Zobrazeno 1 - 10
of 378
pro vyhledávání: '"Shi, Liangliang"'
Optimal transport (OT) is attracting increasing attention in machine learning. It aims to transport a source distribution to a target one at minimal cost. In its vanilla form, the source and target distributions are predetermined, which contracts to
Externí odkaz:
http://arxiv.org/abs/2401.11418
Autor:
Shi, Liangliang1 (AUTHOR) shiliangliang@caeri.com.cn, Zhang, Honghao1,2 (AUTHOR) honghao_zhang@sdu.edu.cn, Wu, Lintao3 (AUTHOR) wlt052410@163.com, Liu, Yu1 (AUTHOR) liuyu@caeri.com.cn, Cheng, Kuo1 (AUTHOR) chengkuo@caeri.com.cn, Han, Yong4 (AUTHOR) yonghan@xmut.edu.cn, Wang, Danqi3 (AUTHOR) danqi_wang@csust.edu.cn
Publikováno v:
Biomimetics (2313-7673). Mar2024, Vol. 9 Issue 3, p124. 17p.
Autor:
Zhao, Xueyan, Zhou, Yan, Peng, Gang, Wen, Lu, Hong, Xiaohua, Hu, Yuan, Wu, Bian, Liu, Xixi, Zhang, Zhanjie, Xiao, Guixiang, JingHuang, Ding, Qian, Yang, Chengzhang, Xiong, Xingao, Ma, Hui, Shi, Liangliang, Yang, Jinsong, Wei, Jielin, Qin, You, Wan, Chao, Zhong, Yi, Leng, Yangming, Zhang, Tao, Wu, Gang, MinYao, Jia, Yulin, Zhang, Xiaomeng, Yang, Kunyu
Publikováno v:
In Oral Oncology September 2024 156
Publikováno v:
In International Journal of Biological Macromolecules August 2024 275 Part 1
Despite its success, generative adversarial networks (GANs) still suffer from mode collapse, i.e., the generator can only map latent variables to a partial set of modes in the target distribution. In this paper, we analyze and seek to regularize this
Externí odkaz:
http://arxiv.org/abs/2106.00563
Autor:
Cao, Haishun, Gong, Mingxi, Wu, Tingquan, Zhang, Changyuan, Anwar, Ali, Shi, Liangliang, Song, Shiwei
Publikováno v:
In Scientia Horticulturae 15 March 2024 328
Publikováno v:
In Journal of Biomechanics March 2024 165
Publikováno v:
In Journal of Environmental Sciences March 2024 137:639-650
Autor:
Shi Liangliang, He Xiaoting
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
In this paper, the Japanese sentences are processed by using the participle technology for participle and syntactic analysis, on the basis of which different weight values are assigned to different Japanese sentence components, and at the same time,
Externí odkaz:
https://doaj.org/article/9045ce54615b4b839a8d0ee488195833
Autor:
He Xiaoting, Shi Liangliang
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
Traditional Japanese translation methods have certain disadvantages, and the introduction of artificial intelligence technology into them can enhance the effect of Japanese interpretation and translation. In this paper, the Japanese language data of
Externí odkaz:
https://doaj.org/article/96d1e7756097411aaab8f24d624a8e5a