One small step for a man
One Giant leap for the mankind

There is no wealth like Knowledge
                            No Poverty like Ignorance
Journal of Emerging Trends in Computing and Information Sciences Logo

Journal of Emerging Trends in Computing and Information Sciences >> Call for Papers Vol. 8 No. 3, March 2017

Journal of Emerging Trends in Computing and Information Sciences

Study of Weights Stability in Training Process Based on Genetic Algorithms and Neural Networks

Full Text Pdf Pdf
Author Rashad A. Al-Jawfi, Ibrahim Abdulrab Ahmed
ISSN 2079-8407
On Pages 282-285
Volume No. 4
Issue No. 3
Issue Date April 01, 2013
Publishing Date April 01, 2013
Keywords Algorithm, Artificial Neural Networks, Learning Stability


Abstract

This research provides a comparing study of using Genetic Algorithms and Neural Networks (Perceptron) methods to get stability stage of final Weights Matrix, which we got after several iterations of Learning Algorithm depending on concrete conditions according to the chosen Genetic Algorithms and Neural Networks. Because of the importance of GAs we have compared it with another learning method like neural networks, we have observed the weights stability, weights stability with less iterations mean that the applied algorithm is favorite and faster. For comparison, we have chosen binary numbers and algorithms which have smooth conditions in order to get clear and specific stability of weights.
Back

Seperator
    Journal of Computing | Call for Papers (CFP) | Journal Blog | Journal of Systems and Software | ARPN Journal of Science and Technology | International Journal of Health and Medical Sciences | International Journal of Economics, Finance and Management     
Copyrights
© 2015 Journal of Computing