Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Zhenan He"'
Autor:
Chenwei Tang, Caiyang Yu, Yi Gao, Jianming Chen, Jiaming Yang, Jiuling Lang, Chuan Liu, Ling Zhong, Zhenan He, Jiancheng Lv
Publikováno v:
Big Data Mining and Analytics, Vol 5, Iss 2, Pp 140-160 (2022)
As a high-tech strategic emerging comprehensive industry, the nuclear industry is committed to the research, production, and processing of nuclear fuel, as well as the development and utilization of nuclear energy. Nowadays, the nuclear industry has
Externí odkaz:
https://doaj.org/article/93e933753aeb445fa28e33c5a2e709dd
Publikováno v:
Journal of Computational Design and Engineering. 10:934-946
Combinatorial optimization problems have very important applications in information technology, transportation, economics, management, network communication, and other fields. Since the problem size in real-scenario application is in large-scale, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80e80a5f56ab3ebd68cb88bfe920b7f0
https://doi.org/10.1093/jcde/qwad029
https://doi.org/10.1093/jcde/qwad029
Publikováno v:
IEEE Transactions on Industrial Informatics. 19:2574-2584
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b51ac2e22522a084951d30a236a21b3b
https://doi.org/10.1109/tii.2022.3169459
https://doi.org/10.1109/tii.2022.3169459
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:6749-6762
In this article, we propose a structure-aligned generative adversarial network framework to improve zero-shot learning (ZSL) by mitigating the semantic gap, domain shift, and hubness problem. The proposed framework contains two parts, i.e., a generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37f2b2fbe7fcee5a2d0a4483fc870148
https://doi.org/10.1109/tnnls.2021.3083367
https://doi.org/10.1109/tnnls.2021.3083367
Publikováno v:
Neural Computing and Applications. 34:16493-16514
Recently, many studies have been carried out on model compression to handle the high computational cost and high memory footprint brought by the implementation of deep neural networks. In this paper, model compression of convolutional neural networks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1631126c7dd21d7aee0ec113930d0c54
https://doi.org/10.1007/s00521-022-07161-0
https://doi.org/10.1007/s00521-022-07161-0
Publikováno v:
IEEE Transactions on Systems, Man, and Cybernetics: Systems. 52:415-425
Catastrophic forgetting is a chronic problem during the online training process of deep neural networks. That is, once a new data set is used to train an existing neural network, the network will lose the ability to recognize the original data set. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d89eab0bd8cd6563e27e4cb28448995b
https://doi.org/10.1109/tsmc.2020.2997410
https://doi.org/10.1109/tsmc.2020.2997410
Publikováno v:
IEEE Transactions on Evolutionary Computation. 25:292-306
As an essential component in multi- and many-objective optimization, decision-making process either selects a subset of solutions from the whole Pareto front or guides the search toward a small part of the Pareto front during the evolutionary process
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51cf58560e26d107a124e65ea09bbc1e
https://doi.org/10.1109/tevc.2020.3027620
https://doi.org/10.1109/tevc.2020.3027620
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 31:4049-4062
Small-sample learning involves training a neural network on a small-sample data set. An expansion of the training set is a common way to improve the performance of neural networks in small-sample learning tasks. However, improper constraints in expan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c11cb5f394486a2f2d0d373a88954f6
https://doi.org/10.1109/tnnls.2019.2951803
https://doi.org/10.1109/tnnls.2019.2951803
Publikováno v:
IEEE Transactions on Evolutionary Computation. 24:494-507
Uncertainty is an important feature abstracted from real-world applications. Multiobjective optimization problems (MOPs) with uncertainty can always be characterized as robust MOPs (RMOPs). Over recent years, multiobjective optimization evolutionary
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d09526d3c40501c05b02935994d99229
https://doi.org/10.1109/tevc.2019.2933444
https://doi.org/10.1109/tevc.2019.2933444