Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Daniel Coquelin"'
Autor:
Oskar Taubert, Fabrice von der Lehr, Alina Bazarova, Christian Faber, Philipp Knechtges, Marie Weiel, Charlotte Debus, Daniel Coquelin, Achim Basermann, Achim Streit, Stefan Kesselheim, Markus Götz, Alexander Schug
Publikováno v:
Communications Biology, Vol 6, Iss 1, Pp 1-8 (2023)
Abstract On the path to full understanding of the structure-function relationship or even design of RNA, structure prediction would offer an intriguing complement to experimental efforts. Any deep learning on RNA structure, however, is hampered by th
Externí odkaz:
https://doaj.org/article/d536d84aae0f4245a6e3998c83d5238a
Accelerating neural network training with distributed asynchronous and selective optimization (DASO)
Autor:
Daniel Coquelin, Charlotte Debus, Markus Götz, Fabrice von der Lehr, James Kahn, Martin Siggel, Achim Streit
Publikováno v:
Journal of Big Data, Vol 9, Iss 1, Pp 1-18 (2022)
Abstract With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) and large-sca
Externí odkaz:
https://doaj.org/article/aa27344a1d45457eb832b4a93df6812a
Autor:
Oskar Taubert, Marie Weiel, Daniel Coquelin, Anis Farshian, Charlotte Debus, Alexander Schug, Achim Streit, Markus Götz
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031320408
We present Propulate, an evolutionary optimization algorithm and software package for global optimization and in particular hyperparameter search. For efficient use of HPC resources, Propulate omits the synchronization after each generation as done i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a7f0e0ec11cedea07ff74f88108ce2a
https://doi.org/10.1007/978-3-031-32041-5_6
https://doi.org/10.1007/978-3-031-32041-5_6
Publikováno v:
Nature machine intelligence, 3 (8), 727–734
Nature machine intelligence 3(8), 727-734 (2021). doi:10.1038/s42256-021-00366-3
Nature machine intelligence 3(8), 727-734 (2021). doi:10.1038/s42256-021-00366-3
Molecular simulations are a powerful tool to complement and interpret ambiguous experimental data on biomolecules to obtain structural models. Such data-assisted simulations often rely on parameters, the choice of which is highly non-trivial and cruc
As with any physical instrument, hyperspectral cameras induce different kinds of noise in the acquired data. Therefore, Hyperspectral denoising is a crucial step for analyzing hyperspectral images (HSIs). Conventional computational methods rarely use
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e15c157f15cb931bba39aaebd31cb3a
http://arxiv.org/abs/2204.06979
http://arxiv.org/abs/2204.06979
Publikováno v:
IGARSS
IEEE 1587-1590 (2021). doi:10.1109/IGARSS47720.2021.9554309
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings]-IEEE, 2021.-ISBN 978-1-6654-0369-6-doi:10.1109/IGARSS47720.2021.9554309
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings]-IEEE, 2021.-ISBN 978-1-6654-0369-6-doi:10.1109/IGARSS47720.2021.9554309IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 2021-07-12-2021-07-16
IEEE 1587-1590 (2021). doi:10.1109/IGARSS47720.2021.9554309
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings]-IEEE, 2021.-ISBN 978-1-6654-0369-6-doi:10.1109/IGARSS47720.2021.9554309
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings]-IEEE, 2021.-ISBN 978-1-6654-0369-6-doi:10.1109/IGARSS47720.2021.9554309IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 2021-07-12-2021-07-16
BigEarthNet is one of the standard large remote sensing datasets. It has been shown previously that neural networks are effective tools to classify the image patches in this data. However, finding the optimum network hyperparameters and architecture
Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
Autor:
Charlotte Debus, James Kahn, Achim Streit, Fabrice von der Lehr, Markus Götz, Daniel Coquelin, Martin Siggel
Publikováno v:
Journal of Big Data, Vol 9, Iss 1, Pp 1-18 (2022)
Journal of Big Data, 9 (1), 14
Journal of Big Data, 9 (1), 14
With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) and large-scale distri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca0d2a644e65022219b7949182b7e3f5
https://publikationen.bibliothek.kit.edu/1000137220
https://publikationen.bibliothek.kit.edu/1000137220
Autor:
Björn Hagemeier, Claudia Comito, Kai Krajsek, Achim Streit, Simon Hanselmann, Daniel Coquelin, Martin Siggel, Achim Basermann, Philipp Knechtges, Michael Tarnawa, Charlotte Debus, Markus Götz
Publikováno v:
IEEE BigData
IEEE 276-287 (2020). doi:10.1109/BigData50022.2020.9378050
2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, 2020-12-10-2020-12-13
IEEE 276-287 (2020). doi:10.1109/BigData50022.2020.9378050
2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, 2020-12-10-2020-12-13
To cope with the rapid growth in available data, the efficiency of data analysis and machine learning libraries has recently received increased attention. Although great advancements have been made in traditional array-based computations, most are li
Autor:
Taubert, Oskar1 (AUTHOR), von der Lehr, Fabrice2 (AUTHOR), Bazarova, Alina3,4 (AUTHOR), Faber, Christian3 (AUTHOR), Knechtges, Philipp2,4 (AUTHOR), Weiel, Marie1,4 (AUTHOR), Debus, Charlotte1,4 (AUTHOR), Coquelin, Daniel1,4 (AUTHOR), Basermann, Achim2 (AUTHOR), Streit, Achim1 (AUTHOR), Kesselheim, Stefan3,4 (AUTHOR), Götz, Markus1,4 (AUTHOR) markus.goetz@kit.edu, Schug, Alexander3,5 (AUTHOR) al.schug@fz-juelich.de
Publikováno v:
Communications Biology. 9/6/2023, Vol. 6 Issue 1, p1-8. 8p.
Autor:
Coquelin, Daniel, Debus, Charlotte, Götz, Markus, von der Lehr, Fabrice, Kahn, James, Siggel, Martin, Streit, Achim
Publikováno v:
Journal of Big Data; 5/10/2022, Vol. 9 Issue 1, p1-18, 18p