Investigating Existing Techniques for Designing Convolutional Neural Network Filters

Arunadevi Karuppasamy, Abdelhamid Abdessalem, Rachid Hedjam, Hamza M. Zidoum

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

Abstract

In the last decades, Deep Learning (DL) has played an essential role in extracting automatically high-level features and performing complex computer vision tasks. A Convolutional Neural Network (CNN) is one of the deep learning methods that is currently attaining state-of-the-art accuracy in image classification and object recognition. CNN has three types of layers: convolutional layer, pooling layer and fully connected layer. The first two types of layers extract different levels of useful features, while the latter type is dedicated to perform classification. Traditional CNNs like AlexNet, VGGNet, GoogLeNet, ResNet use back-propagation approach in their training. Such approach requires huge amount of datasets which leads to high computational cost and suffers from vanishing gradient problem that deteriorates the quality of learning. Recently, a forward propagation approach was proposed to tackle these problems. In this paper, we summarize the results of a comparative study which we conducted on the two learning approaches.

Original languageEnglish
Title of host publication2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538659069
DOIs
Publication statusPublished - Jul 2019
Externally publishedYes
Event10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019 - Kanpur, India
Duration: Jul 6 2019Jul 8 2019

Publication series

Name2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019

Conference

Conference10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019
Country/TerritoryIndia
CityKanpur
Period7/6/197/8/19

Keywords

  • CNN
  • convolutional layer
  • CSVM
  • feature-maps
  • filters
  • PCANet
  • PCANet+
  • ScatNet

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering

Cite this