Zobrazeno 1 - 10
of 181
pro vyhledávání: '"Steve R. Gunn"'
The bubbles generated by breaking waves are of considerable scientific interest due to their influence on air–sea gas transfer, aerosol production, and upper ocean optics and acoustics. However, a detailed understanding of the processes creating de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba5b485cf1f6c83be759eb0043991346
https://eprints.whiterose.ac.uk/186350/1/os-18-565-2022.pdf
https://eprints.whiterose.ac.uk/186350/1/os-18-565-2022.pdf
Bubbles formed by breaking waves in the open ocean influence many surface processes but are poorly understood. We report here on detailed bubble size distributions measured during the High Wind Speed Gas Exchange Study (HiWinGS) in the North Atlantic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a8fdd780f793f4cc0a1b0eaf3752505
https://os.copernicus.org/preprints/os-2021-104/
https://os.copernicus.org/preprints/os-2021-104/
Autor:
Jia Bi, Steve R. Gunn
Publikováno v:
Machine Learning and Knowledge Discovery in Databases. Research Track ISBN: 9783030865221
ECML/PKDD (3)
ECML/PKDD (3)
This paper proposed a new technique Variance Controlled Stochastic Gradient (VCSG) to improve the performance of the stochastic variance reduced gradient (SVRG) algorithm. To avoid over-reducing the variance of gradient by SVRG, a hyper-parameter \(\
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f2b2ae62ec48c86d86ecf1c394d11dc7
https://doi.org/10.1007/978-3-030-86523-8_9
https://doi.org/10.1007/978-3-030-86523-8_9
Autor:
Albert F. H. M. Lechner, Steve R. Gunn
Publikováno v:
COMPLEXIS
Autor:
Steve R. Gunn, Albert F. H. M. Lechner
Publikováno v:
5th International Conference on Computer Science and Information Technology (CSTY 2019).
Sales forecasts are essential to every business strategic plans and can both save the business money and increase its competitive advantage. However, many current businesses underestimate the opportunities accurate forecasts provide and rely on judge
Autor:
Jia Bi, Steve R. Gunn
Publikováno v:
PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030299101
PRICAI (2)
PRICAI (2)
A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory shows these o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::408fb7807d1cd945b61bbce1c29ca17f
https://eprints.soton.ac.uk/430899/
https://eprints.soton.ac.uk/430899/
Autor:
Steve R. Gunn, Jia Bi
Publikováno v:
ICTAI
Deep learning is becoming more widespread due to its power in solving complex classification problems. However, deep learning models often require large memory and energy consumption, which may prevent them from being deployed effectively on embedded
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7593c37bf9b25da8935abb992d6751d5
https://eprints.soton.ac.uk/426560/
https://eprints.soton.ac.uk/426560/
Autor:
Jia Bi, Steve R. Gunn
Publikováno v:
International Journal on Artificial Intelligence Tools. 29:2060002
Deep neural networks become more popular as its ability to solve very complex pattern recognition problems. However, deep neural networks often need massive computational and memory resources, which is main reason resulting them to be difficult effic
Publikováno v:
IVSW
Conventional cryptographic solutions to the security are expensive in terms of computing resources (memory and processing capacity) and power consumption. They are not suitable for the Internet of Things devices that have constrained resources. In th
Accurate measurements of the oceanic whitecap coverage from whitecap images are required for better understanding the air–gas transfer and aerosol production processes. However, this is a challenging task because the whitecap patches are formed imm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38451100dbe2ecc0716c91728e602d47
https://eprints.soton.ac.uk/419336/
https://eprints.soton.ac.uk/419336/