Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이성진 | - |
dc.contributor.author | Sejin Kim | - |
dc.date.accessioned | 2022-03-07T16:00:39Z | - |
dc.date.available | 2022-03-07T16:00:39Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://dgist.dcollection.net/common/orgView/200000594560 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/16324 | - |
dc.description | Near-data processing, Machine learning, Embedding, System architecture | - |
dc.description.statementofresponsibility | N | - |
dc.description.tableofcontents | I. Introduction 1 II. Background 3 2.1 Embedding Layer 3 2.2 Recommender System 4 III. Motivation 6 IV. Design of SEMS 9 4.1 Overall Architecture 9 4.2 Near-data Processing 10 4.3 Developing Applications 12 4.4 Interface 12 4.5 Model Parallelism 15 4.6 Optimization 18 V. Evaluation 20 5.1 Methodology 20 5.2 Experimental Results 21 VI. Related Work 26 VII. Conclusion 28 References 29 |
- |
dc.format.extent | 33 | - |
dc.language | eng | - |
dc.publisher | DGIST | - |
dc.subject | Near-data processing, Machine learning, Embedding, System architecture | - |
dc.title | SEMS: Scalable Embedding Memory System Exploiting Near-data Processing | - |
dc.type | Thesis | - |
dc.identifier.doi | 10.22677/thesis.200000594560 | - |
dc.description.degree | Master | - |
dc.contributor.department | Information and Communication Engineering | - |
dc.contributor.coadvisor | Jaeha Kung | - |
dc.date.awarded | 2022/02 | - |
dc.publisher.location | Daegu | - |
dc.description.database | dCollection | - |
dc.citation | XT.IM 김54 202202 | - |
dc.date.accepted | 1/21/22 | - |
dc.contributor.alternativeDepartment | 정보통신융합전공 | - |
dc.embargo.liftdate | 20270228 | - |
dc.contributor.affiliatedAuthor | Sejin Kim | - |
dc.contributor.affiliatedAuthor | Sungjin Lee | - |
dc.contributor.affiliatedAuthor | Jaeha Kung | - |
dc.contributor.alternativeName | 김세진 | - |
dc.contributor.alternativeName | Sungjin Lee | - |
dc.contributor.alternativeName | 궁재하 | - |
There are no files associated with this item.