NISCAIR Online Periodicals Repository

Research Journals >
Indian Journal of Engineering and Materials Sciences (IJEMS) >
IJEMS Vol.12 [2005] >
IJEMS Vol.12(5) [October 2005] >

Title: Comparison of three back-propagation training algorithms for two case studies
Authors: Kişi, Özgür
Uncuoğlu, Erdal
Issue Date: Oct-2005
Publisher: CSIR
IPC CodeG06N3/02
Abstract: This paper investigates the use of three back-propagation training algorithms, Levenberg-Marquardt, conjugate gradient and resilient back-propagation, for the two case studies, stream-flow forecasting and determination of lateral stress in cohesionless soils. Several neural network (NN) algorithms have been reported in the literature. They include various representations and architectures and therefore are suitable for different applications. In the present study, three NN algorithms are compared according to their convergence velocities in training and performances in testing. Based on the study and test results, although the Levenberg-Marquardt algorithm has been found being faster and having better performance than the other algorithms in training, the resilient back-propagation algorithm has the best accuracy in testing period.
Page(s): 434-442
ISSN: 0975-1017 (Online); 0971-4588 (Print)
Source:IJEMS Vol.12(5) [October 2005]

Files in This Item:

File Description SizeFormat
IJEMS 12(5) 434-442.pdf284.36 kBAdobe PDFView/Open
 Current Page Visits: 118 
Recommend this item


Online Submission of Articles |  NISCAIR Website |  National Knowledge Resources Consortium |  Contact us |  Feedback

Disclaimer: NISCAIR assumes no responsibility for the statements and opinions advanced by contributors. The editorial staff in its work of examining papers received for publication is helped, in an honorary capacity, by many distinguished engineers and scientists.

CC License Except where otherwise noted, the Articles on this site are licensed under Creative Commons License: CC Attribution-Noncommercial-No Derivative Works 2.5 India

Copyright © 2015 The Council of Scientific and Industrial Research, New Delhi. All rights reserved.

Powered by DSpace Copyright © 2002-2007 MIT and Hewlett-Packard | Compliant to OAI-PMH V 2.0

Home Page Total Visits: 163740 since 01-Sep-2015  Last updated on 21-Jun-2016Webmaster: