The research group "Reliable Machine Learning" studies the properties of machine learning algorithms. In view of the recent success of deep learningmethods 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.
Once again this year, the professors of MIDS have invited to a joint pizza evening at the start of the new semester. After the institute was finally able to move into the beautiful rooms of the Georgianum, the event took place there. This gave the new first semester students the opportunity to get to know not only the third semester students but also the offices of the MIDS staff.
The professors involved in the course attach great importance to the good relationship and short distances to the students, which is why we are delighted that the evening was so well received again in 2023.
