Işık Yazarı "Erkoç, Tuğba" 1- Fakülteler | Faculties İçin Listeleme
-
El yazısı rakam sınıflandırması için gözetimsiz benzerlik tabanlı evrişimler
Erkoç, Tuğba; Eskil, Mustafa Taner (Institute of Electrical and Electronics Engineers Inc., 2022)Effective training of filters in Convolutional Neural Networks (CNN) ensures their success. In order to achieve good classification results in CNNs, filters must be carefully initialized, trained and fine-tuned. We propose ... -
A novel similarity based unsupervised technique for training convolutional filters
Erkoç, Tuğba; Eskil, Mustata Taner (IEEE, 2023-05-17)Achieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized ... -
An observation based muscle model for simulation of facial expressions
Erkoç, Tuğba; Ağdoğan, Didem; Eskil, Mustafa Taner (Elsevier Science BV, 2018-05)This study presents a novel facial muscle model for coding of facial expressions. We derive this model from unintrusive observation of human subjects in the progress of the surprise expression. We use a generic and ... -
Subset selection for tuning of hyper-parameters in artificial neural networks
Aki, K.K.Emre; Erkoç, Tuğba; Eskil, Mustafa Taner (IEEE, 2017)Hyper-parameters of a machine learning architecture define its design. Tuning of hyper-parameters is costly and for large data sets outright impractical, whether it is performed manually or algorithmically. In this study ...