Parallel back-propagation for sales prediction on transputer systems

DC ElementWertSprache
dc.contributor.authorThiesing, F.M.
dc.contributor.authorMiddelberg, U.
dc.contributor.authorVornberger, O.
dc.date.accessioned2021-12-23T16:27:31Z-
dc.date.available2021-12-23T16:27:31Z-
dc.date.issued1995
dc.identifier.issn13837575
dc.identifier.urihttps://osnascholar.ub.uni-osnabrueck.de/handle/unios/15494-
dc.descriptionConference of Proceedings of the 1995 3rd World Transputer Congress, WTC ; Conference Date: 4 September 1995 Through 6 September 1995; Conference Code:45265
dc.description.abstractIn his paper artificial neural networks are adapted to a short term forecast for the sale of articles in supermarkets. The data is modelled to fit into feedforward multilayer perceptron networks that are trained by the back-propagation algorithm. For enhancement this has been parallelized in different manners. One batch and two on-line training variants are implemented on parallel Transputer-based PARSYTEC systems: a GCel with T805 and a GC/PP with PowerPC processors and Transputer communication links. The parallelizations run with both the runtime environments PARIX and PVM.
dc.language.isoen
dc.publisherIOS Press, Amsterdam, Netherlands
dc.relation.ispartofConcurrent Systems Engineering Series
dc.subjectBackpropagation
dc.subjectForecasting
dc.subjectInterconnection networks
dc.subjectManagement
dc.subjectMarketing
dc.subjectParallel processing systems
dc.subjectPlanning
dc.subjectTransputers, Batches
dc.subjectFeedforward multilayer perceptron networks, Neural networks
dc.titleParallel back-propagation for sales prediction on transputer systems
dc.typebook
dc.identifier.scopus2-s2.0-0029462422
dc.identifier.urlhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-0029462422&partnerID=40&md5=360b36175af1e077662ad5462b6cd33e
dc.description.volume46
dc.description.startpage318
dc.description.endpage331
dc.publisher.placeHarrogate, UK
dcterms.isPartOf.abbreviationConcurrent Syst Eng Ser
crisitem.author.deptFB 06 - Mathematik/Informatik-
crisitem.author.deptidfb06-
crisitem.author.parentorgUniversität Osnabrück-
crisitem.author.netidVoOl593-
Zur Kurzanzeige

Seitenaufrufe

4
Letzte Woche
0
Letzter Monat
0
geprüft am 06.06.2024

Google ScholarTM

Prüfen