Advanced Search

Show simple item record

dc.contributor.authorDorner, Julian
dc.contributor.authorFavrichon, Samuel
dc.contributor.authorÖğrenci, Arif Selçuk
dc.date.accessioned2019-06-27T08:01:54Z
dc.date.available2019-06-27T08:01:54Z
dc.date.issued2016
dc.identifier.isbn9781509006199
dc.identifier.issn2161-4393en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/502
dc.identifier.urihttps://doi.org/10.1109/IJCNN.2016.7727591
dc.description.abstractNeural networks may allow different organisations to extract knowledge from the data they collect about a similar problem domain. Moreover learning algorithms usually benefit from being able to use more training instances. But the parties owning the data are not always keen on sharing it. We propose a way to implement distributed learning to improve the performance of neural networks without sharing the actual data among different organisations. This paper deals with the alternative methods of determining the weight exchange mechanisms among nodes. The key is to implement the epochs of learning separately at each node and then to select the best weight set among the different neural networks and to publish them to each node. The results show that an increase in performance can be achieved by deploying simple methods for weight exchange.en_US]
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectN/Aen_US
dc.titleWeight Exchange in Distributed Learningen_US
dc.typeconferenceObjecten_US
dc.identifier.startpage3081en_US
dc.identifier.endpage3084
dc.relation.journal2016 International Joint Conference On Neural Networks (IJCNN)en_US
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.identifier.wosWOS:000399925503038en_US
dc.identifier.doi10.1109/IJCNN.2016.7727591en_US
dc.identifier.scopus2-s2.0-85007227791en_US
dc.institutionauthorÖğrenci, Arif Selçuken_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record