Publications

2022

  1. Towards Explainable Artificial Intelligence: Interpreting Neural Network Classifiers with Probabilistic Prime Implicants
    Stephan Wäldchen
    2022
  2. A Complete Characterisation of ReLU-Invariant Distributions
    Jan Macdonald, and Stephan Wäldchen
    In International Conference on Artificial Intelligence and Statistics, 2022
  3. Training characteristic functions with reinforcement learning: Xai-methods play connect four
    Stephan Wäldchen, Sebastian Pokutta, and Felix Huber
    In International Conference on Machine Learning, 2022

2021

  1. The computational complexity of understanding binary classifier decisions
    Stephan Wäldchen, Jan Macdonald, Sascha Hauch, and 1 more author
    Journal of Artificial Intelligence Research, 2021

2020

  1. Time-resolved response of cerebral stiffness to hypercapnia in humans
    Bernhard Kreft, Heiko Tzschätzsch, Felix Schrank, and 6 more authors
    Ultrasound in Medicine & Biology, 2020
  2. Explaining neural network decisions is hard
    Jan Macdonald, Stephan Wäldchen, Sascha Hauch, and 1 more author
    In XXAI Workshop, 37th ICML, 2020

2019

  1. Unmasking Clever Hans predictors and assessing what machines really learn
    Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, and 3 more authors
    Nature communications, 2019
  2. A rate-distortion framework for explaining neural network decisions
    Jan MacDonald, Stephan Wäldchen, Sascha Hauch, and 1 more author
    arXiv preprint arXiv:1905.11092, 2019

2016

  1. Renormalizing entanglement distillation
    Stephan Waeldchen, Janina Gertis, Earl T Campbell, and 1 more author
    Physical Review Letters, 2016