Zobrazeno 1 - 10
of 714
pro vyhledávání: '"Zang, Xiao"'
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38125-38136, 2023
Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational costs, cal
Externí odkaz:
http://arxiv.org/abs/2305.17235
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/o
Externí odkaz:
http://arxiv.org/abs/2301.01731
Autor:
Zang, Xiao
This dissertation explores a series of new methods for clustering functional observations. The common feature shared by all the explored methods is the decomposition of functional data into amplitude and phase components. The first method which we ca
Neural network (NN)-based methods have emerged as an attractive approach for robot motion planning due to strong learning capabilities of NN models and their inherently high parallelism. Despite the current development in this direction, the efficien
Externí odkaz:
http://arxiv.org/abs/2208.11287
Autor:
Jiang, Ru, Xiao, Mei, Zhu, Hua-Yue, Zhao, Dan-Xia, Zang, Xiao, Fu, Yong-Qian, Zhu, Jian-Qiang, Wang, Qi, Liu, Huan
Publikováno v:
In International Journal of Biological Macromolecules July 2024 273 Part 1
Autor:
Freibott, Christina E., Jalali, Ali, Murphy, Sean M., Walley, Alexander Y., Linas, Benjamin P., Jeng, Philip J., Bratberg, Jeffrey, Marshall, Brandon D.L., Zang, Xiao, Green, Traci C., Morgan, Jake R.
Publikováno v:
In Journal of the American Pharmacists Association July-August 2024 64(4)
Autor:
Huang, Bin, Li, Jia-Ming, Zang, Xiao-Mei, Wang, Mei, Pan, Wei, Zhang, Ke-Da, He, Huan, Tan, Qiao-Guo, Miao, Ai-Jun
Publikováno v:
In Journal of Hazardous Materials 5 May 2024 469
Publikováno v:
In Journal of Genetics and Genomics May 2024 51(5):507-516
Autor:
Zang, Xiao, Jiang, Ru, Zhu, Hua-Yue, Wang, Qi, Fu, Yong-Qian, Zhao, Dan-Xia, Li, Jian-Bing, Liu, Huan
Publikováno v:
In Separation and Purification Technology 1 February 2024 330 Part C
Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most of the st
Externí odkaz:
http://arxiv.org/abs/2103.15027