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

05-19-2026

New Scientific Director at MIDS

Dr. Jörg Steinwagner is the new Scientific Director at MIDS since May 1, 2026.
He also supports Professor Janjic’s research group (Chair of Data Assimilation), thereby combining research, teaching, and knowledge transfer. He holds a Ph.D. in meteorology and has many years of experience in the development of data-driven methods, particularly in the fields of satellite-based remote sensing and numerical modeling. His professional career includes work on international research and development projects, including in the areas of Earth observation and weather forecasting.

A key focus of his current work is the design and implementation of knowledge transfer formats on AI and digitalization, as well as the preparation of scientific content tailored to specific audiences for stakeholders from academia, industry, and society. In addition, he develops consulting services and supports the establishment of regional networks, including in cooperation with partners such as AININ and brigk.

Within the context of MIDS, he coordinates key activities such as the Jour Fix, contributes to strategic development, organizes scientific events, and assists with third-party funding applications. In Prof. Janjic’s research group, he is involved in both research and teaching, works on data-driven models and HPC applications, and supports ongoing research projects.

His work helps strengthen the regional AI ecosystem and fosters close collaboration between research and practical application. We are very much looking forward to working with him and warmly welcome him to MIDS.

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.