| Efficient decentralized deep learning by dynamic model averaging M Kamp, L Adilova, J Sicking, F Hüger, P Schlicht, T Wirtz, S Wrobel Joint European conference on machine learning and knowledge discovery in …, 2018 | 98 | 2018 |
| Pulse shape dependence in the dynamically assisted Sauter-Schwinger effect MF Linder, C Schneider, J Sicking, N Szpak, R Schützhold Physical Review D 92 (8), 085009, 2015 | 61 | 2015 |
| Inspect, understand, overcome: a survey of practical methods for AI safety S Houben, S Abrecht, M Akila, A Bär, F Brockherde, P Feifel, ... Deep Neural Networks and Data for Automated Driving, 3-78, 2022 | 26 | 2022 |
| Concurrent credit portfolio losses J Sicking, T Guhr, R Schäfer Plos one 13 (2), e0190263, 2018 | 8 | 2018 |
| Vertrauenswürdiger Einsatz von Künstlicher Intelligenz. Handlungsfelder aus philosophischer, ethischer, rechtlicher und technologischer Sicht als Grundlage für eine … AB Cremers, A Englander, M Gabriel, D Hecker, M Mock, M Poretschkin, ... Fraunhofer-Institut für intelligente Analyse-und Informationssysteme (IAIS …, 2019 | 6 | 2019 |
| Characteristics of monte carlo dropout in wide neural networks J Sicking, M Akila, T Wirtz, S Houben, A Fischer arXiv preprint arXiv:2007.05434, 2020 | 4 | 2020 |
| A Novel Regression Loss for Non-Parametric Uncertainty Optimization J Sicking, M Akila, M Pintz, T Wirtz, A Fischer, S Wrobel arXiv preprint arXiv:2101.02726, 2021 | 3 | 2021 |
| Vertrauenswürdiger Einsatz von Künstlicher Intelligenz AB Cremers, A Englander, M Gabriel, D Hecker, M Mock, M Poretschkin, ... Fraunhofer IAIS, 2019 | 3 | 2019 |
| Leitfaden zur Gestaltung vertrauenswürdiger Künstlicher Intelligenz (KI-Prüfkatalog) M Poretschkin, A Schmitz, M Akila, L Adilova, D Becker, AB Cremers, ... Fraunhofer IAIS, 2021 | 2 | 2021 |
| Approaching neural network uncertainty realism J Sicking, A Kister, M Fahrland, S Eickeler, F Hüger, S Rüping, P Schlicht, ... arXiv preprint arXiv:2101.02974, 2021 | 1 | 2021 |
| Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety S Rüping, E Schulz, J Sicking, T Wirtz, M Akila, SS Gannamaneni, M Mock, ... Deep Neural Networks and Data for Automated Driving: Robustness, Uncertainty …, 2022 | | 2022 |
| A Survey on Uncertainty Toolkits for Deep Learning M Pintz, J Sicking, M Poretschkin, M Akila arXiv preprint arXiv:2205.01040, 2022 | | 2022 |
| Tailored Uncertainty Estimation for Deep Learning Systems J Sicking, M Akila, JD Schneider, F Hüger, P Schlicht, T Wirtz, S Wrobel arXiv preprint arXiv:2204.13963, 2022 | | 2022 |
| Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities J Rosenzweig, J Sicking, S Houben, M Mock, M Akila Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | | 2021 |
| Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties J Sicking, M Akila, M Pintz, T Wirtz, A Fischer, S Wrobel arXiv preprint arXiv:2012.12687, 2020 | | 2020 |
| DenseHMM: Learning Hidden Markov Models by Learning Dense Representations J Sicking, M Pintz, M Akila, T Wirtz arXiv preprint arXiv:2012.09783, 2020 | | 2020 |
| Wasserstein Dropout J Sicking, M Akila, M Pintz, T Wirtz, A Fischer, S Wrobel arXiv e-prints, arXiv: 2012.12687, 2020 | | 2020 |
| Towards More Realistic Neural Network Uncertainties J Sicking, A Kister, M Fahrland, S Eickeler, F Hueger, S Rueping, ... | | 2019 |
| Trustworthy Use of Artificial Intelligence AB Cremers, A Englander, M Gabriel, D Hecker, M Mock, M Poretschkin, ... | | 2019 |
| Big Data, IOT und Machine Learning-Neue Perspektiven für Lastdaten und Schadensvorhersagen H Tiesler, M Messmer, N Paul, J Sicking | | 2019 |
Tim WirtzFraunhofer IAISGeverifieerd e-mailadres voor iais.fraunhofer.de
