DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Seung-Jin | ko |
dc.contributor.author | Kim, Min-Su | ko |
dc.contributor.author | Kim, Kwan-Ho | ko |
dc.contributor.author | Kim, Joo-Young | ko |
dc.contributor.author | Yoo, Hoi-Jun | ko |
dc.date.accessioned | 2013-03-11T07:09:45Z | - |
dc.date.available | 2013-03-11T07:09:45Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2011-01 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON NEURAL NETWORKS, v.22, no.1, pp.64 - 73 | - |
dc.identifier.issn | 1045-9227 | - |
dc.identifier.uri | http://hdl.handle.net/10203/98615 | - |
dc.description.abstract | This paper presents the Visual Attention Engine (VAE), which is a digital cellular neural network (CNN) that executes the VA algorithm to speed up object-recognition. The proposed time-multiplexed processing element (TMPE) CNN topology achieves high performance and small area by integrating 4800 (80 x 60) cells and 120 PEs. Pipelined operation of the PEs and single-cycle global shift capability of the cells result in a high PE utilization ratio of 93%. The cells are implemented by 6T static random access memory-based register files and dynamic shift registers to enable a small area of 4.5 mm(2). The bus connections between PEs and cells are optimized to minimize power consumption. The VAE is integrated within an object-recognition system-on-chip (SoC) fabricated in the 0.13-mu m complementary metal-oxide-semiconductor process. It achieves 24 GOPS peak performance and 22 GOPS sustained performance at 200 MHz enabling one CNN iteration on an 80 x 60 pixel image to be completed in just 4.3 mu s. With VA enabled using the VAE, the workload of the object-recognition SoC is significantly reduced, resulting in 83% higher frame rate while consuming 45% less energy per frame without degradation of recognition accuracy. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | 24-GOPS 4.5-mm(2) Digital Cellular Neural Network for Rapid Visual Attention in an Object-Recognition SoC | - |
dc.type | Article | - |
dc.identifier.wosid | 000286010000006 | - |
dc.identifier.scopusid | 2-s2.0-78651264221 | - |
dc.type.rims | ART | - |
dc.citation.volume | 22 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 64 | - |
dc.citation.endingpage | 73 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON NEURAL NETWORKS | - |
dc.identifier.doi | 10.1109/TNN.2010.2085443 | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kim, Joo-Young | - |
dc.contributor.localauthor | Yoo, Hoi-Jun | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Cellular neural network | - |
dc.subject.keywordAuthor | object-recognition | - |
dc.subject.keywordAuthor | saliency map | - |
dc.subject.keywordAuthor | visual attention | - |
dc.subject.keywordPlus | MODEL | - |
dc.subject.keywordPlus | TIME | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.