Document Type : Research Paper

Authors

Baghdad University - College of Education Ibn Al-Haitham.

Abstract

The aim of this paper is to design fast feed forward neural network to present a method to solve second order boundary value problem for ordinary differential equations. That is to develop an algorithm which can speedup the solution times, reduce solver failures, and increase possibility of obtaining the globally optimal solution and we use several different training algorithms many of them having a very fast convergence rate for reasonable size networks.Finally, we illustrate the method by solving model problem and present comparison with solutions obtained using other different method .

Keywords

Main Subjects

[1] I. A.Galushkin, " Neural Networks Theory", Berlin Heidelberg , 2007.
[2] R. M. Hristev , " The ANN Book ", Edition 1, 1998.
[3] T.Villmann, U.Seiffert and A.Wismϋller , " Theory and Applications of Neural maps ", ESANN2004 PROCEEDINGS - European Symposium on Ann, pp.25 - 38, April 2004 .
[4] L.N.M.Tawfiq and R.S.Naoum , " On Training of Artificial Neural Networks " , AL-Fath Jornal , No 23, 2005 .
[5] L.N.M.Tawfiq and R.S.Naoum " Density and approximation by  using feed forward Artificial neural networks ", Ibn Al-Haitham Journal for Pure & Applied Sciences, Vol. 20 (1) 2007.
[6] A. K. Jabber ," On Training Feed Forward Neural Networks for Approximation Problem ", MSc Thesis, Baghdad University, College of Education (Ibn Al-Haitham), 2009.
[7] K. I. Ibraheem and B. M. Khalaf , Shooting Neural Networks Algorithm for Solving Boundary Value Problems in ODEs , Applications and Applied Mathematics: An International Journal , Vol. 6, Issue 11 , pp. 1927 – 1941, 2011.