Improving Inference Time of Deep Learning Model with Partial Skip of ReLU-fused Matrix Multiplication Operations
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sungkyun | - |
dc.contributor.author | Kim, Jaemin | - |
dc.contributor.author | Kim, Nahun | - |
dc.contributor.author | Kang, Mincheal | - |
dc.contributor.author | Seo, Jiwon | - |
dc.date.accessioned | 2022-07-06T04:10:07Z | - |
dc.date.available | 2022-07-06T04:10:07Z | - |
dc.date.created | 2022-06-03 | - |
dc.date.issued | 2022-04 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138782 | - |
dc.description.abstract | Deep learning has been expanding its application, while large-scale models tend to perform well. However, as such a model inevitably requires a vast amount of resources and computations, lengthy inference time is a crucial, but essential, consequence that needs to be optimized for the efficient utilization of deep learning. To achieve the goal, we aim at fusing the Rectified Linear Unit and matrix multiplication in the inference process, which we may reduce the total amount of computation by predicting the sign bit of output value. We propose four methods of prediction and statistically choose an optimal method for reducing inference time with low accuracy loss. © 2022 IEEE. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Improving Inference Time of Deep Learning Model with Partial Skip of ReLU-fused Matrix Multiplication Operations | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Seo, Jiwon | - |
dc.identifier.doi | 10.1109/ICEIC54506.2022.9748210 | - |
dc.identifier.scopusid | 2-s2.0-85128867551 | - |
dc.identifier.wosid | 000942023400007 | - |
dc.identifier.bibliographicCitation | 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, pp.1 - 4 | - |
dc.relation.isPartOf | 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 | - |
dc.citation.title | 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 4 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Deep learning optimization | - |
dc.subject.keywordPlus | Fully-connected layer | - |
dc.subject.keywordPlus | Inference optimization | - |
dc.subject.keywordPlus | ITS applications | - |
dc.subject.keywordPlus | Large-scale modeling | - |
dc.subject.keywordPlus | Learning models | - |
dc.subject.keywordPlus | Learning optimizations | - |
dc.subject.keywordPlus | Matrix multiplication operation | - |
dc.subject.keywordPlus | Omitted computation | - |
dc.subject.keywordPlus | Optimisations | - |
dc.subject.keywordPlus | Matrix algebra | - |
dc.subject.keywordAuthor | deep learning optimization | - |
dc.subject.keywordAuthor | fully-connected layer | - |
dc.subject.keywordAuthor | inference optimization | - |
dc.subject.keywordAuthor | omitted computation | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9748210 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.