Show simple item record

dc.contributor.authorÇayır, Aykut
dc.contributor.authorYenidoğan, Işıl
dc.contributor.authorDaǧ, Hasan
dc.date.accessioned2021-01-09T11:57:37Z
dc.date.available2021-01-09T11:57:37Z
dc.date.issued2018
dc.identifier.isbn978-153867893-0
dc.identifier.urihttps://doi.org/10.1109/UBMK.2018.8566383en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/3719
dc.description.abstractDeep learning is a subfield of machine learning and deep neural architectures can extract high level features automatically without handcraft feature engineering unlike traditional machine learning algorithms. In this paper, we propose a method, which combines feature extraction layers of a convolutional neural network with traditional machine learning algorithms, such as, support vector machine, gradient boosting machines, and random forest. All of the proposed hybrid models and the above mentioned machine learning algorithms are trained on three different datasets: MNIST, Fashion-MNIST, and CIFAR-10. Results show that the proposed hybrid models are more successful than traditional models while they are being trained from raw pixel values. In this study, we empower traditional machine learning algorithms for classification using feature extraction ability of deep neural network architectures and we are inspired by transfer learning methodology to this.en_US
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.titleFeature Extraction Based on Deep Learning for Some Traditional Machine Learning Methodsen_US
dc.typeConference Paperen_US
dc.relation.journalUBMK 2018 - 3rd International Conference on Computer Science and Engineeringen_US
dc.identifier.doi10.1109/UBMK.2018.8566383en_US
dc.contributor.khasauthorÇayır, Aykuten_US
dc.contributor.khasauthorYenidoğan, Işılen_US
dc.contributor.khasauthorDaǧ, Hasanen_US


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