized by KUS in Reichertshausen (Pfaffenhofen district). Faculty and students presented current work in the fields of data science, AI, and scientific machine learning. Among those in attendance were Dr. Felix Bartel, Dr. Jörg Steinwagner, and Elisabeth Schönau and Andrei Dolmatov, students in Prof. Tijana Janjić’s department.

The event also highlighted the practical approach of MIDS and the Catholic University in collaboration with regional partners. In collaboration with the company Aixelo, it became clear how partnership between the university and industry is already being put into practice during students’ studies. For example, Minh Tran, a MIDS student, completed an internship at Aixelo and, together with company owner Christoph Kreisbeck, presented the results of this collaboration. The exchange illustrated how scientific methods from AI and data science can be transferred to concrete industrial applications.

Through initiatives such as DigiWerk10, MIDS and KU are actively engaged in the Region10 and are strengthening the network between research, students, companies, and societal stakeholders.

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.