Tuğba Erkoç

Ms. Tuğba Erkoç

Işık University
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2018 in Signal Processing: Image Communication
Verified
Journal Article
Closed access
TETuğba Erkoç
Tuğba Erkoç
DADidem Ağdoğan
Didem Ağdoğan
MEM. Taner Eskil
M. Taner Eskil

17 May 2023 in IEEE Access
Verified
Journal Article
Open access
TETuğba Erkoç
Tuğba Erkoç
MEMustafa Taner Eskıl
Mustafa Taner Eskıl
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 with a proper initialization method and trained with backpropagation over several epochs. This training scheme requires a large labeled dataset, which is costly and time-consuming to obtain. In this study, we propose an unsupervised approach that extracts convolutional filters from a given dataset in a self-organized manner by processing the training set only once without using backpropagation training. The proposed method allows for the extraction of filters from a given dataset in the absence of labels. In contrast to previous studies, we no longer need to select the best number of filters and a suitable filter weight initialization scheme. Applying this method to the MNIST, EMNIST-Digits, Kuzushiji-MNIST, and Fashion-MNIST datasets yields high test performances of 99.19%, 99.39%, 95.03%, and 90.11%, respectively, without applying backpropagation training or using any preprocessed and augmented data.

1 December 2017
Verified
Conference Paper
Closed access
KAK.K. Emre Aki
K.K. Emre Aki
TETuğba Erkoç
Tuğba Erkoç
MEM. Taner Eski
M. Taner Eski
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 we propose a Neocognitron based method for reducing the training set to a fraction, while keeping the dynamics and complexity of the domain. Our approach does not require processing of the entire training set, making it feasible for larger data sets. In our experiments we could successfully reduce the MNIST training data set to less than 2.5% (1,489 images) by processing less than 10% of the 60K images. We showed that the reduced data set can be used for tuning of number of hidden neurons in a multi-layer perceptron.