Fast training algorithms for feed forward neural networks
Other Title(s)
تسريع خوارزميات التدريب للشبكات العصبية ذي التغذية التقدمية
Joint Authors
Tawfiq, Lama Naji Muhammad
Uraybi, Yasin Adil
Source
Ibn al-Haitham Journal for Pure and Applied Science
Issue
Vol. 26, Issue 1 (30 Apr. 2013), pp.275-280, 6 p.
Publisher
University of Baghdad College of Education for Pure Science / Ibn al-Haitham
Publication Date
2013-04-30
Country of Publication
Iraq
No. of Pages
6
Main Subjects
Information Technology and Computer Science
Topics
Abstract AR
الهدف من هذا البحث هو مناقشة بعض خوارزميات التدريب ذي الأداء العالي التي تصنف إلى صنفين رئيسين, الصنف الأول يستخدم التقنية الإرشادية التي طورت من خلال تحليل أداء خوارزمية انحدار الميل القياسي, الصنف الآخر لتسريع الخوارزميات يكون باستخدام تقنيات الأمثلية العددية القياسية مثل شبيه نيوتن.
و الهدف الآخر من البحث هو حل العوائق المتعلقة بخوارزميات التدريب السابقة و اقتراح خوارزميات تدريب كفوءة للشبكات العصبية ذي التغذية التقدمية.
Abstract EN
The aim of this paper, is to discuss several high performance training algorithms fall into two main categories.
The first category uses heuristic techniques, which were developed from an analysis of the performance of the standard gradient descent algorithm.
The second category of fast algorithms uses standard numerical optimization techniques such as : quasi-Newton.
Other aim is to solve the drawbacks related with these training algorithms and propose an efficient training algorithm for FFNN.
American Psychological Association (APA)
Tawfiq, Lama Naji Muhammad& Uraybi, Yasin Adil. 2013. Fast training algorithms for feed forward neural networks. Ibn al-Haitham Journal for Pure and Applied Science،Vol. 26, no. 1, pp.275-280.
https://search.emarefa.net/detail/BIM-337135
Modern Language Association (MLA)
Tawfiq, Lama Naji Muhammad& Uraybi, Yasin Adil. Fast training algorithms for feed forward neural networks. Ibn al-Haitham Journal for Pure and Applied Science Vol. 26, no. 1 (Apr. 2013), pp.275-280.
https://search.emarefa.net/detail/BIM-337135
American Medical Association (AMA)
Tawfiq, Lama Naji Muhammad& Uraybi, Yasin Adil. Fast training algorithms for feed forward neural networks. Ibn al-Haitham Journal for Pure and Applied Science. 2013. Vol. 26, no. 1, pp.275-280.
https://search.emarefa.net/detail/BIM-337135
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 279
Record ID
BIM-337135
