Zobrazeno 1 - 10
of 218
pro vyhledávání: '"Fesser, P."'
Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-invariance in images. Group-convolutional architectures, which encode symm
Externí odkaz:
http://arxiv.org/abs/2410.05499
Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing certificat
Externí odkaz:
http://arxiv.org/abs/2401.05338
Autor:
Fesser, Lukas, Weber, Melanie
Structural and Positional Encodings can significantly improve the performance of Graph Neural Networks in downstream tasks. Recent literature has begun to systematically investigate differences in the structural properties that these approaches encod
Externí odkaz:
http://arxiv.org/abs/2311.14864
Autor:
Fesser, Lukas, Weber, Melanie
While Graph Neural Networks (GNNs) have been successfully leveraged for learning on graph-structured data across domains, several potential pitfalls have been described recently. Those include the inability to accurately leverage information encoded
Externí odkaz:
http://arxiv.org/abs/2309.09384
Physics-informed Neural Networks (PINNs) have recently gained popularity in the scientific community due to their effective approximation of partial differential equations (PDEs) using deep neural networks. However, their application has been general
Externí odkaz:
http://arxiv.org/abs/2306.09478
Autor:
Fesser, Lukas, Iváñez, Sergio Serrano de Haro, Devriendt, Karel, Weber, Melanie, Lambiotte, Renaud
The notion of curvature on graphs has recently gained traction in the networks community, with the Ollivier-Ricci curvature (ORC) in particular being used for several tasks in network analysis, such as community detection. In this work, we choose a d
Externí odkaz:
http://arxiv.org/abs/2306.06474
Autor:
Dimitrov, Evgeni, Fang, Xiang, Fesser, Lukas, Serio, Christian, Teitler, Carson, Wang, Angela, Zhu, Weitao
A Bernoulli Gibbsian line ensemble $\mathfrak{L} = (L_1, \dots, L_N)$ is the law of the trajectories of $N-1$ independent Bernoulli random walkers $L_1, \dots, L_{N-1}$ with possibly random initial and terminal locations that are conditioned to never
Externí odkaz:
http://arxiv.org/abs/2011.04478
Autor:
Thomas Ziegenhals, Ronja Frieling, Philipp Wolf, Katharina Göbel, Stina Koch, Mia Lohmann, Markus Baiersdörfer, Stephanie Fesser, Ugur Sahin, Andreas N. Kuhn
Publikováno v:
Frontiers in Molecular Biosciences, Vol 10 (2023)
Introduction: Exogeneous messenger ribonucleic acid (mRNA) can be used as therapeutic and preventive medication. However, during the enzymatic production process, commonly called in vitro transcription, by-products occur which can reduce the therapeu
Externí odkaz:
https://doaj.org/article/cb043fdb9f8c4415a1911c2e6e3bab04
Autor:
Julien Riou, Anthony Hauser, Anna Fesser, Christian L. Althaus, Matthias Egger, Garyfallos Konstantinoudis
Publikováno v:
Nature Communications, Vol 14, Iss 1, Pp 1-9 (2023)
COVID-19-releated public health measures may have indirectly impacted mortality rates by causing or averting deaths. Here, the authors use data from Switzerland until April 2022 and estimate that, after accounting for deaths directly related to COVID
Externí odkaz:
https://doaj.org/article/a9e84d8a577c4ed182488001b76e2999
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.