Performance analysis of different optimizers for deep learning-based Image recognition

Basit Öğe Kaydı
dc.authorid0000-0002-3188-8116
dc.contributor.authorPostalcıoğlu, Seda
dc.date.accessioned2021-06-23T19:54:35Z
dc.date.available2021-06-23T19:54:35Z
dc.date.issued2020
dc.departmentBAİBÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractDeep learning refers to Convolutional Neural Network (CNN). CNN is used for image recognition for this study. The dataset is named Fruits-360 and it is obtained from the Kaggle dataset. Seventy percent of the pictures are selected as training data and the rest of the images are used for testing. In this study, an image size is 100 x 100 x 3. Training is realized using Stochastic Gradient Descent with Momentum (sgdm), Adaptive Moment Estimation (adam) and Root Mean Square Propogation (rmsprop) techniques. The threshold value is determined as 98% for the training. When the accuracy reaches more than 98%, training is stopped. Calculation of the final validation accuracy is done using trained network. In this study, more than 98% of the predicted labels match the true labels of the validation set. Accuracies are calculated using test data for sgdm, adam and rmsprop techniques. The results are 98.08%, 98.85%, 98.88%, respectively. It is clear that fruits are recognized with good accuracy.en_US
dc.identifier.doi10.1142/S0218001420510039
dc.identifier.issn0218-0014
dc.identifier.issn1793-6381
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-85067280021en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.urihttps://doi.org/10.1142/S0218001420510039
dc.identifier.urihttps://hdl.handle.net/20.500.12491/10586
dc.identifier.volume34en_US
dc.identifier.wosWOS:000521944600003en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.institutionauthorPostalcioglu, Seda
dc.language.isoenen_US
dc.publisherWorld Scientific Publ Co Pte Ltden_US
dc.relation.ispartofInternational Journal Of Pattern Recognition And Artificial Intelligenceen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectConvolutional Neural Networken_US
dc.subjectImage Recognitionen_US
dc.subjectSgdm Adamen_US
dc.subjectRmspropen_US
dc.titlePerformance analysis of different optimizers for deep learning-based Image recognitionen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Bilgisayar Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu