Zobrazeno 1 - 10
of 120
pro vyhledávání: '"Xu, Kaiqiang"'
Publikováno v:
In Expert Systems With Applications 15 October 2024 252 Part B
Autor:
Xu, Kaiqiang, Shahab, Asfandyar, Rinklebe, Jörg, Xiao, He, Li, Jieyue, Ye, Feng, Li, Yanhong, Wang, Dunqiu, Bank, Michael S., Wei, Gangjian
Publikováno v:
In Emerging Contaminants September 2024 10(3)
Autor:
Xu, Kaiqiang, Wan, Xinchen, Wang, Hao, Ren, Zhenghang, Liao, Xudong, Sun, Decang, Zeng, Chaoliang, Chen, Kai
In Machine Learning (ML) system research, efficient resource scheduling and utilization have always been an important topic given the compute-intensive nature of ML applications. In this paper, we introduce the design of TACC, a full-stack cloud infr
Externí odkaz:
http://arxiv.org/abs/2110.01556
Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly. In order to deploy and apply the neural networks to ed
Externí odkaz:
http://arxiv.org/abs/2001.06774
Publikováno v:
In Information Sciences December 2023 651
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Lu, Yang, Li, Xuemeng, Qian, Zhekai, Zhang, Tianheng, Xu, Kaiqiang, Zhai, Yanrong, Bi, Meihua
Publikováno v:
In Optical Fiber Technology September 2023 79
Autor:
Wang, Yu, Lyu, Yiran, Tong, Shilu, Ding, Cheng, Wei, Lan, Zhai, Mengying, Xu, Kaiqiang, Hao, Ruiting, Wang, Xiaochen, Li, Na, Luo, Yueyun, Li, Yonghong, Wang, Jiao
Publikováno v:
In Environmental Research 15 August 2023 231 Part 1
Latest algorithms for automatic neural architecture search perform remarkable but few of them can effectively design the number of channels for convolutional neural networks and consume less computational efforts. In this paper, we propose a method f
Externí odkaz:
http://arxiv.org/abs/1909.01861
Autor:
Yang, Chuanguang, An, Zhulin, Zhu, Hui, Hu, Xiaolong, Zhang, Kun, Xu, Kaiqiang, Li, Chao, Xu, Yongjun
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG mod
Externí odkaz:
http://arxiv.org/abs/1908.09699