Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Johann Hauswald"'
Autor:
Francisco Romero, Johann Hauswald, Aditi Partap, Daniel Kang, Matei Zaharia, Christos Kozyrakis
Publikováno v:
Proceedings of the VLDB Endowment. 16:447-460
The availability of vast video collections and the accuracy of ML models has generated significant interest in video analytics systems. Since naively processing all frames using expensive models is impractical, researchers have proposed optimizations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da3dafc955733c68a87b3616f086f6d7
https://doi.org/10.14778/3570690.3570695
https://doi.org/10.14778/3570690.3570695
Autor:
Jason Mars, Johann Hauswald, Parker Hill, Michael A. Laurenzano, Stefan Larson, Lingjia Tang, Jonathan K. Kummerfeld, Andrew Lee, Anish Mahendran
Publikováno v:
NAACL-HLT (1)
In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in datasets and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40c3f71aae02474cb2ef9b5ccd24156b
http://arxiv.org/abs/1904.03122
http://arxiv.org/abs/1904.03122
Autor:
Jason Mars, Johann Hauswald, Yunqi Zhang, Ronald G. Dreslinski, Cheng Li, Trevor Mudge, Arjun Khurana, Michael A. Laurenzano, Lingjia Tang, Austin Rovinski, Vinicius Petrucci
Publikováno v:
IEEE Micro. 36:42-53
Demand is expected to grow significantly for cloud services that deliver sophisticated artificial intelligence on the critical path of user queries, as is the case with intelligent personal assistants such as Apple's Siri. If the prediction of the tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bec9443862d4580c98ec77f494d98b40
https://doi.org/10.1109/mm.2016.37
https://doi.org/10.1109/mm.2016.37
Autor:
Yunqi Zhang, Michael A. Laurenzano, Arjun Khurana, Johann Hauswald, Lingjia Tang, Ronald G. Dreslinski, Jason Mars, Austin Rovinski, Yiping Kang, Hailong Yang, Trevor Mudge, Cheng Li, Vinicius Petrucci
Publikováno v:
ACM Transactions on Computer Systems. 34:1-32
As user demand scales for intelligent personal assistants (IPAs) such as Apple’s Siri, Google’s Google Now, and Microsoft’s Cortana, we are approaching the computational limits of current datacenter (DC) architectures. It is an open question ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d7892d0f86f0c73ac6e56f1f6175e56
https://doi.org/10.1145/2870631
https://doi.org/10.1145/2870631
Autor:
Trevor Mudge, Lingjia Tang, Cheng Li, Johann Hauswald, Jason Mars, Michael A. Laurenzano, Arjun Khurana, Vinicius Petrucci, Yunqi Zhang, Austin Rovinski, Ronald G. Dreslinski
Publikováno v:
ASPLOS
As user demand scales for intelligent personal assistants (IPAs) such as Apple's Siri, Google's Google Now, and Microsoft's Cortana, we are approaching the computational limits of current datacenter architectures. It is an open question how future se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::314c71b8ec7bdc2a478a817b352c8228
https://doi.org/10.1145/2786763.2694347
https://doi.org/10.1145/2786763.2694347
Autor:
Michael A. Laurenzano, Trevor Mudge, Quan Chen, Ronald G. Dreslinski, Lingjia Tang, Cheng Li, Johann Hauswald, Jason Mars, Yiping Kang
Publikováno v:
ISCA
As applications such as Apple Siri, Google Now, Microsoft Cortana, and Amazon Echo continue to gain traction, webservice companies are adopting large deep neural networks (DNN) for machine learning challenges such as image processing, speech recognit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f43568b0f87dff66b6640be7b6e08f4a
https://doi.org/10.1145/2749469.2749472
https://doi.org/10.1145/2749469.2749472
Autor:
Johann Hauswald, Ronald G. Dreslinski, Qi Zheng, Chaitali Chakrabarti, Trevor Mudge, Thomas Manville
Publikováno v:
ICASSP
Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2234d6fe821eb0875216f9dfb40f0c55
https://doi.org/10.1109/icassp.2014.6855235
https://doi.org/10.1109/icassp.2014.6855235