Zobrazeno 1 - 10
of 141
pro vyhledávání: '"Tom Peterka"'
Autor:
Sukriti Manna, Troy D. Loeffler, Rohit Batra, Suvo Banik, Henry Chan, Bilvin Varughese, Kiran Sasikumar, Michael Sternberg, Tom Peterka, Mathew J. Cherukara, Stephen K. Gray, Bobby G. Sumpter, Subramanian K. R. S. Sankaranarayanan
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-10 (2022)
Reinforcement learning algorithms are emerging as powerful machine learning approaches. This paper introduces a novel machine-learning approach for learning in continuous action space and applies this strategy to the generation of high dimensional po
Externí odkaz:
https://doaj.org/article/856fb35b358a4d51a94ca42f1d112763
Publikováno v:
Visual Informatics, Vol 4, Iss 2, Pp 109-121 (2020)
We propose a deep learning approach to collectively compare two or multiple ensembles, each of which is a collection of simulation outputs. The purpose of collective comparison is to help scientists understand differences between simulation models by
Externí odkaz:
https://doaj.org/article/ec8458a6f71d4f18a6a55aa11ec3d530
Publikováno v:
IEEE Access, Vol 7, Pp 156929-156955 (2019)
Convergence between high-performance computing (HPC) and big data analytics (BDA) is currently an established research area that has spawned new opportunities for unifying the platform layer and data abstractions in these ecosystems. This work presen
Externí odkaz:
https://doaj.org/article/754198e84bc744878bf41e35187dbef7
Autor:
Junjing Deng, David J. Vine, Si Chen, Qiaoling Jin, Youssef S. G. Nashed, Tom Peterka, Stefan Vogt, Chris Jacobsen
Publikováno v:
Scientific Reports, Vol 7, Iss 1, Pp 1-10 (2017)
Abstract X-ray microscopy can be used to image whole, unsectioned cells in their native hydrated state. It complements the higher resolution of electron microscopy for submicrometer thick specimens, and the molecule-specific imaging capabilites of fl
Externí odkaz:
https://doaj.org/article/2bea7a6aee8c45a792653c273a78fc6f
Publikováno v:
IEEE Transactions on Big Data. 8:1637-1649
B-spline models are a powerful way to represent scientific data sets with a functional approximation. However, these models can suffer from spurious oscillations when the data to be approximated are not uniformly distributed. Model regularization (i.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d60d8c0097937f815543a5ec4bc16ba
http://arxiv.org/abs/2301.01209
http://arxiv.org/abs/2301.01209
Autor:
Xin Liang, Sheng Di, Franck Cappello, Mukund Raj, Chunhui Liu, Kenji Ono, Zizhong Chen, Tom Peterka, Hanqi Guo
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. :1-16
The objective of this work is to develop error-bounded lossy compression methods to preserve topological features in 2D and 3D vector fields. Specifically, we explore the preservation of critical points in piecewise linear and bilinear vector fields.
Autor:
Orcun Yildiz, Henry Chan, Krishnan Raghavan, William Judge, Mathew J. Cherukara, Prasanna Balaprakash, Subramanian Sankaranarayanan, Tom Peterka
Publikováno v:
2022 IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S).
Publikováno v:
IEEE transactions on visualization and computer graphics.
We present a novel technique for hierarchical super resolution (SR) with neural networks (NNs), which upscales volumetric data represented with an octree data structure to a high-resolution uniform grid with minimal seam artifacts on octree node boun
Autor:
Todd Munson, Ian Foster, Shinjae Yoo, Hubertus J. J. van Dam, Igor Yakushin, Zichao Di, Line Pouchard, Manish Parashar, Kerstin Kleese van Dam, Ali Murat Gok, Kevin Huck, Xin Liang, Ozan Tugluk, Lipeng Wan, Justin M. Wozniak, Wei Xu, Kshitij Mehta, Jong Choi, Matthew Wolf, Mark Ainsworth, Julie Bessac, Franck Cappello, Sheng Di, Tom Peterka, Hanqi Guo, Scott Klasky, Christopher Kelly, Tong Shu
Publikováno v:
The International Journal of High Performance Computing Applications. 35:617-635
A growing disparity between supercomputer computation speeds and I/O rates means that it is rapidly becoming infeasible to analyze supercomputer application output only after that output has been written to a file system. Instead, data-generating app