341 citations
- Volkswagen Group (United States)US10 papers
- Technical University of MunichDE7 papers
- Eötvös Loránd UniversityHU5 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE5 papers
- RWTH Aachen UniversityDE5 papers
- Michigan State UniversityUS4 papers
- Technische Universität BraunschweigDE4 papers
- Ludwig-Maximilians-Universität MünchenDE3 papers
- Technische Universität DarmstadtDE3 papers
- Xanadu Quantum Technologies (Canada)CA3 papers
- BMW (Germany)DE2 papers
- École Polytechnique Fédérale de LausanneCH2 papers
12 papers · 1 filter
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink +6
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional ne…
Quantum algorithms with local particle number conservation: noise effects and error correction
Michael Streif, Martin Leib, Filip Wudarski +2
Quantum circuits with local particle number conservation (LPNC) restrict the quantum computation to a subspace of the Hilbert space of the qubit register. In a noiseless or fault-t…
Beating classical heuristics for the binary paint shop problem with the quantum approximate optimization algorithm
Michael Streif, Sheir Yarkoni, Andrea Skolik +2
The binary paint shop problem (BPSP) is an APX-hard optimization problem of the automotive industry. In this work, we show how to use the Quantum Approximate Optimization Algorithm…
Forbidden subspaces for level-1 QAOA and IQP circuits
Michael Streif, Martin Leib
We present a thorough investigation of problems that can be solved exactly with the level-1 Quantum Approximate Optimization Algorithm (QAOA). To this end we implicitly define a cl…
Dalek -- a deep-learning emulator for TARDIS
Wolfgang E. Kerzendorf, Christian Vogl, Johannes Buchner +3
Supernova spectral time series contain a wealth of information about the progenitor and explosion process of these energetic events. The modeling of these data requires the explora…
Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning
Sascha Rosbach, Xing Li, Simon Großjohann +2
General-purpose trajectory planning algorithms for automated driving utilize complex reward functions to perform a combined optimization of strategic, behavioral, and kinematic fea…