Zobrazeno 1 - 10
of 837
pro vyhledávání: '"Tu Chun"'
Autor:
Le, Ba-Phuoc a, Chen, Jyh-Chen a, ⁎, Hu, Chieh b, Lin, Wei-Jie b, Tu, Chun-Chin b, Chen, Liang-Chin b
Publikováno v:
In Results in Engineering December 2024 24
Publikováno v:
In Science of the Total Environment 25 November 2024 953
Publikováno v:
In Plant Science March 2025 352
Chemical mechanical planarization of nanotwinned copper/polyimide for low temperature hybrid bonding
Autor:
He, Pin-Syuan, Tu, Chun-Wei, Shie, Kai-Cheng, Liu, Chien-Yu, Tsai, Hsin-Yu, Tran, Dinh-Phuc, Chen, Chih
Publikováno v:
In Journal of Electroanalytical Chemistry 15 September 2024 969
Autor:
Guo, Rui, Zhang, Qiang, Chen, Chang Zhao, Sun, Jie Ya, Tu, Chun Yan, He, Meng Xing, Shen, Ren Fang, Huang, Jiu, Zhu, Xiao Fang
Publikováno v:
In Journal of Hazardous Materials 15 May 2024 470
Publikováno v:
In Materials Science in Semiconductor Processing 15 March 2024 172
Autor:
Luss, Ronny, Chen, Pin-Yu, Dhurandhar, Amit, Sattigeri, Prasanna, Zhang, Yunfeng, Shanmugam, Karthikeyan, Tu, Chun-Chen
As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the global an
Externí odkaz:
http://arxiv.org/abs/1905.12698
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks
Autor:
Tu, Chun-Chen, Ting, Paishun, Chen, Pin-Yu, Liu, Sijia, Zhang, Huan, Yi, Jinfeng, Hsieh, Cho-Jui, Cheng, Shin-Ming
Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when
Externí odkaz:
http://arxiv.org/abs/1805.11770
Autor:
Dhurandhar, Amit, Chen, Pin-Yu, Luss, Ronny, Tu, Chun-Chen, Ting, Paishun, Shanmugam, Karthikeyan, Das, Payel
In this paper we propose a novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network. Given an input we find what should be %necessarily and minimally and suf
Externí odkaz:
http://arxiv.org/abs/1802.07623