Stability of back propagation training algorithm for neural networks
Other Title(s)
استقرارية خوارزمية التدريب المرتد للشبكات العصبية
Author
Source
Issue
Vol. 9, Issue 4 (31 Dec. 2012), pp.713-719, 7 p.
Publisher
University of Baghdad College of Science for Women
Publication Date
2012-12-31
Country of Publication
Iraq
No. of Pages
7
Main Subjects
Topics
Abstract AR
يتضمن البحث اشتقاق و برهان حدود أو الفترة التي ينتمي إليها ثابت العزم µ و معدل التعلم لقاعدة التدريب المرتد في الشبكات العصبية الصناعية كذلك يتضمن البحث اشتقاق القيد الأعلى لمعدل التعلم نظريا و القيمة التقريبية عمليا.
Abstract EN
In this paper, we derive and prove the stability bounds of the momentum coefficient μ and the learning rate η of the back propagation updating rule in Artificial Neural Networks.
The theoretical upper bound of learning rate η is derived and its practical approximation is obtained.
American Psychological Association (APA)
Tawfiq, Lama Naji Muhammad. 2012. Stability of back propagation training algorithm for neural networks. Baghdad Science Journal،Vol. 9, no. 4, pp.713-719.
https://search.emarefa.net/detail/BIM-316708
Modern Language Association (MLA)
Tawfiq, Lama Naji Muhammad. Stability of back propagation training algorithm for neural networks. Baghdad Science Journal Vol. 9, no. 4 (2012), pp.713-719.
https://search.emarefa.net/detail/BIM-316708
American Medical Association (AMA)
Tawfiq, Lama Naji Muhammad. Stability of back propagation training algorithm for neural networks. Baghdad Science Journal. 2012. Vol. 9, no. 4, pp.713-719.
https://search.emarefa.net/detail/BIM-316708
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 718
Record ID
BIM-316708