Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Jaeha Kung"'
Autor:
Matthew Bodenham, Jaeha Kung
Publikováno v:
IEEE Access, Vol 12, Pp 124428-124439 (2024)
Deployment of language models to resource-constrained edge devices is an uphill battle against their ever-increasing size. The task transferability of language models makes deployment to the edge an attractive application. Prior neural architecture s
Externí odkaz:
https://doaj.org/article/beab71169cf84eb48136e9ff321f53c4
Autor:
Sangwoo Hwang, Yujin Hwang, Duhee Kim, Junhee Lee, Han Kyoung Choe, Junghyup Lee, Hongki Kang, Jaeha Kung
Publikováno v:
Frontiers in Neuroscience, Vol 17 (2023)
Recent developments in artificial neural networks and their learning algorithms have enabled new research directions in computer vision, language modeling, and neuroscience. Among various neural network algorithms, spiking neural networks (SNNs) are
Externí odkaz:
https://doaj.org/article/cc16cc0993f0458c9b4935476be7e452
Publikováno v:
IEEE Access, Vol 8, Pp 179837-179844 (2020)
Cache side-channel attack is one of the critical security threats to modern computing systems. As a representative cache side-channel attack, Flush+Reload attack allows an attacker to steal confidential information (e.g., private encryption key) by m
Externí odkaz:
https://doaj.org/article/fc61e8fa306e472f84064b4c37b6db9d
Publikováno v:
IEEE Transactions on Circuits and Systems II: Express Briefs. 70:1154-1158
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::718235826bea6eb1212a2f4caee7afa0
https://doi.org/10.1109/tcsii.2022.3217696
https://doi.org/10.1109/tcsii.2022.3217696
Publikováno v:
IEEE Transactions on Computers. :1-14
Training deep neural networks (DNNs) is a computationally expensive job, which can take weeks or months even with high performance GPUs. As a remedy for this challenge, community has started exploring the use of more efficient data representations in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a344fd0c719c6434e63c88f62d659bed
https://doi.org/10.1109/tc.2023.3253050
https://doi.org/10.1109/tc.2023.3253050
Publikováno v:
IEEE Transactions on Emerging Topics in Computing. 10:1428-1442
We propose a HW-SW co-optimization technique to perform energy-efficient spGEMM operations for deep learning. First, we present an automated pruning algorithm, named AutoRelax, that allows some level of relaxation to achieve higher compression ratio.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f28f63a12fcc19bb8468a533afd0c44
https://doi.org/10.1109/tetc.2021.3089848
https://doi.org/10.1109/tetc.2021.3089848
Publikováno v:
IEEE Computer Architecture Letters. 21:157-160
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d689706e53b24fc245849e9ef8f1f72
https://doi.org/10.1109/lca.2022.3227560
https://doi.org/10.1109/lca.2022.3227560
Publikováno v:
ACM Transactions on Design Automation of Electronic Systems. 27:1-24
Recent advances in deep learning have made it possible to implement artificial intelligence in mobile devices. Many studies have put a lot of effort into developing lightweight deep learning models optimized for mobile devices. To overcome the perfor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c94425b722801d901ffe356a2bb5714
https://doi.org/10.1145/3513085
https://doi.org/10.1145/3513085
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 69:1171-1184
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ab01ebc8fe908cd3a0842339fb4f45b
https://doi.org/10.1109/tcsi.2021.3134010
https://doi.org/10.1109/tcsi.2021.3134010
Autor:
Taeryoung Seol, Sehwan Lee, Geunha Kim, Samhwan Kim, Euiseong Kim, Seungyeob Baik, Jaeha Kung, Ji-Woong Choi, Arup K. George, Junghyup Lee
Publikováno v:
2023 IEEE International Solid- State Circuits Conference (ISSCC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f74cc83f43e8be5f05286ae77bcda84f
https://doi.org/10.1109/isscc42615.2023.10067537
https://doi.org/10.1109/isscc42615.2023.10067537