Mosul University
  • Register
  • Login
  • العربیة

AL-Rafidain Journal of Computer Sciences and Mathematics

Notice

As part of Open Journals’ initiatives, we create website for scholarly open access journals. If you are responsible for this journal and would like to know more about how to use the editorial system, please visit our website at https://ejournalplus.com or
send us an email to info@ejournalplus.com

We will contact you soon

  1. Home
  2. Volume 11, Issue 1
  3. Authors

Current Issue

By Issue

By Subject

Keyword Index

Author Index

Indexing Databases XML

About Journal

Aims and Scope

Editorial Board

Editorial Staff

Publication Ethics

Indexing and Abstracting

Related Links

Peer Review Process

News

Conjugate Gradient Algorithm Based on Aitken's Process for Training Neural Networks

    Khalil K. Abbo Hind H. Mohammed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2014, Volume 11, Issue 1, Pages 39-51
10.33899/csmj.2014.163730

  • Show Article
  • Download
  • Cite
  • Statistics
  • Share

Abstract

Conjugate gradient methods constitute excellent neural network training methods, because of their simplicity, numerical efficiency and their very low memory requirements. It is well-known that the procedure of training a neural network is highly consistent with unconstrained optimization theory and many attempts have been made to speed up this process. In particular, various algorithms motivated from numerical optimization theory have been applied for accelerating neural network training. In this paper, we propose a conjugate gradient neural network training algorithm by using  Aitken's process which guarantees sufficient descent with Wolfe line search. Moreover, we establish that our proposed method is globally convergent for general functions under the strong Wolfe conditions. In the experimental results, we compared the behavior of our proposed method(NACG) with well- known methods in this field.
 
Keywords:
    Artificial neural front networks Education algorithms Aitken method Conjugate gradient algorithms
  • PDF (429 K)
  • XML
(2014). Conjugate Gradient Algorithm Based on Aitken's Process for Training Neural Networks. AL-Rafidain Journal of Computer Sciences and Mathematics, 11(1), 39-51. doi: 10.33899/csmj.2014.163730
Khalil K. Abbo; Hind H. Mohammed. "Conjugate Gradient Algorithm Based on Aitken's Process for Training Neural Networks". AL-Rafidain Journal of Computer Sciences and Mathematics, 11, 1, 2014, 39-51. doi: 10.33899/csmj.2014.163730
(2014). 'Conjugate Gradient Algorithm Based on Aitken's Process for Training Neural Networks', AL-Rafidain Journal of Computer Sciences and Mathematics, 11(1), pp. 39-51. doi: 10.33899/csmj.2014.163730
Conjugate Gradient Algorithm Based on Aitken's Process for Training Neural Networks. AL-Rafidain Journal of Computer Sciences and Mathematics, 2014; 11(1): 39-51. doi: 10.33899/csmj.2014.163730
  • RIS
  • EndNote
  • BibTeX
  • APA
  • MLA
  • Harvard
  • Vancouver
  • Article View: 53
  • PDF Download: 42
  • LinkedIn
  • Twitter
  • Facebook
  • Google
  • Telegram
  • Home
  • Glossary
  • News
  • Aims and Scope
  • Privacy Policy
  • Sitemap
This journal is licensed under a Creative Commons Attribution 4.0 International (CC-BY 4.0)

Powered by eJournalPlus