Zobrazeno 1 - 10
of 630
pro vyhledávání: '"Cheung, Peter P."'
Autor:
Wang, Erwei, Davis, James J., Stavrou, Georgios-Ilias, Cheung, Peter Y. K., Constantinides, George A., Abdelfattah, Mohamed S.
FPGA-specific DNN architectures using the native LUTs as independently trainable inference operators have been shown to achieve favorable area-accuracy and energy-accuracy tradeoffs. The first work in this area, LUTNet, exhibited state-of-the-art per
Externí odkaz:
http://arxiv.org/abs/2112.02346
Autor:
Que, Zhiqiang, Wang, Erwei, Marikar, Umar, Moreno, Eric, Ngadiuba, Jennifer, Javed, Hamza, Borzyszkowski, Bartłomiej, Aarrestad, Thea, Loncar, Vladimir, Summers, Sioni, Pierini, Maurizio, Cheung, Peter Y, Luk, Wayne
This paper presents novel reconfigurable architectures for reducing the latency of recurrent neural networks (RNNs) that are used for detecting gravitational waves. Gravitational interferometers such as the LIGO detectors capture cosmic events such a
Externí odkaz:
http://arxiv.org/abs/2106.14089
Autor:
Wang, Erwei, Davis, James J., Moro, Daniele, Zielinski, Piotr, Lim, Jia Jie, Coelho, Claudionor, Chatterjee, Satrajit, Cheung, Peter Y. K., Constantinides, George A.
The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for on-device
Externí odkaz:
http://arxiv.org/abs/2102.04270
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Research has shown that deep neural networks contain significant redundancy, and thus that high classification accuracy can be achieved even when weights and activations are quantized down to binary values. Network binarization on FPGAs greatly incre
Externí odkaz:
http://arxiv.org/abs/1910.12625
Autor:
Zhao, Yiren, Gao, Xitong, Guo, Xuan, Liu, Junyi, Wang, Erwei, Mullins, Robert, Cheung, Peter Y. K., Constantinides, George, Xu, Cheng-Zhong
Modern deep Convolutional Neural Networks (CNNs) are computationally demanding, yet real applications often require high throughput and low latency. To help tackle these problems, we propose Tomato, a framework designed to automate the process of gen
Externí odkaz:
http://arxiv.org/abs/1910.10075
Research has shown that deep neural networks contain significant redundancy, and that high classification accuracies can be achieved even when weights and activations are quantised down to binary values. Network binarisation on FPGAs greatly increase
Externí odkaz:
http://arxiv.org/abs/1904.00938
Autor:
Wang, Erwei, Davis, James J., Zhao, Ruizhe, Ng, Ho-Cheung, Niu, Xinyu, Luk, Wayne, Cheung, Peter Y. K., Constantinides, George A.
Publikováno v:
ACM Comput. Surv. 52, 2, Article 40 (May 2019), 39 pages
Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation have become a
Externí odkaz:
http://arxiv.org/abs/1901.06955