DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Youngbeom | ko |
dc.contributor.author | Kim, Hyeonuk | ko |
dc.contributor.author | Choi, Seungkyu | ko |
dc.contributor.author | Shin, Jaekang | ko |
dc.contributor.author | Kim, Lee-Sup | ko |
dc.date.accessioned | 2023-01-04T05:00:17Z | - |
dc.date.available | 2023-01-04T05:00:17Z | - |
dc.date.created | 2022-11-23 | - |
dc.date.created | 2022-11-23 | - |
dc.date.issued | 2023-01 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, v.42, no.1, pp.332 - 336 | - |
dc.identifier.issn | 0278-0070 | - |
dc.identifier.uri | http://hdl.handle.net/10203/303928 | - |
dc.description.abstract | To adopt deep neural networks in resource constrained edge devices, various energy-and memory-efficient embedded accelerators have been proposed. However, most off-the-shelf networks are well-trained with vast amounts of data, but unexplored users’ data or accelerator’s constraints can lead to unexpected accuracy loss. Therefore, a network adaptation suitable for each user and device is essential to make a high confidence prediction in given environment. We propose simple but efficient data reformation methods that can effectively reduce the communication cost with off-chip memory during the adaptation. Our proposal utilizes the data’s zero-centered distribution and spatial correlation to concentrate the sporadically spread bit-level zeros to the units of value. Consequently, we reduced communication volume by up to 55.6% per task with an area overhead of 0.79% during the personalization training. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Energy-Efficient CNN Personalized Training by Adaptive Data Reformation | - |
dc.type | Article | - |
dc.identifier.wosid | 000920800400027 | - |
dc.identifier.scopusid | 2-s2.0-85129624792 | - |
dc.type.rims | ART | - |
dc.citation.volume | 42 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 332 | - |
dc.citation.endingpage | 336 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS | - |
dc.identifier.doi | 10.1109/TCAD.2022.3170845 | - |
dc.contributor.localauthor | Kim, Lee-Sup | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Convolutional neural network (CNN) | - |
dc.subject.keywordAuthor | data compression | - |
dc.subject.keywordAuthor | personalization training | - |
dc.subject.keywordAuthor | sparsity | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.