Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Philipose, Matthai"'
Autor:
Chen, Lequn, Deng, Weixin, Canumalla, Anirudh, Xin, Yu, Zhuo, Danyang, Philipose, Matthai, Krishnamurthy, Arvind
Having large batch sizes is one of the most critical aspects of increasing the accelerator efficiency and the performance of DNN model inference. However, existing model serving systems cannot achieve adequate batch sizes while meeting latency object
Externí odkaz:
http://arxiv.org/abs/2308.07470
Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (more commonly) the whole model have the same low bitwidth (e.g., 2 bits)
Externí odkaz:
http://arxiv.org/abs/1805.10368
Autor:
Hsieh, Kevin, Ananthanarayanan, Ganesh, Bodik, Peter, Bahl, Paramvir, Philipose, Matthai, Gibbons, Phillip B., Mutlu, Onur
Large volumes of videos are continuously recorded from cameras deployed for traffic control and surveillance with the goal of answering "after the fact" queries: identify video frames with objects of certain classes (cars, bags) from many days of rec
Externí odkaz:
http://arxiv.org/abs/1801.03493
While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of neural netw
Externí odkaz:
http://arxiv.org/abs/1712.01340
Recent advances have enabled "oracle" classifiers that can classify across many classes and input distributions with high accuracy without retraining. However, these classifiers are relatively heavyweight, so that applying them to classify video is c
Externí odkaz:
http://arxiv.org/abs/1611.06453
Autor:
Urban, Gregor, Geras, Krzysztof J., Kahou, Samira Ebrahimi, Aslan, Ozlem, Wang, Shengjie, Caruana, Rich, Mohamed, Abdelrahman, Philipose, Matthai, Richardson, Matt
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy
Externí odkaz:
http://arxiv.org/abs/1603.05691
Autor:
Geras, Krzysztof J., Mohamed, Abdel-rahman, Caruana, Rich, Urban, Gregor, Wang, Shengjie, Aslan, Ozlem, Philipose, Matthai, Richardson, Matthew, Sutton, Charles
We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs. First, we show that a deep CNN with an architecture inspired by the models recently introduced in image
Externí odkaz:
http://arxiv.org/abs/1511.06433
Autor:
Philipose, Matthai.
Publikováno v:
Connect to this title online; UW restricted.
Thesis (Ph. D.)--University of Washington, 2005.
Vita. Includes bibliographical references (p. 240-245).
Vita. Includes bibliographical references (p. 240-245).
Externí odkaz:
http://hdl.handle.net/1773/6891
Publikováno v:
In Journal of Visual Communication and Image Representation May 2014 25(4):719-726
Publikováno v:
In Journal of Visual Communication and Image Representation May 2014 25(4):709-718