عنوان المقالة:تصميم شبكة عصبية ذات تغذية تقدمية لحل مشاكل القيمة الذاتية مع شروط حدودية ديرشليت Design Feed Forward Neural Network to Solve Eigenvalue Problems with Dirishlit Boundary Conditions
Luma Naji Mohammed Tawfiq1 and Othman Mahdi Salih2
الملخص الانجليزي
The aim of this paper is to design feed forward neural network for solving nonlinear second order, eigenvalue problem for ordinary differential equations. The network technique finds eigenvalue and the corresponding nonzero eigenvector which represent the solution of equation in a certain domain. The neural networks use the principle of back propagation with different training algorithms such as quasi-Newton, Levenberg-Marquardt, and Bayesian Regulation. Illustration example is presented to show speed, accuracy and effectiveness of using the networks techniques for solving this type of equations, and a comparison between the suggested networks technique and other methods.
تاريخ النشر
08/08/2014
الناشر
International Journal of Modern Mathematical Sciences,
رقم المجلد
11
رقم العدد
2
ISSN/ISBN
2166-286X
الصفحات
58-68
الكلمات المفتاحية
Ordinary differential equation, Eigenvalue, Eigenvector, Eigenvalue problems, Feed forward neural network, Back propagation, Training algorithm.
عثمان مهدي صالح | Othman Mahdi Salih | 1724