Multigradient-based convolutional neural network

Seongyoun Woo, Chulhee Lee

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


The convolutional neural network (CNN) is a promising algorithm for artificial intelligence. Although it was developed for image classification, much research is currently in progress in various fields, such as object detection and image processing. The basic principle of the CNN, especially for classification, is to adopt a loss function and minimize it in an iterative way. In this paper, a multigradient-based training algorithm is proposed for image classification. The proposed algorithm defines an object function based on multigradients and trains the CNN by maximizing the corresponding objective function. When applied to open access databases, the proposed algorithm performed better than conventional back-propagation based CNN methods.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages4
ISBN (Electronic)9781538663769
Publication statusPublished - 2019 Feb
Event2019 IEEE International Conference on Industrial Technology, ICIT 2019 - Melbourne, Australia
Duration: 2019 Feb 132019 Feb 15

Publication series

NameProceedings of the IEEE International Conference on Industrial Technology


Conference2019 IEEE International Conference on Industrial Technology, ICIT 2019

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Multigradient-based convolutional neural network'. Together they form a unique fingerprint.

Cite this