Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Ege Beyazit"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 32:1228-1240
Learning with streaming data has received extensive attention during the past few years. Existing approaches assume that the feature space is fixed or changes by following explicit regularities, limiting their applicability in real-time applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee91644fb5c9031571f9471ee26a7cd3
https://doi.org/10.1109/tnnls.2020.2981386
https://doi.org/10.1109/tnnls.2020.2981386
Publikováno v:
AAAI
We study the problem of online learning with varying feature spaces. The problem is challenging because, unlike traditional online learning problems, varying feature spaces can introduce new features or stop having some features without following a p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef7f008e0d8e1753afc2eefad72fb06d
https://doi.org/10.1609/aaai.v33i01.33013232
https://doi.org/10.1609/aaai.v33i01.33013232
Publikováno v:
IJCAI
Learning interpretable representations in an unsupervised setting is an important yet a challenging task. Existing unsupervised interpretable methods focus on extracting independent salient features from data. However they miss out the fact that the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e7d8f3ff700236a6b33d0e318d293d0
https://doi.org/10.24963/ijcai.2020/273
https://doi.org/10.24963/ijcai.2020/273
Publikováno v:
The Computer Journal. 62:641-656
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ada27845ad12bcf45e0f173e7b16370f
https://doi.org/10.1093/comjnl/bxy057
https://doi.org/10.1093/comjnl/bxy057
Video transcoding is the process of converting a video to the format supported by the viewer's device. Video transcoding requires huge storage and computational resources, thus, many video stream providers choose to carry it out on the cloud. Video s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aff2bc382712d81b2b0143682fae3b42
Publikováno v:
IJCAI
Learning with streaming data has received extensive attention during the past few years. Existing approaches assume the feature space is fixed or changes by following explicit regularities, limiting their applicability in dynamic environments where t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04ce59ad11557f08d54a72cf4fa3b2e5
https://doi.org/10.24963/ijcai.2019/346
https://doi.org/10.24963/ijcai.2019/346
Publikováno v:
ICTAI
Traffic crashes have threatened properties and lives for more than thirty years. Thanks to the recent proliferation of traffic data, the machine learning techniques have been broadly expected to make contributions in the traffic safety community due
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85d2efe13d61c38e0862c60e93c5ce79
https://doi.org/10.1109/ictai.2018.00034
https://doi.org/10.1109/ictai.2018.00034
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014179
ICANN (1)
ICANN (1)
We present a novel adaptive feedforward neural network for online learning from doubly-streaming data, where both the data volume and feature space grow simultaneously. Traditional online learning and feature selection algorithms can’t handle this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3b182a76524ebb96c6f13a4e09912a5
https://doi.org/10.1007/978-3-030-01418-6_50
https://doi.org/10.1007/978-3-030-01418-6_50