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

05-22-2023

Get to know Data Science at KU

On May 05, the Long Night of Science took place in Ingolstadt and on May 06, KU welcomed all interested people to the Open Day. Also MIDS was involved with some actions.

At the beginning of May, there was a lot going on for people interested in science and those who wanted to find out more about studying. KU offered a diverse program in Eichstätt and Ingolstadt and also MIDS informed about its research topics and the study program Data Science.

Prof. Nadja Ray, Prof. Thomas Setzer and Dr. Raphael Schulz had, in addition to mathematical puzzles and general information about the new bachelor's program, interesting presentations, for example on "How do Amazon and Netflix know what we want?" and "The page rank algorithm: What's behind the Google search engine?". The visitors got an insight into what is behind the big term "machine learning" and were also able to ask their questions about it.

For students interested in studying mathematics at KU, not only the direct exchange with the professors and the numerous information material was helpful. The Data Science student council was also available for personal feedback.

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.