Zobrazeno 1 - 10
of 3 276
pro vyhledávání: '"Weißenbacher A"'
An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as well as semantically-similar environments. We introduce Symmetry-Invariant Transformer (SiT), a scalable visio
Externí odkaz:
http://arxiv.org/abs/2406.15025
Autor:
Athavale, Anagha, Bartocci, Ezio, Christakis, Maria, Maffei, Matteo, Nickovic, Dejan, Weissenbacher, Georg
We present the first automated verification technique for confidence-based 2-safety properties, such as global robustness and global fairness, in deep neural networks (DNNs). Our approach combines self-composition to leverage existing reachability an
Externí odkaz:
http://arxiv.org/abs/2405.14400
Autor:
Schachner, Martin, Schneider, Bernd, Weissenbacher, Fabian, Kirillova, Nadezda, Possegger, Horst, Bischof, Horst, Klug, Corina
A better understanding of interactive pedestrian behavior in critical traffic situations is essential for the development of enhanced pedestrian safety systems. Real-world traffic observations play a decisive role in this, since they represent behavi
Externí odkaz:
http://arxiv.org/abs/2402.02533
Autor:
Weissenbacher, Max
We study the massless Vlasov equation on the exterior of the subextremal and extremal Reissner-Nordstr\"om spacetimes. We prove that moments decay at an exponential rate in the subextremal case and at a polynomial rate in the extremal case. This poly
Externí odkaz:
http://arxiv.org/abs/2303.15338
Autor:
Theresa Hautz, Hubert Hackl, Hendrik Gottschling, Raphael Gronauer, Julia Hofmann, Stefan Salcher, Bettina Zelger, Rupert Oberhuber, Benno Cardini, Annemarie Weissenbacher, Thomas Resch, Jakob Troppmair, Stefan Schneeberger
Publikováno v:
EBioMedicine, Vol 108, Iss , Pp 105330- (2024)
Summary: Background: A better understanding of the molecular events during liver normothermic machine perfusion (NMP) is warranted to develop a data-based approach for the identification of biomarkers representative of graft quality and posttransplan
Externí odkaz:
https://doaj.org/article/dabf014d3eea4d158514cdf8c8d27c59
Autor:
Nora M. Biermann, Susanna Piechl, Nora Dinhopl, Andrea Fuchs-Baumgartinger, Christiane Weissenbacher-Lang, Christof A. Bertram
Publikováno v:
Frontiers in Veterinary Science, Vol 11 (2024)
Neoplastic processes of the mandible and their treatment are rarely reported in large animal species. Specifically, giant cell tumor of bone is an uncommon tumor in animals and has been associated in humans with locally invasive behavior and a high r
Externí odkaz:
https://doaj.org/article/1d904303536947f4b81238b951e2e553
Autor:
João Correia, Nicole Kube, Lauren Florisson, Max Janse, Brian Zimmerman, Doris Preininger, Jonas Nowaczek, Anton Weissenbacher, Hugo Batista, Philippe Jouk
Publikováno v:
Journal of Zoological and Botanical Gardens, Vol 5, Iss 1, Pp 90-118 (2024)
The European Union of Aquarium Curators (EUAC) boasts a membership of 150 dedicated individuals, standing as a vital cornerstone within the European public aquarium community. Since 2004, the EUAC Conservation Fund has granted over a quarter of a mil
Externí odkaz:
https://doaj.org/article/ae210196bcdd458ba5dd5192ce35a6ab
Autor:
Hautz, Theresa, Hackl, Hubert, Gottschling, Hendrik, Gronauer, Raphael, Hofmann, Julia, Salcher, Stefan, Zelger, Bettina, Oberhuber, Rupert, Cardini, Benno, Weissenbacher, Annemarie, Resch, Thomas, Troppmair, Jakob, Schneeberger, Stefan
Publikováno v:
In eBioMedicine October 2024 108
Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current algorithms over-
Externí odkaz:
http://arxiv.org/abs/2111.01365
Autor:
Karen O'Connor, Su Golder, Davy Weissenbacher, Ari Z Klein, Arjun Magge, Graciela Gonzalez-Hernandez
Publikováno v:
Journal of Medical Internet Research, Vol 26, p e47923 (2024)
BackgroundPatient health data collected from a variety of nontraditional resources, commonly referred to as real-world data, can be a key information source for health and social science research. Social media platforms, such as Twitter (Twitter, Inc
Externí odkaz:
https://doaj.org/article/54be9b657ffc4072b081103097149cd5