A study on object classification using deep convolutional neural networks and comparison with shallow networks


Erdas A., Arslan E., Ozturkcan B., Yildiran U.

6th International Conference on Control Engineering and Information Technology, CEIT 2018, İstanbul, Turkey, 25 - 27 October 2018 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ceit.2018.8751754
  • City: İstanbul
  • Country: Turkey
  • Keywords: CFAR-10, CNN, Deep convolutional neural networks, GPU, Image classification
  • Yıldız Technical University Affiliated: No

Abstract

© 2018 IEEE.The aim of this work is to solve object classification problem using Neural Networks. Two types of neural networks are used and compared, namely, classical Feed Forward Neural Networks and Deep Convolutional Networks. Success of the designed networks is investigated using CIFAR-10 dataset.