Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Romain Egele"'
Autor:
Yixuan Sun, Ololade Sowunmi, Romain Egele, Sri Hari Krishna Narayanan, Luke Van Roekel, Prasanna Balaprakash
Publikováno v:
Mathematics, Vol 12, Iss 10, p 1483 (2024)
Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper’s advanced search algorithms for multiobjective optimization, streamlining the development of neural netwo
Externí odkaz:
https://doaj.org/article/26b78888604d4cb9b4e1eb441a3ab64a
Autor:
Matthieu Dorier, Romain Egele, Prasanna Balaprakash, Jaehoon Koo, Sandeep Madireddy, Srinivasan Ramesh, Allen D. Malony, Rob Ross
Publikováno v:
CLUSTER 2022-IEEE International Conference on Cluster Computing (CLUSTER)
CLUSTER 2022-IEEE International Conference on Cluster Computing (CLUSTER), Sep 2022, Heidelberg, Germany. pp.381-393, ⟨10.1109/CLUSTER51413.2022.00049⟩
CLUSTER 2022-IEEE International Conference on Cluster Computing (CLUSTER), Sep 2022, Heidelberg, Germany. pp.381-393, ⟨10.1109/CLUSTER51413.2022.00049⟩
Distributed data storage services tailored to specific applications have grown popular in the high-performance computing (HPC) community as a way to address I/O and storage challenges. These services offer a variety of specific interfaces, semantics,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::afe01b69b639ebd0abcfe69f48db14cb
https://hal.science/hal-03864478
https://hal.science/hal-03864478
Autor:
Romain Egele, Romit Maulik, Krishnan Raghavan, Bethany Lusch, Isabelle Guyon, Prasanna Balaprakash
Publikováno v:
26TH International Conference on Pattern Recognition
26TH International Conference on Pattern Recognition, Aug 2022, Montréal, Canada. pp.1908-1914
26TH International Conference on Pattern Recognition, Aug 2022, Montréal, Canada. pp.1908-1914
International audience; Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is competitive with approaches based on Bayesian ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51edfa6fba9cfae3dc581011d10483d6
http://arxiv.org/abs/2110.13511
http://arxiv.org/abs/2110.13511
Autor:
Venkatram Vishwanath, Prasanna Balaprakash, Rick Stevens, Romain Egele, Isabelle Guyon, Zhengying Liu, Fangfang Xia
Publikováno v:
SC
SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2021, St. Louis, Missouri, United States. ⟨10.1145/3458817.3476203⟩
SC'21
SC'21, Nov 2021, St. Louis, Missouri, United States. ⟨10.1145/3458817.3476203⟩
SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2021, St. Louis, Missouri, United States. ⟨10.1145/3458817.3476203⟩
SC'21
SC'21, Nov 2021, St. Louis, Missouri, United States. ⟨10.1145/3458817.3476203⟩
International audience; Developing high-performing predictive models for large tabular data sets is a challenging task. The state-of-the-art methods are based on expert-developed model ensembles from different supervised learning methods. Recently, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3bbe126d8f212ad7a7789e98bc76ff0
https://hal.archives-ouvertes.fr/hal-02973288/file/agebo_tabular.pdf
https://hal.archives-ouvertes.fr/hal-02973288/file/agebo_tabular.pdf
Publikováno v:
SC
Developing surrogate geophysical models from data is a key research topic in atmospheric and oceanic modeling because of the large computational costs associated with numerical simulation methods. Researchers have started applying a wide range of mac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d70963634569b40ee3675dc165544b1f
http://arxiv.org/abs/2004.10928
http://arxiv.org/abs/2004.10928