Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Leslie N. Smith"'
Publikováno v:
Frontiers in Artificial Intelligence, Vol 6 (2023)
Externí odkaz:
https://doaj.org/article/f824b8c4724340839d7e4ba1fbec02cd
Autor:
Leslie N. Smith, Adam Conovaloff
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
Reaching the performance of fully supervised learning with unlabeled data and only labeling one sample per class might be ideal for deep learning applications. We demonstrate for the first time the potential for building one-shot semi-supervised (BOS
Externí odkaz:
https://doaj.org/article/34e830e0815e46428499a4d87e293ac6
Autor:
Leslie N. Smith
Publikováno v:
Trends in Computer Science and Information Technology. :037-041
Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories; gradient masking, robust optimization, and adversarial example detect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c3529e733b33c4ad8686cc70562eb32
https://doi.org/10.17352/tcsit.000017
https://doi.org/10.17352/tcsit.000017
Autor:
Leslie N. Smith
This paper describes the principle of "General Cyclical Training" in machine learning, where training starts and ends with "easy training" and the "hard training" happens during the middle epochs. We propose several manifestations for training neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d9a53b635c98999e6424e9235c26f76
http://arxiv.org/abs/2202.08835
http://arxiv.org/abs/2202.08835
Autor:
Ina T. Martin, Marcia O'Dwyer, Dean Yoder, Shishir Adhikari, Gundeep Singh, Farah Sayed, Antony Ingrisano, Michael McMaster, Leslie N. Smith, Elizabeth. S. Bolman, Fang Ji, Kenneth D. Singer, Samuel Schwab, Michael Hinczewski
Publikováno v:
Heritage Science, Vol 9, Iss 1, Pp 1-11 (2021)
Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art stud
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c5d90121d324ec927aa66f74d69202b
https://doi.org/10.1186/s40494-021-00618-w
https://doi.org/10.1186/s40494-021-00618-w
Autor:
Leslie N. Smith, Kristen Nock, David Bonanno, Vicki Lynn Ferrini, Paul Elmore, Frederick E. Petry
Publikováno v:
Heliyon
Heliyon, Vol 5, Iss 10, Pp e02570-(2019)
Heliyon, Vol 5, Iss 10, Pp e02570-(2019)
We present research using single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training. We performed numerical ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db3c655213e4626d48c9fba0a4eb7151
https://pubmed.ncbi.nlm.nih.gov/31687485
https://pubmed.ncbi.nlm.nih.gov/31687485
Autor:
Camellia R. Davis, A. Shaun Rowe, R. Curtis, Leslie A. Hamilton, Leslie N. Smith, Victoria W. Reynolds, Grayson K. Peek
Publikováno v:
Journal of Critical Care. 30:1283-1286
Purpose Increased awareness of delirium in the intensive care unit (ICU) has led to higher use of antipsychotic medications for treatment of delirium. These medications are often not discontinued at ICU or hospital discharge, which may increase the r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aec3287a16f0965959fe7ff8e8a6a076
https://doi.org/10.1016/j.jcrc.2015.08.009
https://doi.org/10.1016/j.jcrc.2015.08.009
Autor:
Nicholay Topin, Leslie N. Smith
In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to understanding why de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6460568d49e6afb2227897e91f8d6f3
http://arxiv.org/abs/1708.07120
http://arxiv.org/abs/1708.07120
Publikováno v:
SPIE Proceedings.
Deep Learning has proven to be an effective method for making highly accurate predictions from complex data sources. Convolutional neural networks continue to dominate image classification problems and recursive neural networks have proven their util
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f60237159b43d7e08f16ac05356a4ca
https://doi.org/10.1117/12.2268001
https://doi.org/10.1117/12.2268001
Autor:
Michael Elad, Leslie N. Smith
Publikováno v:
IEEE Signal Processing Letters. 20:79-82
In this letter, we propose two improvements of the MOD and K-SVD dictionary learning algorithms, by modifying the two main parts of these algorithms-the dictionary update and the sparse coding stages. Our first contribution is a different dictionary-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::987746febd63b03d0dae640eaf7e0597
https://doi.org/10.1109/lsp.2012.2229976
https://doi.org/10.1109/lsp.2012.2229976