We show that architectures from the machine learning domain of continual learning can help language models to procedurally learn facts about the world.
moreNews - Data Science Chair
We design a multi-agent simulation that can produce company data that also contains hidden fraud cases.
more
We rigorously evaluate commonly used approaches that explain the decisions of network attack detection systems.
more
In our work we propose a method for learning explicit representations of PDEs from non-grid data
moreBigData@Geo geht in die zweite Runde!
07/04/2023
Mehr kooperierende Betriebe, höhere Förderung, ein neuer Partner innerhalb der Uni: BigData@Geo geht in die zweite Runde und will mit Hilfe von Klimadaten konkrete Handlungsempfehlungen für Unternehmen mit Naturbezug erstellen.
more
In our work we present a benchmark dataset for learning forecasts of dynamical systems on non-grid structured data
more
In our paper we propose a method allowing the comparison of human behaviour across behavioural networks with different properties.
moreDr Anna Krause is co-organizing the workshop "Neuro-Explicit AI and Expert-Informed Machine Learning for Engineering and Physical Sciences (ExML)" at ECMLPKDD 2023.
more
In our paper, we conduct an initial study to investigate the use of audio data from the We4Bee project in detecting bee swarming.
moreCAIDAS at the ai.bay 2023
02/28/2023
