Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Seijoon Kim"'
Publikováno v:
IEEE Access, Vol 9, Pp 2633-2643 (2021)
Despite recent developments in deep learning and their success in computer vision, model efficiency is increasingly becoming a vital factor for their deployment in various real-world applications. To provide a more effective form of computational cap
Externí odkaz:
https://doaj.org/article/37ce5c602d484768b46ea3e403f1191b
Publikováno v:
IEEE Access, Vol 6, Pp 49601-49610 (2018)
Today’s data centers have various computing and storage devices for processing a myriad of data, and they generally consume a considerable amount of electrical energy. This paper proposes a smart grid-inspired methodology to observe and profile the
Externí odkaz:
https://doaj.org/article/64e994f1e2894130b057fc081bac97de
Publikováno v:
IEEE Access, Vol 9, Pp 2633-2643 (2021)
Despite recent developments in deep learning and their success in computer vision, model efficiency is increasingly becoming a vital factor for their deployment in various real-world applications. To provide a more effective form of computational cap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d1947afc317f026f88cf22261756fd6
https://doi.org/10.1109/access.2020.3047071
https://doi.org/10.1109/access.2020.3047071
Publikováno v:
IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 29:162-175
Memory-augmented neural networks (MANNs) were introduced to handle long-term dependent data efficiently. MANNs have shown promising results in question answering (QA) tasks that require holding contexts for answering a given question. As demands for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::952f5469557785c0bede2d298cfb85db
https://doi.org/10.1109/tvlsi.2020.3037166
https://doi.org/10.1109/tvlsi.2020.3037166
Binary memristive crossbars have gained huge attention as an energy-efficient deep learning hardware accelerator. Nonetheless, they suffer from various noises due to the analog nature of the crossbars. To overcome such limitations, most previous work
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1391782320f4a7efd4fa8b39d49cbdc
Publikováno v:
DAC
Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep neural netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::397cc2be2b0651e66bb3d7c341ca1be9
http://arxiv.org/abs/2003.11741
http://arxiv.org/abs/2003.11741
Publikováno v:
IEEE Access, Vol 6, Pp 49601-49610 (2018)
Today’s data centers have various computing and storage devices for processing a myriad of data, and they generally consume a considerable amount of electrical energy. This paper proposes a smart grid-inspired methodology to observe and profile the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3904c3e83787aa49fc28607c7c4556c4
https://doi.org/10.1109/access.2018.2868469
https://doi.org/10.1109/access.2018.2868469
Publikováno v:
DAC
The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability. Recently, conversion of a trained deep neural network to an SNN has improved the accuracy of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a93ef429986bd772f66c83ab38b8f19
https://doi.org/10.1145/3316781.3317822
https://doi.org/10.1145/3316781.3317822
Publikováno v:
DAC: Annual ACM/IEEE Design Automation Conference; 2020, Issue 57, p143-148, 6p
Publikováno v:
DATE
Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require recurrent d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02560fae2f996b707fc1a4f94e41f285