Implementation of a convolutional neural network using Tensorflow machine learning platform

Authors

  • Yu.Ya. Tomka Yuriy Fedkovich Chernivtsi National University
  • M.V. Talakh Yuriy Fedkovich Chernivtsi National University
  • V.V. Dvorzhak Yuriy Fedkovich Chernivtsi National University
  • O.G. Ushenko Yuriy Fedkovych Chernivtsi National University

DOI:

https://doi.org/10.31649/1681-7893-2022-44-2-55-65

Keywords:

Computer Vision, Convolutional Neural Network, CNN, Deep Learning, Image Classification, Image Understanding

Abstract

The generalized algorithm of a typical convolutional neural network realization by means of TensorFlow machine learning library is considered. The peculiarities of the coding implementation of the convolutional neural network in the image recognition problem are analyzed with the example of the MNIST datаset.

Author Biographies

Yu.Ya. Tomka, Yuriy Fedkovich Chernivtsi National University

Ph.D., assistant professor of Computer Science Department, Yuriy Fedkovich Chernivtsi National University

M.V. Talakh, Yuriy Fedkovich Chernivtsi National University

Ph.D., assistant professor of Computer Science Department, Yuriy Fedkovich Chernivtsi National University

V.V. Dvorzhak, Yuriy Fedkovich Chernivtsi National University

Ph.D., assistant professor of Computer Science Department, Yuriy Fedkovich Chernivtsi National University

O.G. Ushenko , Yuriy Fedkovych Chernivtsi National University

D.Sc., Professor, Head of Optics and Publishing Department, Yuriy Fedkovych Chernivtsi National University

References

Y. Lecun. Gradient-based Learning Applied to Document Recognition [Electronic resource] / Y.Lecun, L. Bottou, Y. Bengio, P. Haffner. – 1998. – Access Mode: http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf.

A Krizhevsky. ImageNet Classification with Deep Convolutional Neural Networks [Electronic resource] / A. Krizhevsky, S. Sutskever, G. Hinton – Access Mode: http://papers.nips.cc/paper/4824-imagenet-classifica-tion-with-deep-convolutional-neural-networks.pdf.

M. Zeiler. Visualizing and Understanding Convolutional Networks [Electronic resource] / M. Zeiler, R. Fergus. – 2013. – Access Mode: https://arxiv.org/pdf/1311.2901v3.pdf.

C. Szegedy. Going Deeper with Convolutions [Electronic resource] / C. Szegedy, W. Liu, Y. Jia та ін. – 2014. – Access Mode: https://arxiv.org/pdf/1409.4842.pdf.

K. Simonyan. Very deep convolutional networks for large-scale image recognition [Electronic resource] / K. Simonyan, A. Zisserman. – 2015. – Access Mode: https://arxiv.org/pdf/1409.1556.pdf.

K. He. Deep Residual Learning for Image Recognition [Electronic resource] / K. He, X. Zhang, S. Ren, J. Sun. – 2015. – Access Mode: https://arxiv.org/pdf/1512.03385.pdf.

Ioffe S. Batch Normalization: Accelerating Deep Network Training b y Reducing Internal Covariate Shift [Electronic resource] / S. Ioffe, C. Szegedy. – 2015. – Access Mode: https://arxiv.org/pdf/1502.03167.pdf.

An open-source software library for Machine Intelligence [Electronic resource]. – 2018. – Access Mode: https://www.tensorflow.org/

LeCun Y. The MNIST - Database of handwritten digits [Electronic resource] / Y. LeCun, C. Cortes, C. Burges – Access Mode: http://yann.lecun.com/exdb/mnist/.

Python TensorFlow Tutorial – Build a Neural Network [Electronic resource]. – 2017. – Access Mode: http://adventuresinmachinelearning.com/python-tensorflow-tutorial/.

Stochastic Gradient Descent – Mini-batch and more [Electronic resource]. – 2017. – Access Mode: http://adventuresinmachinelearning.com/stochastic-gradient-descent/.

Improve your neural networks – Part 1 [TIPS AND TRICKS] [Electronic resource]. – 2017. – Access Mode: http://adventuresinmachinelearning.com/improve-neural-networks-part-1/.

The CIFAR-10 dataset / The CIFAR-100 dataset [Electronic resource] – Access Mode: https://www.cs.toronto.edu/~kriz/cifar.html.

Neural Networks Tutorial – A Pathway to Deep Learning [Electronic resource]. – 2017. – Access Mode: http://adventuresinmachinelearning.com/neural-networks-tutorial/.

Stochastic Gradient Descent – Mini-batch and more [Electronic resource]. – 2017. – Access Mode: http://adventuresinmachinelearning.com/stochastic-gradient-descent/.

TensorFlow. API Documentation. v.1.5. [Electronic resource]. – 2017. – Access Mode: https://www.tensorflow.org/api_guides/python/train.

Olexander N. Romanyuk, and etc. "A function-based approach to real-time visualization using graphics processing units", Proc. SPIE 11581, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2020, 115810E (14 October 2020).

L.I. Timchenko, N.I. Kokriatskaia, S.V. Pavlov, and etc. "Q-processors for real-time image processing", Proc. SPIE 11581, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2020, 115810F (14 October 2020).

Intellectual Technologies in Medical Diagnosis, Treatment and Rehabilitation: monograph / [S. In Pavlov, O.G. Avrunin, S.M. Zlepko, E.V. Bodyanskyi, etc.]; edited by S. Pavlov, O. Avrunin. - Vinnytsia: PP "TD "Edelveiss and K", 2019. -260 p. ISBN 978-617-7237-59-3

Intelligent Technologies of Computer Planning and Modeling in Medical Diagnosis, Treatment and Rehabilitation: monograph // edited by S.V. Pavlov, O.G. Avrunin, O.V. Hrushko - Zhytomyr: "Euro-Volyn" PE, 2021. - 202 p. ISBN 978-617-7992-15-7.

Downloads

Abstract views: 158

Published

2023-01-20

How to Cite

[1]
Y. . Tomka, M. . Talakh, V. . Dvorzhak, and O. . Ushenko, “Implementation of a convolutional neural network using Tensorflow machine learning platform”, Опт-ел. інф-енерг. техн., vol. 44, no. 2, pp. 55–65, Jan. 2023.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.

Most read articles by the same author(s)

1 2 > >>