The deep multichannel discrete-time cellular neural network model for classification

Emrah Abtioglu*, Mustak Erhan Yalcin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

High latency and power consumption are two major problems that need to be addressed in convolutional neural networks (CNN). In this paper, the convolutional layer is replaced with a discrete-time cellular neural network (CellNN) to overcome these problems. Multiple configurations of CellNNs are trained in a framework called TensorFlow to classify objects from the CIFAR-10 database. Effects of the number of iterations, the number of channels, batch normalization, and activation functions on the classification accuracies are presented. It is shown that TensorFlow is a tool that is capable of training discrete-time CellNNs. Although the accuracies of the proposed networks on CIFAR-10 are slightly lesser than the existing CNNs, with reduced parameters and multiply-accumulates (MACs), power consumption and computation time of our networks will be less than CNNs.

Original languageEnglish
Pages (from-to)4171-4178
Number of pages8
JournalInternational Journal of Circuit Theory and Applications
Volume50
Issue number11
DOIs
Publication statusPublished - Nov 2022

Bibliographical note

Publisher Copyright:
© 2022 John Wiley & Sons Ltd.

Funding

This work was supported by the Istanbul Technical University under grant ITU BAP, Project ID:40679.

FundersFunder number
Istanbul Teknik Üniversitesi
Bilimsel Araştırma Projeleri Birimi, İstanbul Teknik Üniversitesi

    Keywords

    • cellular neural network
    • convolutional neural network
    • deep learning
    • image processing

    Fingerprint

    Dive into the research topics of 'The deep multichannel discrete-time cellular neural network model for classification'. Together they form a unique fingerprint.

    Cite this