Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Hengyue Pan"'
Publikováno v:
Neural Processing Letters. 54:3249-3261
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6dd08e6fd76307fa9d3b96fba5f1b9c5
https://doi.org/10.1007/s11063-022-10766-0
https://doi.org/10.1007/s11063-022-10766-0
Autor:
Peijie Dong, Xin Niu, Lujun Li, Zhiliang Tian, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
Neural architecture search (NAS) has made tremendous progress in the automatic design of effective neural network structures but suffers from a heavy computational burden. One-shot NAS significantly alleviates the burden through weight sharing and im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9753cf587a1451cb0f4d7e563062914
http://arxiv.org/abs/2301.09850
http://arxiv.org/abs/2301.09850
Autor:
Peijie Dong, Xin Niu, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field. Conventional efficient learning methods focus on lightweight convolution desig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9be25ff6c96cfeb806b871bbcc33d012
Publikováno v:
MultiMedia Modeling ISBN: 9783031278174
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5ce488f04d1a0a20b88abc0860c8843
https://doi.org/10.1007/978-3-031-27818-1_56
https://doi.org/10.1007/978-3-031-27818-1_56
Publikováno v:
2022 IEEE High Performance Extreme Computing Conference (HPEC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8ed7b01169dd7b4019e013ae486d96c
https://doi.org/10.1109/hpec55821.2022.9926298
https://doi.org/10.1109/hpec55821.2022.9926298
Publikováno v:
International Conference on Neural Networks, Information, and Communication Engineering (NNICE 2022).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ffef9703cc8ddaa1e579773aeefef41
https://doi.org/10.1117/12.2639214
https://doi.org/10.1117/12.2639214
Publikováno v:
2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51a6a478f6869015297ad9975d7fd491
https://doi.org/10.1109/icaibd55127.2022.9820180
https://doi.org/10.1109/icaibd55127.2022.9820180
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::828f84d1a35700091811cba946f86e78
https://doi.org/10.1109/icassp43922.2022.9747280
https://doi.org/10.1109/icassp43922.2022.9747280
Publikováno v:
Neurocomputing. 380:201-211
In this paper, we propose a novel annealed gradient descent (AGD) algorithm for deep learning. AGD optimizes a sequence of gradually improving smoother mosaic functions that approximate the original non-convex objective function according to an annea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c300c17ab121fd2b4ff4e8637d098af1
https://doi.org/10.1016/j.neucom.2019.11.021
https://doi.org/10.1016/j.neucom.2019.11.021
Publikováno v:
Remote Sensing Letters. 11:323-332
Direction and width prediction have become hot topics in accurate ship location, while the resolution of remote sensing data has been increasing. In the current machine learning, demand for extensi...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::821c77d8f25783bc1132240cb0194a54
https://doi.org/10.1080/2150704x.2020.1716406
https://doi.org/10.1080/2150704x.2020.1716406