In the beginning of March all member of the DFG priority program 2089 "Rhizoshphere Spatiotemporal Organisation" meet for their annual meeting at Leipzig. The main aim of the 27 project partners is the identification of spatiotemporal patterns in the rhizosphere and the explanation of the underlying mechanisms. In her project, Prof. Dr. Nadja Ray from MIDS together with the Co-PI Alexander Prechtel from FAU and the doctoral student Maximilian Rötzer investigate the mutual interaction between root growth/decay and the soil structure by means of mathematical modeling and numerical simulations.
Welcome to the website of the Chair of Reliable Machine Learning
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".
About us
Math News
SPP annual meeting at Leipzig
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.