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

09-28-2023

Preliminary course for the incoming Data Science students

We offer a preliminary course for the incoming data science students, in which we will recall some basic knowledge of mathematics from school, but also introduce some new contents that should enable a smooth start with the regular lectures. In addition, incoming students can already get into contact with fellow students and the data science student representatives, and get to know the Ingolstadt campus and city of Ingolstadt. The course takes place from October 4th to October 13th at the WFI in Ingolstadt. It starts on October 4th, 2023 at 9:30 in NB 101 (located at the WFI, Ingolstadt campus, Auf der Schanz, https://www.ku.de/unileben/campus-und-umfeld/lageplan/ingolstadt-neubau). The course is not mandatory and there will be no ECTS from this course. However, we highly recommend participating in the course and ask incoming students to register for the course on KU.campus using your student's login details if possible. In KU.campus you can also find detailed information about the detailed dates/times and lecture halls.

Registration for further first semester courses is also already possible on KU.campus. The proposed schedule and further information can be found here: https://www.ku.de/en/mgf/studiengaenge/bachelor/data-science

In addition to the pre course, we offer an introductory session on October 17th from 10-12 in NB 301 at WFI in Ingolstadt, where we and representatives from various facilities of the university provide further necessary information about the study program. For this event no registration is necessary.

Finally, general information about the orientation days at KU can be found following the link below. The listed activities are continuously updated.

https://www.ku.de/studium/informationen-fuer-studierende/orientierungswochen/bachelor

If there are any open questions, please do not hesitate to contact the student's subject advisor Raphael Schulz (raphael.schulz(at)ku.de) or the program's spokes person Nadja Ray (nadja.ray(at)ku.de).

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.