Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Raab, René"'
Autor:
Schwinn, Leo, Bungert, Leon, Nguyen, An, Raab, René, Pulsmeyer, Falk, Precup, Doina, Eskofier, Björn, Zanca, Dario
The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and per
Externí odkaz:
http://arxiv.org/abs/2205.09619
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify promising appr
Externí odkaz:
http://arxiv.org/abs/2105.10304
Publikováno v:
International Conference on Scale Space and Variational Methods in Computer Vision, 307-319, 2021
Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible input perturbations, so called ad
Externí odkaz:
http://arxiv.org/abs/2103.12531
Autor:
Schwinn, Leo, Nguyen, An, Raab, René, Bungert, Leon, Tenbrinck, Daniel, Zanca, Dario, Burger, Martin, Eskofier, Bjoern
The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either require a re-
Externí odkaz:
http://arxiv.org/abs/2102.12196
Autor:
Schwinn, Leo, Nguyen, An, Raab, René, Zanca, Dario, Eskofier, Bjoern, Tenbrinck, Daniel, Burger, Martin
The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. Although several sophisticated defense mechanisms have been introduced, most were later shown to be ineffect
Externí odkaz:
http://arxiv.org/abs/2011.02707
Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are accompanied by
Externí odkaz:
http://arxiv.org/abs/2002.10097
Autor:
Raab, René, Küderle, Arne, Zakreuskaya, Anastasiya, Stern, Ariel D, Klucken, Jochen, Kaissis, Georgios, Rueckert, Daniel, Boll, Susanne, Eils, Roland, Wagener, Harald, Eskofier, Bjoern M *
Publikováno v:
In The Lancet Digital Health November 2023 5(11):e840-e847
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
International Journal of Environmental Research & Public Health; Apr2023, Vol. 20 Issue 7, p5378, 16p