Výsledky vyhledávání - "Shao, Zhihui"

Report

Learning for Robust Combinatorial Optimization: Algorithm and Application

Autor: Shao, Zhihui, Yang, Jianyi, Shen, Cong, Ren, Shaolei

Learning to optimize (L2O) has recently emerged as a promising approach to solving optimization problems by exploiting the strong prediction power of neural networks and offering lower runtime complexity than conventional solvers. While L2O has been

Externí odkaz: http://arxiv.org/abs/2112.10377

Zobrazit plný text záznamu

Akademický článek

One stone three birds: Ni-catalyzed asymmetric allenylic substitution of allenic ethers, hydroalkylation of 1,3-enynes and double alkylation of enynyl ethers

Autor: Yang, Zhirong, Wang, Shan, Jiang, Ming, Li, Gengchen, Li, Long, Peng, Fangzhi, Shao, Zhihui

Publikováno v: In Chinese Chemical Letters August 2024 35(8)

Zobrazit plný text záznamu

Akademický článek

Facile preparation and efficient MnxCoy porous nanosheets for the sustainable catalytic process of soot

Autor: Hu, Miaomiao, Zhou, Kun, Zhao, Tingyi, Li, Zheng, Zeng, Xianhai, Yu, Di, Yu, Xuehua, Zhao, Mingqin, Shao, Zhihui, Xu, Qixiang, Cui, Bing

Publikováno v: In Green Energy & Environment March 2024 9(3):516-528

Zobrazit plný text záznamu

Report

Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring

Autor: Shao, Zhihui, Yang, Jianyi, Ren, Shaolei

Inference accuracy of deep neural networks (DNNs) is a crucial performance metric, but can vary greatly in practice subject to actual test datasets and is typically unknown due to the lack of ground truth labels. This has raised significant concerns

Externí odkaz: http://arxiv.org/abs/2007.01472

Zobrazit plný text záznamu

Report

Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets

Autor: Shao, Zhihui, Yang, Jianyi, Ren, Shaolei

To increase the trustworthiness of deep neural network (DNN) classifiers, an accurate prediction confidence that represents the true likelihood of correctness is crucial. Towards this end, many post-hoc calibration methods have been proposed to lever

Externí odkaz: http://arxiv.org/abs/2006.08914

Zobrazit plný text záznamu

Report

Your Noise, My Signal: Exploiting Switching Noise for Stealthy Data Exfiltration from Desktop Computers

Autor: Shao, Zhihui, Islam, Mohammad A., Ren, Shaolei

Attacks based on power analysis have been long existing and studied, with some recent works focused on data exfiltration from victim systems without using conventional communications (e.g., WiFi). Nonetheless, prior works typically rely on intrusive

Externí odkaz: http://arxiv.org/abs/2001.06729

Zobrazit plný text záznamu