Zobrazeno 1 - 10
of 95
pro vyhledávání: '"Jeon, Hyeran"'
The expansion of neural network sizes and the enhancement of image resolution through modern camera sensors result in heightened memory and power demands for neural networks. Reducing peak memory, which is the maximum memory consumed during the execu
Externí odkaz:
http://arxiv.org/abs/2406.03744
Transformer models gain popularity because of their superior inference accuracy and inference throughput. However, the transformer is computation-intensive, causing a long inference time. The existing works on transformer inference acceleration have
Externí odkaz:
http://arxiv.org/abs/2301.09262
Autor:
Bernard, Nigel, Nguyen, Hoa, Chandan, Aman, Jagdeeshan, Savyasachi, Prabhugaonkar, Namdev, Shah, Rutuja, Jeon, Hyeran
With the growing complexity of big data workloads that require abundant data and computation, data centers consume a tremendous amount of power daily. In an effort to minimize data center power consumption, several studies developed power models that
Externí odkaz:
http://arxiv.org/abs/2207.10217
With the growing burden of training deep learning models with large data sets, transfer-learning has been widely adopted in many emerging deep learning algorithms. Transformer models such as BERT are the main player in natural language processing and
Externí odkaz:
http://arxiv.org/abs/2207.09539
Autor:
Zelek, Ryan, Jeon, Hyeran
The role of unmanned vehicles for searching and localizing the victims in disaster impacted areas such as earthquake-struck zones is getting more important. Self-navigation on an earthquake zone has a unique challenge of detecting irregularly shaped
Externí odkaz:
http://arxiv.org/abs/2202.01421
Autor:
Karki, Aajna, Keshava, Chethan Palangotu, Shivakumar, Spoorthi Mysore, Skow, Joshua, Hegde, Goutam Madhukeshwar, Jeon, Hyeran
Deep neural networks (DNNs) have been proving the effectiveness in various computing fields. To provide more efficient computing platforms for DNN applications, it is essential to have evaluation environments that include assorted benchmark workloads
Externí odkaz:
http://arxiv.org/abs/1901.04987
Autor:
Yu, Wenjing1 (AUTHOR) wenjingy@upenn.edu, Jeon, Hyeran Helen1 (AUTHOR) hjeon@upenn.edu, Kim, Soriul2 (AUTHOR) soriul@korea.ac.kr, Dayo, Adeyinka3 (AUTHOR) dayoad@upenn.edu, Mupparapu, Muralidhar3 (AUTHOR) mmd@upenn.edu, Boucher, Normand S.1 (AUTHOR) hjeon@upenn.edu
Publikováno v:
Diagnostics (2075-4418). Jan2024, Vol. 14 Issue 1, p44. 13p.
Publikováno v:
In American Journal of Orthodontics & Dentofacial Orthopedics June 2023 163(6):793-801
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.