Show simple item record

dc.contributor.advisorÇetin, A. Enis
dc.contributor.authorDeveci, Tuba Ceren
dc.date.accessioned2018-01-26T06:29:13Z
dc.date.available2018-01-26T06:29:13Z
dc.date.copyright2018-01
dc.date.issued2018-01
dc.date.submitted2018-01-25
dc.identifier.urihttp://hdl.handle.net/11693/35750
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (M.S.): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2018en_US
dc.descriptionIncludes bibliographical references (leaves 56-61).en_US
dc.description.abstractDeep learning has made significant improvements at many image processing tasks in recent years, such as image classification, object recognition and object detection. Convolutional neural networks (CNN), which is a popular deep learning architecture designed to process data in multiple array form, show great success to almost all detection & recognition problems and computer vision tasks. However, the number of parameters in a CNN is too high such that the computers require more energy and larger memory size. In order to solve this problem, we investigate the energy efficient network models based on CNN architecture. In addition to previously studied energy efficient models such as Binary Weight Network (BWN), we introduce novel energy efficient models. Hadamard-transformed Image Network (HIN) is a variation of BWN, but uses compressed Hadamardtransformed images as input. Binary Weight and Hadamard-transformed Image Network (BWHIN) is developed by combining BWN and HIN as a new energy ef- ficient model. Performances of the neural networks with di erent parameters and di erent CNN architectures are compared and analyzed on MNIST and CIFAR-10 datasets. It is observed that energy efficiency is achieved with a slight sacrifice at classification accuracy. Among all energy efficient networks, our novel ensemble model outperforms other energy efficient models.en_US
dc.description.statementofresponsibilityby Tuba Ceren Deveci.en_US
dc.format.extentxi, 67 leaves : charts (some color) ; 30 cmen_US
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectImage classificationen_US
dc.subjectDeep learningen_US
dc.subjectConvolutional neural networksen_US
dc.subjectEnergy efficiencyen_US
dc.subjectEnsemble modelsen_US
dc.titleImage classification with energy efficient hadamard neural networksen_US
dc.title.alternativeVerimli enerjili hadamard sinir ağları ile görüntü sınıflandırmasıen_US
dc.typeThesisen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.publisherBilkent Universityen_US
dc.description.degreeM.S.en_US
dc.identifier.itemidB157532
dc.embargo.release2021-01-03


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record