Weight Exchange in Distributed Learning

dc.contributor.author Dorner, Julian
dc.contributor.author Favrichon, Samuel
dc.contributor.author Öğrenci, Arif Selçuk
dc.date.accessioned 2019-06-27T08:01:54Z
dc.date.available 2019-06-27T08:01:54Z
dc.date.issued 2016
dc.department Fakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü en_US
dc.description.abstract Neural 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.identifier.citationcount 0
dc.identifier.doi 10.1109/IJCNN.2016.7727591 en_US
dc.identifier.endpage 3084
dc.identifier.isbn 9781509006199
dc.identifier.issn 2161-4393 en_US
dc.identifier.issn 2161-4393
dc.identifier.scopus 2-s2.0-85007227791 en_US
dc.identifier.startpage 3081 en_US
dc.identifier.uri https://hdl.handle.net/20.500.12469/502
dc.identifier.uri https://doi.org/10.1109/IJCNN.2016.7727591
dc.identifier.wos WOS:000399925503038 en_US
dc.institutionauthor Öğrenci, Arif Selçuk en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.journal 2016 International Joint Conference On Neural Networks (IJCNN) en_US
dc.relation.publicationcategory Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.scopus.citedbyCount 1
dc.title Weight Exchange in Distributed Learning en_US
dc.type Conference Object en_US
dc.wos.citedbyCount 0
dspace.entity.type Publication

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Weight Exchange in Distributed Learning_2.pdf
Size:
179.59 KB
Format:
Adobe Portable Document Format
Description: