233 citations
- BMW Group (Germany)DE23 papers
- Technical University of MunichDE19 papers
- Ludwig-Maximilians-Universität MünchenDE8 papers
- University of StuttgartDE6 papers
- Universität UlmDE4 papers
- Google (Switzerland)CH3 papers
- Robert Bosch (Germany)DE3 papers
- Siemens (Germany)DE3 papers
- Amazon (United States)US2 papers
- ETH ZurichCH2 papers
- Infineon Technologies (Germany)DE2 papers
- Istituto Nazionale di Fisica NucleareIT2 papers
4 papers · 1 filter
Sensitivity analysis of image classification models using generalized polynomial chaos
Lukas Bahr, Lucas Poßner, Konstantin Weise +2
Integrating advanced communication protocols in production has accelerated the adoption of data-driven predictive quality methods, notably machine learning (ML) models. However, ML…
Neural Networks for Generating Better Local Optima in Topology Optimization
Leon Herrmann, Ole Sigmund, Viola Muning Li +2
Neural networks have recently been employed as material discretizations within adjoint optimization frameworks for inverse problems and topology optimization. While advantageous re…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…
Deep Inverse Q-learning with Constraints
Gabriel Kalweit, Maria Huegle, Moritz Werling +1
Popular Maximum Entropy Inverse Reinforcement Learning approaches require the computation of expected state visitation frequencies for the optimal policy under an estimate of the r…