Full metadata record

DC Field Value Language
dc.contributor.author Kim, Jinhwi ko
dc.contributor.author Galanopoulos, Apostolos ko
dc.contributor.author Joseph, Jude Vivek ko
dc.contributor.author Kwak, Jeongho ko
dc.date.accessioned 2021-01-29T07:28:11Z -
dc.date.available 2021-01-29T07:28:11Z -
dc.date.created 2021-01-14 -
dc.date.issued 2020-10-21 -
dc.identifier.citation 11th International Conference on Information and Communication Technology Convergence, ICTC 2020, pp.22 - 24 -
dc.identifier.isbn 9781728167589 -
dc.identifier.issn 2162-1233 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/12888 -
dc.description.abstract In this paper, we explore an impact of GPU/CPU scaling of a state-of-the-art AI embedded device on its energy consumption and AI performance. We use Nvidia Jetson TX2 as an experiment device thanks to its tractability to scale GPU/CPU and modify AI framework and libraries. Via extensive experiment in various ML (Machine Learning) scenarios, i.e., face recognition and objective detection, we demonstrate a clear tradeoff between GPU/CPU scaling, energy consumption (of GPU/CPU as well as entire device) and training/inference speed. Finally, we envision a future work aiming to optimize processing and networking resources simultaneously at an extended scenario that multiple AI embedded devices cooperate with each other for a common AI application. © 2020 IEEE. -
dc.language English -
dc.publisher IEEE Computer Society -
dc.title A Study on Energy-Process-Latency Tradeoff in Embedded Artificial Intelligence -
dc.type Conference -
dc.identifier.doi 10.1109/ICTC49870.2020.9289270 -
dc.identifier.scopusid 2-s2.0-85098986064 -
dc.type.local Article(Overseas) -
dc.type.rims CONF -
dc.description.journalClass 1 -
dc.contributor.localauthor Kwak, Jeongho -
dc.contributor.nonIdAuthor Galanopoulos, Apostolos -
dc.contributor.nonIdAuthor Joseph, Jude Vivek -
dc.identifier.citationStartPage 22 -
dc.identifier.citationEndPage 24 -
dc.identifier.citationTitle 11th International Conference on Information and Communication Technology Convergence, ICTC 2020 -
dc.identifier.conferencecountry KO -
dc.identifier.conferencelocation 제주 -

qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.