Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network

       In this paper, we focus on designing feed forward neural network (FFNN) for solving Mixed Volterra – Fredholm Integral Equations (MVFIEs) of second kind in 2–dimensions. in our method, we present a multi – layers model consisting of a hidden layer which has five hidden units (neurons) and on...

Full description

Bibliographic Details
Main Author: Al-Saif et al.
Format: Article
Language:Arabic
Published: College of Science for Women, University of Baghdad 2019-03-01
Series:Baghdad Science Journal
Subjects:
Online Access:http://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/3187
id doaj-705fc073b4654d3b9cc6f2c025f1dc30
record_format Article
spelling doaj-705fc073b4654d3b9cc6f2c025f1dc302020-11-25T00:36:58ZaraCollege of Science for Women, University of BaghdadBaghdad Science Journal2078-86652411-79862019-03-0116110.21123/bsj.16.1.01163187Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural NetworkAl-Saif et al.        In this paper, we focus on designing feed forward neural network (FFNN) for solving Mixed Volterra – Fredholm Integral Equations (MVFIEs) of second kind in 2–dimensions. in our method, we present a multi – layers model consisting of a hidden layer which has five hidden units (neurons) and one linear output unit. Transfer function (Log – sigmoid) and training algorithm (Levenberg – Marquardt) are used as a sigmoid activation of each unit. A comparison between the results of numerical experiment and the analytic solution of some examples has been carried out in order to justify the efficiency and the accuracy of our method.                                   http://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/3187Feed Forward neural network, Levenberg – Marquardt (trainlm) training algorithm, Mixed Volterra - Fredholm integral equations
collection DOAJ
language Arabic
format Article
sources DOAJ
author Al-Saif et al.
spellingShingle Al-Saif et al.
Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
Baghdad Science Journal
Feed Forward neural network, Levenberg – Marquardt (trainlm) training algorithm, Mixed Volterra - Fredholm integral equations
author_facet Al-Saif et al.
author_sort Al-Saif et al.
title Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
title_short Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
title_full Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
title_fullStr Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
title_full_unstemmed Solving Mixed Volterra - Fredholm Integral Equation (MVFIE) by Designing Neural Network
title_sort solving mixed volterra - fredholm integral equation (mvfie) by designing neural network
publisher College of Science for Women, University of Baghdad
series Baghdad Science Journal
issn 2078-8665
2411-7986
publishDate 2019-03-01
description        In this paper, we focus on designing feed forward neural network (FFNN) for solving Mixed Volterra – Fredholm Integral Equations (MVFIEs) of second kind in 2–dimensions. in our method, we present a multi – layers model consisting of a hidden layer which has five hidden units (neurons) and one linear output unit. Transfer function (Log – sigmoid) and training algorithm (Levenberg – Marquardt) are used as a sigmoid activation of each unit. A comparison between the results of numerical experiment and the analytic solution of some examples has been carried out in order to justify the efficiency and the accuracy of our method.                                  
topic Feed Forward neural network, Levenberg – Marquardt (trainlm) training algorithm, Mixed Volterra - Fredholm integral equations
url http://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/3187
work_keys_str_mv AT alsaifetal solvingmixedvolterrafredholmintegralequationmvfiebydesigningneuralnetwork
_version_ 1725303360381255680