Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Sangyun Oh"'
Publikováno v:
IEEE Access, Vol 8, Pp 106097-106108 (2020)
Lightweight neural networks that employ depthwise convolution have a significant computational advantage over those that use standard convolution because they involve fewer parameters; however, they also require more time, even with graphics processi
Externí odkaz:
https://doaj.org/article/fdcbc9b0d8be4eae90c44bc329c7504a
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:5220-5231
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::72db46ff67bb678a5f9cc9dffc889b87
https://doi.org/10.1109/tcad.2022.3150249
https://doi.org/10.1109/tcad.2022.3150249
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200823
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4ec75639022f5e4429fe3dd5f401327
https://doi.org/10.1007/978-3-031-20083-0_39
https://doi.org/10.1007/978-3-031-20083-0_39
Publikováno v:
CVPR
Quantization plays an important role in deep neural network (DNN) hardware. In particular, logarithmic quantization has multiple advantages for DNN hardware implementations, and its weakness in terms of lower performance at high precision compared wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cf2731fb596bde7ef85587e202cede4
https://doi.org/10.1109/cvpr46437.2021.00080
https://doi.org/10.1109/cvpr46437.2021.00080
Autor:
Sung-Hoon Kim, Mingyu Woo, Yesung Kang, Seokhyeong Kang, Yoonho Park, Taeho Lim, Eunji Kwon, Sangyun Oh
Publikováno v:
DATE
Owing to the growth of the size of convolutional neural networks (CNNs), quantization and loop tiling (also called loop breaking) are mandatory to implement CNN on an embedded system. However, channel loop tiling of quantized CNNs induces unexpected
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::239c375b1367ba853a466ea6c92eaecd
https://doi.org/10.23919/date48585.2020.9116465
https://doi.org/10.23919/date48585.2020.9116465
Autor:
Moonki Jung, Yong-Gon Koh, Sung-Hwan Kim, Sangyun Oh, Juhyun Son, Kyoung-Tak Kang, Sung-Jae Kim
Publikováno v:
Journal of Orthopaedic Research®. 36:2202-2209
The posterolateral corner (PLC) structures including the popliteofibular ligament (PFL), popliteus tendon (PT) and lateral collateral ligament (LCL) are important soft tissues for posterior translational, external rotational, and varus angulation kne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5569567036017eed4391df3123af7225
https://doi.org/10.1002/jor.23871
https://doi.org/10.1002/jor.23871
Autor:
Yong-Min Chun, Sung-Hwan Kim, Min Jung, Sang-Woo Jeon, Sung-Jae Kim, Chong-Hyuk Choi, Sangyun Oh
Publikováno v:
Arthroscopy and Orthopedic Sports Medicine. 5:19-28
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac491f348027711b46cb442c191d1560
https://doi.org/10.14517/aosm17017
https://doi.org/10.14517/aosm17017
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 36:1978-1988
Coarse-grained reconfigurable architectures (CGRAs) can provide extremely energy-efficient acceleration for applications that are rich in arithmetic operations such as digital signal processing and multimedia applications. Since those applications ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd25785eb0f5bf73594408fa49a432c4
https://doi.org/10.1109/tcad.2017.2682645
https://doi.org/10.1109/tcad.2017.2682645
Autor:
Kyoung-Tak, Kang, Yong-Gon, Koh, Juhyun, Son, Moonki, Jung, Sangyun, Oh, Sung-Jae, Kim, Sung-Hwan, Kim
Publikováno v:
Journal of orthopaedic research : official publication of the Orthopaedic Research Society.
The posterolateral corner (PLC) structures including the popliteofibular ligament (PFL), popliteus tendon (PT) and lateral collateral ligament (LCL) are important soft tissues for posterior translational, external rotational, and varus angulation kne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::506283ec4d9363dbda844d9c01de166d
https://pubmed.ncbi.nlm.nih.gov/29436742
https://pubmed.ncbi.nlm.nih.gov/29436742
Publikováno v:
DATE
The increasing use of machine learning algorithms, such as Convolutional Neural Networks (CNNs), makes the hardware accelerator approach very compelling. However the question of how to best design an accelerator for a given CNN has not been answered
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b85aeb517d1be6daa41826ee1d45e649
https://doi.org/10.23919/date.2017.7927162
https://doi.org/10.23919/date.2017.7927162