Affordable Access

Access to the full text

Designing Convolutional Neural Network Architecture Using Genetic Algorithms

Authors
  • Bhandare, Ashray1
  • Kaur, Devinder1
  • 1 Department of EECS, the University of Toledo, Toledo, Ohio
Type
Published Article
Journal
International Journal of Advanced Network, Monitoring and Controls
Publisher
Exeley Inc.
Publication Date
Sep 01, 2021
Volume
6
Issue
3
Pages
26–35
Identifiers
DOI: 10.21307/ijanmc-2021-024
Source
Exeley
Keywords
Disciplines
  • Computer Science, Software Engineering
License
Green

Abstract

In this paper, genetic algorithm (GA) is used to optimally determine the architecture of a convolutional neural network (CNN) that is used to classify handwritten numbers. The CNN is a class of deep feed-forward network, which have seen major success in the field of visual image analysis. During training, a good CNN architecture is capable of extracting complex features from the given training data; however, at present, there is no standard way to determine the architecture of a CNN. Domain knowledge and human expertise are required in order to design a CNN architecture. Typically architectures, The GA determine the exact architecture of a CNN by evolving the various hyper parameters of the architecture for a given application. The proposed method was tested on the MNIST dataset. The results show that the genetic algorithm is capable of generating successful CNN architectures. The proposed method performs the entire process of architecture generation without any human intervention.

Report this publication

Statistics

Seen <100 times