Zobrazeno 1 - 10
of 708
pro vyhledávání: '"Horváth, Tamás"'
We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using explanations. EEGL is an iter
Externí odkaz:
http://arxiv.org/abs/2403.07849
Publikováno v:
Computer Methods in Applied Mechanics and Engineering,Volume 432, Part A,2024
We present a divergence-free and $H(div)$-conforming hybridized discontinuous Galerkin (HDG) method and a computationally efficient variant called embedded-HDG (E-HDG) for solving stationary incompressible viso-resistive magnetohydrodynamic (MHD) equ
Externí odkaz:
http://arxiv.org/abs/2310.06687
Autor:
Siepmann, Timo, Pintér, Alexandra, Buchmann, Sylvia J., Stibal, Leonie, Arndt, Martin, Kubasch, Anne Sophie, Kubasch, Marie Luise, Penzlin, Ana Isabel, Frenz, Elka, Zago, Wagner, Horváth, Tamás, Szatmári Jr., Szabolcs, Bereczki, Dániel, Takáts, Annamária, Ziemssen, Tjalf, Lipp, Axel, Freeman, Roy, Reichmann, Heinz, Barlinn, Kristian, Illigens, Ben Min-Woo
Publikováno v:
Frontiers in Neurology (2017), 8, ISSN: 1664-2295. DOI: 10.3389/fneur.2017.00212. Artikelnr.: 212
Background: In Parkinson’s disease (PD), alpha-synuclein accumulation in cutaneous autonomic pilomotor and sudomotor nerve fibers has been linked to autonomic nervous system disturbances even in the early stages of the disease. This study aims to a
Externí odkaz:
http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-230507
http://www.qucosa.de/fileadmin/data/qucosa/documents/23050/fneur-08-00212.pdf
http://www.qucosa.de/fileadmin/data/qucosa/documents/23050/fneur-08-00212.pdf
Motivated by the increasing interest in applications of graph geodesic convexity in machine learning and data mining, we present a heuristic for computing the geodesic convex hull of node sets in networks. It generates a set of almost maximal outerpl
Externí odkaz:
http://arxiv.org/abs/2206.07350
Publikováno v:
In Computer Methods in Applied Mechanics and Engineering 1 December 2024 432 Part A
Autor:
Horvath, Tamas L., Rhebergen, S.
In (J. Comput. Phys., 417, 109577, 2020) we introduced a space-time embedded-hybridizable discontinuous Galerkin method for the solution of the incompressible Navier-Stokes equations on time-dependent domains of which the motion of the domain is pres
Externí odkaz:
http://arxiv.org/abs/2105.12542
One of the central problems studied in the theory of machine learning is the question of whether, for a given class of hypotheses, it is possible to efficiently find a {consistent} hypothesis, i.e., which has zero training error. While problems invol
Externí odkaz:
http://arxiv.org/abs/2105.06251
We introduce and analyze a space-time hybridized discontinuous Galerkin method for the evolutionary Navier--Stokes equations. Key features of the numerical scheme include point-wise mass conservation, energy stability, and pressure robustness. We pro
Externí odkaz:
http://arxiv.org/abs/2103.13492
The Weisfeiler-Lehman graph kernels are among the most prevalent graph kernels due to their remarkable time complexity and predictive performance. Their key concept is based on an implicit comparison of neighborhood representing trees with respect to
Externí odkaz:
http://arxiv.org/abs/2101.08104
Publikováno v:
In Trends in Endocrinology & Metabolism