Advanced neural-network training algorithm with optimized error based on modified gram schmidt with reorthogonalization
Joint Authors
Ismail, Isra Abd al-Sattar
Faraj, M. S.
Source
International Journal of Intelligent Computing and Information Sciences
Issue
Vol. 6, Issue 1 (31 Jan. 2006)6 p.
Publisher
Ain Shams University Faculty of Computer and Information Sciences
Publication Date
2006-01-31
Country of Publication
Egypt
No. of Pages
6
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
In this paper we purpose an advanced supervised training method for neural networks.
It is based on Modified Gram-Schmidt with reorthogonalization (MGSR) process.
And it is formulated, in some sense, in the spirit of the Feed-Forward Neural Network (FFNN) algorithm.
It outperforms (in terms of training accuracy, convergence properties, overall training time, etc.) the basic back propagation and its variations with variable learning rate significantly.
The new method developed in this paper is aiming at improving convergence properties, in supervised training of neural networks.
Simulation results are provided to demonstrate the superior performance of the purposed algorithm over the FFNN algorithm.
American Psychological Association (APA)
Ismail, Isra Abd al-Sattar& Faraj, M. S.. 2006. Advanced neural-network training algorithm with optimized error based on modified gram schmidt with reorthogonalization. International Journal of Intelligent Computing and Information Sciences،Vol. 6, no. 1.
https://search.emarefa.net/detail/BIM-284348
Modern Language Association (MLA)
Ismail, Isra Abd al-Sattar& Faraj, M. S.. Advanced neural-network training algorithm with optimized error based on modified gram schmidt with reorthogonalization. International Journal of Intelligent Computing and Information Sciences Vol. 6, no. 1 (Jan. 2006).
https://search.emarefa.net/detail/BIM-284348
American Medical Association (AMA)
Ismail, Isra Abd al-Sattar& Faraj, M. S.. Advanced neural-network training algorithm with optimized error based on modified gram schmidt with reorthogonalization. International Journal of Intelligent Computing and Information Sciences. 2006. Vol. 6, no. 1.
https://search.emarefa.net/detail/BIM-284348
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references.
Record ID
BIM-284348