Zobrazeno 1 - 10
of 1 641
pro vyhledávání: '"Yue, Yun"'
In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision. While these methods have achieved state-of-the-art performance on various metric learning tasks using hyperbolic distance measurements,
Externí odkaz:
http://arxiv.org/abs/2404.15523
Adaptive optimizers, such as Adam, have achieved remarkable success in deep learning. A key component of these optimizers is the so-called preconditioning matrix, providing enhanced gradient information and regulating the step size of each gradient d
Externí odkaz:
http://arxiv.org/abs/2312.01658
Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. In this paper, we revisit the
Externí odkaz:
http://arxiv.org/abs/2305.15817
Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has shown compet
Externí odkaz:
http://arxiv.org/abs/2302.01409
Autor:
Yue, Yun, Han, Jin, Shen, Xinyan, Zhu, Fei, Liu, Yikang, Zhang, Wenqing, Xia, Wei, Wu, Mengqi
Publikováno v:
In Carbohydrate Polymers 15 September 2024 340
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-15 (2023)
Abstract A scientific and rational evaluation of teaching is essential for personalized learning. In the current teaching assessment model that solely relies on Grade Point Average (GPA), learners with different learning abilities may be classified a
Externí odkaz:
https://doaj.org/article/de461f87d87b484fbe7441bce9a46093
Autor:
Chen-Yue Liu, Jian-Bei Chen, Yue-Yun Liu, Xue-Ming Zhou, Man Zhang, You-Ming Jiang, Qing-Yu Ma, Zhe Xue, Zong-Yao Zhao, Xiao-Juan Li, Jia-Xu Chen
Publikováno v:
Chinese Medicine, Vol 18, Iss 1, Pp 1-4 (2023)
Externí odkaz:
https://doaj.org/article/18af570247374227bec83641af29e057
Autor:
Yue, Yun, Liu, Yongchao, Tong, Suo, Li, Minghao, Zhang, Zhen, Wen, Chunyang, Bao, Huanjun, Gu, Lihong, Gu, Jinjie, Mu, Yixiang
Publikováno v:
Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part III
We develop a novel framework that adds the regularizers of the sparse group lasso to a family of adaptive optimizers in deep learning, such as Momentum, Adagrad, Adam, AMSGrad, AdaHessian, and create a new class of optimizers, which are named Group M
Externí odkaz:
http://arxiv.org/abs/2107.14432
Publikováno v:
In World Neurosurgery May 2024 185:e1224-e1229
Publikováno v:
In Accident Analysis and Prevention May 2024 199