Application of a Scaled MNIST Dataset Blended with Natural Scene Background on ResNet

Alexander Marinov, Nhamo Mtetwa, Hadi Larijani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

354 Downloads (Pure)

Abstract

Deep learning (DL) has gained a lot of popularity in the science and business community. It has been successful in a range of applications, especially in computer vision. This paper presents results from applying scaled MNIST images dataset to a popular implementation of deep learning called ResNet. This is a valuable contribution because in general convolutional networks are not scale invariant. Our objective is to explore the behavior of a residual neural network when trained and evaluated using three different datasets of scaled MNIST images.
Original languageEnglish
Title of host publicationICBDE'19: Proceedings of the 2019 International Conference on Big Data and Education
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages77-81
Number of pages5
ISBN (Electronic)9781450361866
ISBN (Print)9781450361866
DOIs
Publication statusPublished - 30 Mar 2019
Event2019 International Conference on Big Data and Education - University of Greenwich, London, United Kingdom
Duration: 30 Mar 20191 Apr 2019
https://www.icbde.org/2019.html (Link to conference website)

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2019 International Conference on Big Data and Education
Abbreviated titleICBDE 2019
Country/TerritoryUnited Kingdom
CityLondon
Period30/03/191/04/19
Internet address

Keywords

  • feature cnn
  • machine learning
  • scaling
  • mnist
  • resnet
  • deep learning
  • Deep learning
  • Feature cnn
  • Machine learning
  • Mnist
  • Scaling
  • Resnet

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Application of a Scaled MNIST Dataset Blended with Natural Scene Background on ResNet'. Together they form a unique fingerprint.

Cite this