Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Yang, Qihong"'
In this work, we propose an end-to-end adaptive sampling neural network (MMPDE-Net) based on the moving mesh method, which can adaptively generate new sampling points by solving the moving mesh PDE. This model focuses on improving the quality of samp
Externí odkaz:
http://arxiv.org/abs/2311.16167
In practical engineering experiments, the data obtained through detectors are inevitably noisy. For the already proposed data-enabled physics-informed neural network (DEPINN) \citep{DEPINN}, we investigate the performance of DEPINN in calculating the
Externí odkaz:
http://arxiv.org/abs/2303.08455
In this article, we propose two kinds of neural networks inspired by power method and inverse power method to solve linear eigenvalue problems. These neural networks share similar ideas with traditional methods, in which the differential operator is
Externí odkaz:
http://arxiv.org/abs/2209.11134
We present a data-enabled physics-informed neural network (DEPINN) with comprehensive numerical study for solving industrial scale neutron diffusion eigenvalue problems (NDEPs). In order to achieve an engineering acceptable accuracy for complex engin
Externí odkaz:
http://arxiv.org/abs/2208.13483
Autor:
Yang, Qihong1,2 (AUTHOR), To, Kenneth Kin Wah3 (AUTHOR), Hu, Guilin4 (AUTHOR), Fu, Kai2 (AUTHOR), Yang, Chuan2 (AUTHOR), Zhu, Shuangli2 (AUTHOR), Pan, Can2 (AUTHOR), Wang, Fang2 (AUTHOR), Luo, Kewang1 (AUTHOR) kewangluo@126.com, Fu, Liwu2 (AUTHOR) fulw@mail.sysu.edu.cn
Publikováno v:
Cell Communication & Signaling. 6/13/2024, Vol. 22 Issue 1, p1-15. 15p.
Publikováno v:
In Neural Networks December 2024 180
Autor:
Yu, Chuying, Liang, Xuyu, Li, Weiliu, Jiang, Yaqin, Yang, Qihong, Gan, Guiyun, Wang, Peng, Cai, Liangyu, Li, Wenjia, Zhang, Xiaosheng, Wang, Yikui
Publikováno v:
In Scientia Horticulturae 1 December 2024 338
Autor:
Bian, Zhi, Zhou, Shaojun, Fu, Hao, Yang, Qihong, Sun, Zhenqi, Tang, Junjie, Liu, Guiquan, Liu, Kaikui, Li, Xiaolong
For better user satisfaction and business effectiveness, more and more attention has been paid to the sequence-based recommendation system, which is used to infer the evolution of users' dynamic preferences, and recent studies have noticed that the e
Externí odkaz:
http://arxiv.org/abs/2107.05474
Autor:
Gutierrez, Vincent, Kim-Vasquez, Doyeon, Shum, Michael, Yang, Qihong, Dikeman, Dante, Louie, Stan G., Shirihai, Orian S., Tsukamoto, Hidekazu, Liesa, Marc
Publikováno v:
In Redox Biology April 2024 70
The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it difficult
Externí odkaz:
http://arxiv.org/abs/2012.07335