Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Steven Hoi"'
Publikováno v:
Neurocomputing. 501:410-419
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e25856866197ba20fdf39122ad2f09c2
https://doi.org/10.1016/j.neucom.2022.05.112
https://doi.org/10.1016/j.neucom.2022.05.112
Publikováno v:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6188303b8aa52dcce51da9b5db2e6ad
https://doi.org/10.18653/v1/2022.naacl-main.247
https://doi.org/10.18653/v1/2022.naacl-main.247
The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new pote
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb0f6ca1d1a443bc89d0a3753fa05580
http://arxiv.org/abs/2101.00590
http://arxiv.org/abs/2101.00590
Publikováno v:
Proceedings of the 2021 SIAM International Conference on Data Mining (SDM) ISBN: 9781611976700
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::454b3ebb08f00666d7b93474dfdfeee5
https://doi.org/10.1137/1.9781611976700.6
https://doi.org/10.1137/1.9781611976700.6
Autor:
Bin Li, Steven Hoi
Publikováno v:
Online Portfolio Selection: Principles and Algorithms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae2571d7b3b62b7f75d531082b8316de
https://doi.org/10.1201/b19011-19
https://doi.org/10.1201/b19011-19
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
Locally Linear Support Vector Machine (LLSVM) has been actively used in classification tasks due to its capability of classifying nonlinear patterns. However, existing LLSVM suffers from two drawbacks: (1) a particular and appropriate regularization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa17e21fb3b1834b08593d61432fe777
https://doi.org/10.1609/aaai.v32i1.11896
https://doi.org/10.1609/aaai.v32i1.11896
Publikováno v:
Scopus-Elsevier
Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29787b72b81860f961d53813b3db1c82
Publikováno v:
Scopus-Elsevier
Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable for appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1aad56bd0b653876db162401807a7670
http://arxiv.org/abs/1206.4633
http://arxiv.org/abs/1206.4633
Publikováno v:
Scopus-Elsevier
Previous studies of Non-Parametric Kernel Learning (NPKL) usually formulate the learning task as a Semi-Definite Programming (SDP) problem that is often solved by some general purpose SDP solvers. However, for TV data examples, the time complexity of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e55addbd6b9414eeaf288f9c5e58fb74
https://hdl.handle.net/10453/29140
https://hdl.handle.net/10453/29140
Publikováno v:
Environmental Science & Technology. 27:2158-2161
In order to control SO 2 emissions, one option is to win metal from sulfide ores under reducing conditions. In this direct reduction process with soda ash as the flux, one of the key steps is the recovery of sulfur from Na 2 S. The objective of the p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::683e034fa8393a398480c58a5723dc32
https://doi.org/10.1021/es00047a023
https://doi.org/10.1021/es00047a023