Cifar-10 Image Classification with Convolutional Neural Networks for Embedded Systems

Calik R. C., Demirci M. F.

15th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2018, Aqaba, Jordan, 28 October - 01 November 2018, vol.2018-November, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2018-November
  • Doi Number: 10.1109/aiccsa.2018.8612873
  • City: Aqaba
  • Country: Jordan
  • Keywords: Convolutional Neural Network, Deep Neural Network, Image Classification, Machine Learning
  • Ankara Yıldırım Beyazıt University Affiliated: No

Abstract

© 2018 IEEE.Convolutional Neural Networks (CNN) have been successfully applied to image classification problems. Although powerful, they require a large amount of memory. The purpose of this paper is to perform image classification using CNNs on the embedded systems, where only a limited amount of memory is available. Our experimental analysis shows that 85.9% image classification accuracy is obtained by our framework while requiring 2GB memory only, making our framework ideal to be used in embedded systems.