DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, HW | - |
dc.contributor.author | Park, CI | - |
dc.date.accessioned | 2015-06-25T02:04:36Z | - |
dc.date.available | 2015-06-25T02:04:36Z | - |
dc.date.created | 2009-10-07 | - |
dc.date.issued | 2000-08 | - |
dc.identifier.issn | 0916-8532 | - |
dc.identifier.other | 2015-OAK-0000019122 | en_US |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/10371 | - |
dc.description.abstract | Learning process is essential for good performance when a neural network is applied to a practical application. The backpropagation algorithm [1] is a well-known learning method widely used in most neural networks. However. since the backpropagation algorithm is time-consuming, much research have been done to speed up the process. The block backpropagation algorithm. which seems to be more efficient than the backpropagation, is recently proposed by Coetzee in [2]. In this paper, we propose an efficient parallel algorithm fur the block backpropagation method and its performance model in mesh-connected parallel computer systems. The proposed algorithm adopts master-slave model for weight broadcasting and data parallelism for computation of weights. In order to validate our performance model. a neural network is implemented for printed character recognition application in the TiME [3] which is a prototype parallel machine consisting of 32 transputers connected in mesh topology. It is shown that speedup by our performance model is very close to that by experiments. | - |
dc.description.statementofresponsibility | open | en_US |
dc.language | English | - |
dc.publisher | IEICE-INST ELECTRONICS INFORMATION CO | - |
dc.relation.isPartOf | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | - |
dc.rights | BY_NC_ND | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/2.0/kr | en_US |
dc.title | An efficient parallel block backpropagation learning algorithm in transputer-based mesh-connected parallel computers | - |
dc.type | Article | - |
dc.contributor.college | 컴퓨터공학과 | en_US |
dc.author.google | Lee, HW | en_US |
dc.author.google | Park, CI | en_US |
dc.relation.volume | E83D | en_US |
dc.relation.issue | 8 | en_US |
dc.relation.startpage | 1622 | en_US |
dc.relation.lastpage | 1630 | en_US |
dc.contributor.id | 10054851 | en_US |
dc.relation.journal | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | en_US |
dc.relation.index | SCI급, SCOPUS 등재논문 | en_US |
dc.relation.sci | SCIE | en_US |
dc.collections.name | Journal Papers | en_US |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E83D, no.8, pp.1622 - 1630 | - |
dc.identifier.wosid | 000088984700002 | - |
dc.date.tcdate | 2018-03-23 | - |
dc.citation.endPage | 1630 | - |
dc.citation.number | 8 | - |
dc.citation.startPage | 1622 | - |
dc.citation.title | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | - |
dc.citation.volume | E83D | - |
dc.contributor.affiliatedAuthor | Park, CI | - |
dc.identifier.scopusid | 2-s2.0-34250787 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | ARTIFICIAL NEURAL NETWORKS | - |
dc.subject.keywordPlus | IMPLEMENTATION | - |
dc.subject.keywordPlus | ARCHITECTURES | - |
dc.subject.keywordAuthor | block backpropagation | - |
dc.subject.keywordAuthor | parallel computing | - |
dc.subject.keywordAuthor | load balancing | - |
dc.subject.keywordAuthor | transputer | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.