Annual VeriKAS Project Meeting

10 February 2025

We had a very successful meeting for the VeriKAS project on the 23^rd of January in Hamburg. With the tremendous success of data-driven approaches in neural networks for detection, decision-making and robot tasks, the debate on the weak interpretability of the “black-box” model becomes more intense. The VeriKAS project is a BMWi funded project that aims to realize robust explanation and certification of deep learning-based systems, in collaboration with our project partners ZAL, HITeC and hs2. For some of our recent publications in this context see recent papers by Habekost, Gromniak, Lu or Magg on here.