Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Philipp Petersen"'
Autor:
Gunnar Treff, Judith Staudner, Xandro Bayer, Nikolaus Hautsch, Thorsten Möller, Philipp Petersen
Publikováno v:
Current Issues in Sport Science, Vol 9, Iss 4 (2024)
Introduction Polarized endurance training is an important and frequently discussed training intensity distribution (TID). The polarized TID is described as the largest fraction of training time or sessions spent with low-intensity exercise in inten
Externí odkaz:
https://doaj.org/article/081a4b2cfa794557a6a6c76e04d930cb
Publikováno v:
Mitteilungen der Deutschen Mathematiker-Vereinigung. 29:191-197
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::27598abb4c65dd2d48e2343af1ea6db0
https://doi.org/10.1515/dmvm-2021-0074
https://doi.org/10.1515/dmvm-2021-0074
Publikováno v:
Mathematical Aspects of Deep Learning ISBN: 9781009025096
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e3718bc8d533560e7df88d4a417f8928
https://doi.org/10.1017/9781009025096.002
https://doi.org/10.1017/9781009025096.002
Publikováno v:
Acta Orthopaedica Belgica. 87:521-527
A variety of different plate designs and materials are available to treat distal radius fractures. This study evaluates clinical results with a carbon fibre- reinforced (CFR)-polyether ether ketone (PEEK) plate in comparison to a standard titanium pl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d487871f182f60c565e7089f27d5116c
https://doi.org/10.52628/87.3.18
https://doi.org/10.52628/87.3.18
Publikováno v:
Analysis and Applications. 18:715-770
Approximation rate bounds for emulations of real-valued functions on intervals by deep neural networks (DNNs) are established. The approximation results are given for DNNs based on ReLU activation functions. The approximation error is measured with r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::775fbd7677f7ea7cfd37e8c8c378e144
https://doi.org/10.1142/s0219530519410136
https://doi.org/10.1142/s0219530519410136
We present a deep learning-based algorithm to jointly solve a reconstruction problem and a wavefront set extraction problem in tomographic imaging. The algorithm is based on a recently developed digital wavefront set extractor as well as the well-kno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28b01e5c00970f2f888b3c6adfb6009c
https://hdl.handle.net/10037/26407
https://hdl.handle.net/10037/26407
Autor:
Felix Voigtlaender, Philipp Petersen
Publikováno v:
Proceedings of the American Mathematical Society. 148:1567-1581
Convolutional neural networks are the most widely used type of neural networks in applications. In mathematical analysis, however, mostly fully-connected networks are studied. In this paper, we establish a connection between both network architecture
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29bc51c5e0a34c9808501a12bd9defaa
https://doi.org/10.1090/proc/14789
https://doi.org/10.1090/proc/14789
We perform a comprehensive numerical study of the effect of approximation-theoretical results for neural networks on practical learning problems in the context of numerical analysis. As the underlying model, we study the machine-learning-based soluti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b4bce24a89daffe6cf1f9e113d910fd
https://hdl.handle.net/10037/24272
https://hdl.handle.net/10037/24272
Publikováno v:
Analysis and Applications. 18:803-859
We analyze to what extent deep Rectified Linear Unit (ReLU) neural networks can efficiently approximate Sobolev regular functions if the approximation error is measured with respect to weaker Sobolev norms. In this context, we first establish upper a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49648bff7cc388853a5923d509585785
https://doi.org/10.1142/s0219530519410021
https://doi.org/10.1142/s0219530519410021
Publikováno v:
SIAM Journal on Imaging Sciences. 12:1936-1966
Microlocal analysis provides deep insight into singularity structures and is often crucial for solving inverse problems, predominately, in imaging sciences. Of particular importance is the analysis of wavefront sets and the correct extraction of thos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a2e9ebffff3dd8c7cdee2532d19195b
https://doi.org/10.1137/19m1237594
https://doi.org/10.1137/19m1237594