A novel enhanced softmax loss function for brain tumour detection using deep learning.

Journal: Journal of neuroscience methods
Published Date: Nov 14, 2019

Abstract

BACKGROUND AND AIM: In deep learning, the sigmoid function is unsuccessfully used for the multiclass classification of the brain tumour due to its limit of binary classification. This study aims to increase the classification accuracy by reducing the risk of overfitting problem and supports multi-class classification. The proposed system consists of a convolutional neural network with modified softmax loss function and regularization.

Authors

  • Sunil Maharjan
    Charles Sturt University, Sydney, Australia.
  • Abeer Alsadoon
    School of Computing and Mathematics, Charles Sturt University, Sydney Campus, Sydney, Australia. aalsadoon@studygroup.com.
  • P W C Prasad
    School of Computing and Mathematics, Charles Sturt University, Sydney Campus, Sydney, Australia.
  • Thair Al-Dalain
    Charles Sturt University, Sydney, Australia.
  • Omar Hisham Alsadoon
    Department of Islamic Sciences, Al Iraqia University, Baghdad, Iraq.

Keywords

External Resources

Popular Topics
Recent Journals