Show simple item record

dc.contributor.authorÇalişan, M. and Talu, M.F.
dc.date.accessioned2021-04-08T12:07:51Z
dc.date.available2021-04-08T12:07:51Z
dc.date.issued2017
dc.identifier10.1109/IDAP.2017.8090270
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85039920699&doi=10.1109%2fIDAP.2017.8090270&partnerID=40&md5=ffaea955717b17714fc5936600da1cd1
dc.identifier.urihttp://acikerisim.bingol.edu.tr/handle/20.500.12898/4457
dc.description.abstractIn this study, artificial learning approach which can express high dimensional data in a lower space (autocoding) and known as "autoencoder" in the literature has been investigated in detail without using a predefined ready mathematical model. The most important feature of this method, which can be used in place of traditional feature extraction methods (HOG, SHIFT, SURF, Wavelet, etc.), is the ability to extract data-specific features. By applying the real (MNIST) and synthetic data, the effects on the success of the parameters of the method are measured and the results are presented in a tabular form. © 2017 IEEE.
dc.language.isoTurkish
dc.sourceIDAP 2017 - International Artificial Intelligence and Data Processing Symposium
dc.titleExamination of the effect of the basic parameters of the auto-encoder on coding performance [Oto-kodlayici'nin temel parametrelerinin kodlama başarimi üzerindeki etkisinin incelenmesi]


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record