On training neural network to solve some class of boundary value problems
Other Title(s)
حول تدريب الشبكات العصبية لحل صنف من مسائل القيم الحدودية
Author
Source
al-Qadisiyah Journal for Computer Science and Mathematics
Issue
Vol. 8, Issue 1 (30 Jun. 2016)12 p.
Publisher
University of al-Qadisiyah College of computer Science and Information Technology
Publication Date
2016-06-30
Country of Publication
Iraq
No. of Pages
12
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
The aim of this paper is to train feed forward neural network for solving some class of boundary value problems for ordinary differential equations.
Using backpropagation training algorithm, where the Levenberg – Marquardt training algorithm is used to train the network .The existence of the proposed solution was proved.
The suggested networks have been studied intensively for a few decades and have provided an option for modeling complex systems.
Therefore this option was utilized to reduce the computation of solution, and finally the method is demonstrated through illustrative examples.
American Psychological Association (APA)
Jabir, Ala Kamil. 2016. On training neural network to solve some class of boundary value problems. al-Qadisiyah Journal for Computer Science and Mathematics،Vol. 8, no. 1.
https://search.emarefa.net/detail/BIM-787413
Modern Language Association (MLA)
Jabir, Ala Kamil. On training neural network to solve some class of boundary value problems. al-Qadisiyah Journal for Computer Science and Mathematics Vol. 8, no. 1 (2016).
https://search.emarefa.net/detail/BIM-787413
American Medical Association (AMA)
Jabir, Ala Kamil. On training neural network to solve some class of boundary value problems. al-Qadisiyah Journal for Computer Science and Mathematics. 2016. Vol. 8, no. 1.
https://search.emarefa.net/detail/BIM-787413
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-787413