Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding

Mahmoud, Omer and Anwar, Farhat and Salami, Momoh Jimoh Emiyoka (2007) Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding. Journal of Engineering Science and Technology , 2 (2). pp. 188-199. ISSN 1823-4690

Preview

PDF Download (750kB) | Preview

Abstract

One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms.

Item Type:	Article (Journal)
Additional Information:	5968/6463
Uncontrolled Keywords:	Image compression /Decompression, Neural network, Optimisation
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices > TK7885 Computer engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering
Depositing User:	Dr. Omer Mahmoud
Date Deposited:	18 Jul 2013 09:26
Last Modified:	25 Nov 2019 16:07
URI:	http://irep.iium.edu.my/id/eprint/6463

Actions (login required)

View Item