A novel similarity based unsupervised technique for training convolutional filters

Yükleniyor...
Küçük Resim

Tarih

2023-05-17

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

IEEE

Erişim Hakkı

info:eu-repo/semantics/openAccess

Araştırma projeleri

Organizasyon Birimleri

Dergi sayısı

Özet

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.

Açıklama

This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Grant 118E293.

Anahtar Kelimeler

Backpropagation, Computer architecture, Convolutional neural networks, Feature extraction, Microprocessors, Task analysis, Training, Unsupervised learning, Extraction, Job analysis, Neural networks, Backpropagation training, Initialization methods, Labeled dataset, Training schemes, Unsupervised techniques, Network, Representation, Neocognitron

Kaynak

IEEE Access

WoS Q Değeri

Q2
Q2

Scopus Q Değeri

Q1

Cilt

11

Sayı

Künye

Erkoç, T. & Eskil, M. T. (2023). A novel similarity based unsupervised technique for training convolutional filters. IEEE Access, 11, 49393-49408. doi:10.1109/ACCESS.2023.3277253