Detailed Information

Cited 0 time in webofscience Cited 198 time in scopus
Metadata Downloads

GPU implementation of neural networks

Full metadata record
DC FieldValueLanguage
dc.contributor.authorOh, KS-
dc.contributor.authorJung, K-
dc.date.available2018-05-10T18:04:32Z-
dc.date.created2018-04-17-
dc.date.issued2004-06-
dc.identifier.issn0031-3203-
dc.identifier.urihttp://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/19989-
dc.description.abstractGraphics processing unit (GPU) is used for a faster artificial neural network. It is used to implement the matrix multiplication of a neural network to enhance the time performance of a text detection system. Preliminary results produced a 20-fold performance enhancement using an ATI RADEON 9700 PRO board. The parallelism of a GPU is fully utilized by accumulating a lot of input feature vectors and weight vectors, then converting the many inner-product operations into one matrix operation. Further research areas include benchmarking the performance with various hardware and GPU-aware learning algorithms. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.-
dc.publisherPERGAMON-ELSEVIER SCIENCE LTD-
dc.relation.isPartOfPATTERN RECOGNITION-
dc.titleGPU implementation of neural networks-
dc.typeArticle-
dc.identifier.doi10.1016/j.patcog.2004.01.013-
dc.type.rimsART-
dc.identifier.bibliographicCitationPATTERN RECOGNITION, v.37, no.6, pp.1311 - 1314-
dc.description.journalClass1-
dc.identifier.wosid000221553100019-
dc.identifier.scopusid2-s2.0-2142662996-
dc.citation.endPage1314-
dc.citation.number6-
dc.citation.startPage1311-
dc.citation.titlePATTERN RECOGNITION-
dc.citation.volume37-
dc.contributor.affiliatedAuthorOh, KS-
dc.contributor.affiliatedAuthorJung, K-
dc.type.docTypeArticle-
dc.subject.keywordAuthorgraphics processing unit(GPU)-
dc.subject.keywordAuthorneural network(NN)-
dc.subject.keywordAuthormulti-layer perceptron-
dc.subject.keywordAuthortext detection-
dc.description.journalRegisteredClassscopus-
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Information Technology > Global School of Media > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Jung, Kee chul photo

Jung, Kee chul
College of Information Technology (Global School of Media)
Read more

Altmetrics

Total Views & Downloads

BROWSE