Stability of Back Propagation Training Algorithm for Neural Networks
Baghdad Science Journal
View Archive Info| Field | Value | |
| Title |
Stability of Back Propagation Training Algorithm for Neural Networks
|
|
| Creator |
Journal, Baghdad Science
|
|
| Description |
In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained
|
|
| Publisher |
College of Science for Women - University of Baghdad
|
|
| Date |
2012-12-02
|
|
| Type |
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion Peer-reviewed Article |
|
| Format |
application/pdf
|
|
| Identifier |
http://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/1417
|
|
| Source |
مجلة بغداد للعلوم; مجلد 9 عدد 4 (2012): issue 4; 713-719
Baghdad Science Journal; Vol 9 No 4 (2012): issue 4; 713-719 2411-7986 2078-8665 |
|
| Language |
eng
|
|
| Relation |
http://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/1417/1348
|
|
| Rights |
Copyright (c) 2012 Baghdad Science Journal
|
|