Modification of high performance training algorithms for solve singularly perturbed volterra integro-differential and integral equation
Other Title(s)
خوارزميات التدريب ذات الأداء العالي المحسنة لحل معادلة فولتيرا التكاملية التفاضلية و التكاملية المضطربة الشاذة
Author
al-Ibrahimi, Khalid Mandil Muhammad
Source
al-Qadisiyah Journal for Computer Science and Mathematics
Issue
Vol. 11, Issue 1 (31 Mar. 2019), pp.36-44, 9 p.
Publisher
University of al-Qadisiyah College of computer Science and Information Technology
Publication Date
2019-03-31
Country of Publication
Iraq
No. of Pages
9
Main Subjects
Topics
Abstract AR
في هذا البحث, نستخدم الشبكات العصبية لحل معادلة فولتيرا التكاملية التفاضلية ذات الاضطراب المنفردة ومعادلة فولتيرا التكاملية المنفردة ذات الاضطراب .
استخدمنا تحسين خوارزميات التدريب ذات الاداء العالي مثل كوازي نيوتن , ليفنبيرك - ماركواردت وبايسن ركوليشن .
تمت مقارنة الطريقة المقترحة مع خوارزميات التدريب القياسية والحلول التحليلية وجدنا أن الطريقة المقترحة تتميز بالدقة العالية في النتائج , وانخفاض معدل الخطأ وسرعة التقارب كثيرًا مع الطرق القياسية
Abstract EN
In this paper, we apply neural network for solve singularly perturbed Volterra integro-differential equations (SPVIDE) and singularly perturbed Volterra integral equations (SPVIE).
Using Modification Of High Performance Training Algorithms such as quase-Newton, Levenberge-Marqaurdt, and Baysian Regulation.
The proposed method was compared with the standard training algorithms and analytical methods.
We found that the proposed method is characterized by high accuracy in the results, a lower error rate and a speed that is much convergent to standard methods
American Psychological Association (APA)
al-Ibrahimi, Khalid Mandil Muhammad. 2019. Modification of high performance training algorithms for solve singularly perturbed volterra integro-differential and integral equation. al-Qadisiyah Journal for Computer Science and Mathematics،Vol. 11, no. 1, pp.36-44.
https://search.emarefa.net/detail/BIM-837846
Modern Language Association (MLA)
al-Ibrahimi, Khalid Mandil Muhammad. Modification of high performance training algorithms for solve singularly perturbed volterra integro-differential and integral equation. al-Qadisiyah Journal for Computer Science and Mathematics Vol. 11, no. 1 (2019), pp.36-44.
https://search.emarefa.net/detail/BIM-837846
American Medical Association (AMA)
al-Ibrahimi, Khalid Mandil Muhammad. Modification of high performance training algorithms for solve singularly perturbed volterra integro-differential and integral equation. al-Qadisiyah Journal for Computer Science and Mathematics. 2019. Vol. 11, no. 1, pp.36-44.
https://search.emarefa.net/detail/BIM-837846
Data Type
Journal Articles
Language
English
Notes
Includes appendices : p. 39-43
Record ID
BIM-837846