Zobrazeno 1 - 10
of 182
pro vyhledávání: '"Zizhong Chen"'
Publikováno v:
IEEE Access, Vol 7, Pp 168175-168186 (2019)
The deep convolutional neural networks (DCNN) require large number of training data to avoid overfitting, which makes it unsuitable for processing small-scale image datasets. The transfer learning using DCNN (TCNN) reuses pre-trained layers to genera
Externí odkaz:
https://doaj.org/article/38d16df2337a4dcdb7aed9c49bb136a8
Publikováno v:
Mathematics, Vol 10, Iss 15, p 2743 (2022)
Learning label noise is gaining increasing attention from a variety of disciplines, particularly in supervised machine learning for classification tasks. The k nearest neighbors (kNN) classifier is often used as a natural way to edit the training set
Externí odkaz:
https://doaj.org/article/0b95a561f97b4698ae431725f5a30067
Publikováno v:
Journal of Energy Chemistry. 78:401-411
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f311e8f0093b7d022a33bbb0b738840
https://doi.org/10.1016/j.jechem.2022.12.052
https://doi.org/10.1016/j.jechem.2022.12.052
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:2916-2930
Mitigating label noise is a crucial problem in classification. Noise filtering is an effective method of dealing with label noise which does not need to estimate the noise rate or rely on any loss function. However, most filtering methods focus mainl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65918dd4c77d376d881149ef37fb5713
https://doi.org/10.1109/tnnls.2020.3047046
https://doi.org/10.1109/tnnls.2020.3047046
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 34:1231-1242
Feature reduction is an important aspect of Big Data analytics on today's ever-larger datasets. Rough sets are a classical method widely applied in attribute reduction. Most rough set algorithms use the priori domain knowledge of a dataset to process
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0beb84bbe0cb01f74e3deb9a3765933
https://doi.org/10.1109/tkde.2020.2997039
https://doi.org/10.1109/tkde.2020.2997039
Autor:
Xin Liang, Sheng Di, Franck Cappello, Mukund Raj, Chunhui Liu, Kenji Ono, Zizhong Chen, Tom Peterka, Hanqi Guo
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. :1-16
The objective of this work is to develop error-bounded lossy compression methods to preserve topological features in 2D and 3D vector fields. Specifically, we explore the preservation of critical points in piecewise linear and bilinear vector fields.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91a0a9083734f55dc934d987edb32f43
https://doi.org/10.1109/tvcg.2022.3214821
https://doi.org/10.1109/tvcg.2022.3214821
Autor:
Shuyin Xia, Shulin Wu, Xinxing Chen, Guoyin Wang, Xinbo Gao, Qinghua Zhang, Elisabeth Giem, Zizhong Chen
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. :1-15
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d82b5e6c750b4abf5b9c47a8b4b72773
https://doi.org/10.1109/tkde.2022.3222447
https://doi.org/10.1109/tkde.2022.3222447
Publikováno v:
ACM Transactions on Parallel Computing.
The current trend of performance growth in HPC systems is accompanied by a massive increase in energy consumption. In this paper, we introduce GreenMD, an energy-efficient framework for heterogeneous systems for LU factorization utilizing multi-GPUs.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8af5ef768091beb0585d002fd17e8ef
https://doi.org/10.1145/3583590
https://doi.org/10.1145/3583590
Publikováno v:
2022 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5088010239c8ab923c9ed9ab6448b88e
https://doi.org/10.1109/tocs56154.2022.10015914
https://doi.org/10.1109/tocs56154.2022.10015914
Publikováno v:
SC22: International Conference for High Performance Computing, Networking, Storage and Analysis.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::020718fe08864bae296cbd5d77f2c5b3
https://doi.org/10.1109/sc41404.2022.00067
https://doi.org/10.1109/sc41404.2022.00067