Open AccessDesign Feed Forward Neural Network to Solve Singular Boundary Value Problems
Author(s) -
L. N. M. Tawfiq,
Ashraf A. T. Hussein
Publication year - 2013
Publication title -
isrn applied mathematics
Language(s) - English
Resource type - Journals
eISSN - 2090-5572
pISSN - 2090-5564
DOI - 10.1155/2013/650467
Subject(s) - artificial neural network , interpolation (computer graphics) , convergence (economics) , ordinary differential equation , backpropagation , boundary value problem , feedforward neural network , computer science , mathematical optimization , mathematics , differential equation , algorithm , artificial intelligence , mathematical analysis , motion (physics) , economics , economic growth
The aim of this paper is to design feed forward neural network for solving second-order singular boundary value problems in ordinary differential equations. The neural networks use the principle of back propagation with different training algorithms such as quasi-Newton, Levenberg-Marquardt, and Bayesian Regulation. Two examples are considered to show that effectiveness of using the network techniques for solving this type of equations. The convergence properties of the technique and accuracy of the interpolation technique are considered.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom