Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Parichay Kapoor"'
Autor:
Yongjoo Ahn, Geunsik Lim, Dongju Chae, MyungJoo Ham, Hyoungjoo Ahn, Jaeyun Jung, Gichan Jang, Wook Song, Ji-Hoon Lee, Ji-Joong Moon, Parichay Kapoor, Sangjung Woo
Publikováno v:
ICSE (SEIP)
We propose NNStreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to deep neural network applications. A new trend with the wide-spread of deep neural network applications is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcb6616e3dccf506213510dc225ff3b8
http://arxiv.org/abs/2101.06371
http://arxiv.org/abs/2101.06371
Autor:
Dongju Chae, Parichay Kapoor
Publikováno v:
ICSE (Workshops)
A hardware/software co-design for AI accelerators such as Neural Processing Unit (NPU) is essential not only to support the required functionality but also to meet primary goals of improved performance and power efficiency. However, their ever-changi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54ebbd0dc61b1c9579570d7bd07ffd7f
https://doi.org/10.1145/3387940.3392225
https://doi.org/10.1145/3387940.3392225
Publikováno v:
CVPR
Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model size reduction, achieving performance enhancement on devices is, however
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f364449d4c198ae53a5b79b0dc56f4e
https://doi.org/10.1109/cvpr42600.2020.00198
https://doi.org/10.1109/cvpr42600.2020.00198