File Download
There are no files associated with this item.
SFX Link
- Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
- Lee, Jongeun
- Intelligent Computing and Codesign Lab.
Views & Downloads
Detailed Information
Cited time in 
Cited time in 
Cited time in
Metadata Downloads
Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.citation.conferencePlace | KO | - |
| dc.citation.conferencePlace | Ramada Plaza Jeju HotelJeju | - |
| dc.citation.endPage | 78 | - |
| dc.citation.startPage | 77 | - |
| dc.citation.title | 13th International SoC Design Conference, ISOCC 2016 | - |
| dc.contributor.author | Seo, Jungwoo | - |
| dc.contributor.author | Yu, Joonsang | - |
| dc.contributor.author | Lee, Jongeun | - |
| dc.contributor.author | Choi, Kiyoung | - |
| dc.date.accessioned | 2023-12-19T20:06:16Z | - |
| dc.date.available | 2023-12-19T20:06:16Z | - |
| dc.date.created | 2017-02-10 | - |
| dc.date.issued | 2016-10-23 | - |
| dc.description.abstract | As deep neural networks grow larger, they suffer from a huge number of weights, and thus reducing the overhead of handling those weights becomes one of key challenges nowadays. This paper presents a new approach to binarizing neural networks, where the weights are pruned and forced to take degenerate binary values. Experimental results show that the proposed approach achieves significant reductions in computation and power consumption at the cost of a slight accuracy loss | - |
| dc.identifier.bibliographicCitation | 13th International SoC Design Conference, ISOCC 2016, pp.77 - 78 | - |
| dc.identifier.doi | 10.1109/ISOCC.2016.7799741 | - |
| dc.identifier.isbn | 978-146739308-9 | - |
| dc.identifier.scopusid | 2-s2.0-85010369342 | - |
| dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/37535 | - |
| dc.identifier.url | http://ieeexplore.ieee.org/document/7799741/authors | - |
| dc.language | 영어 | - |
| dc.publisher | 13th International SoC Design Conference, ISOCC 2016 | - |
| dc.title | A new approach to binarizing neural networks | - |
| dc.type | Conference Paper | - |
| dc.date.conferenceDate | 2016-10-23 | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.