Please use this identifier to cite or link to this item: http://repository.elizadeuniversity.edu.ng/jspui/handle/20.500.12398/477
Title: Learning algorithm effect on multilayer feed forward artificial neural network performance in image coding
Authors: Mahmoud, Omer
Anwar, Farhat
Salami, Momoh-Jimoh E.
Keywords: Image Compression /Decompression
Neural Network
Optimisation
Issue Date: Aug-2007
Publisher: Journal of Engineering Science and Technology
Citation: Mahmoud, O., Anwar, F., & Salami, M. J. E. (2007). Learning algorithm effect on multilayer feed forward artificial neural network performance in image coding. Journal of Engineering Science and Technology, 2(2), 188-199.
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.
URI: http://repository.elizadeuniversity.edu.ng/jspui/handle/20.500.12398/477
Appears in Collections:Research Articles

Files in This Item:
File Description SizeFormat 
Learning algorithm effect on multilayer feed forward artificial neural network performance in image coding.pdfArticle full-text732.54 kBAdobe PDFThumbnail
View/Open


Items in EUSpace are protected by copyright, with all rights reserved, unless otherwise indicated.