A Numerical Method for Solving Fractional Differential Equations by Using Neural Network

We present a new method for solving the fractional differential equations of initial value problems by using neural networks which are constructed from cosine basis functions with adjustable parameters. By training the neural networks repeatedly the numerical solutions for the fractional differentia...

Full description

Saved in:
Bibliographic Details
Main Authors: Haidong Qu, Xuan Liu
Format: Article
Language:English
Published: Wiley 2015-01-01
Series:Advances in Mathematical Physics
Online Access:http://dx.doi.org/10.1155/2015/439526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850178996426244096
author Haidong Qu
Xuan Liu
author_facet Haidong Qu
Xuan Liu
author_sort Haidong Qu
collection DOAJ
description We present a new method for solving the fractional differential equations of initial value problems by using neural networks which are constructed from cosine basis functions with adjustable parameters. By training the neural networks repeatedly the numerical solutions for the fractional differential equations were obtained. Moreover, the technique is still applicable for the coupled differential equations of fractional order. The computer graphics and numerical solutions show that the proposed method is very effective.
format Article
id doaj-art-bdd167c16687455ebeb3e01bbbcfaa8e
institution OA Journals
issn 1687-9120
1687-9139
language English
publishDate 2015-01-01
publisher Wiley
record_format Article
series Advances in Mathematical Physics
spelling doaj-art-bdd167c16687455ebeb3e01bbbcfaa8e2025-08-20T02:18:36ZengWileyAdvances in Mathematical Physics1687-91201687-91392015-01-01201510.1155/2015/439526439526A Numerical Method for Solving Fractional Differential Equations by Using Neural NetworkHaidong Qu0Xuan Liu1Department of Mathematics, Hanshan Normal University, Chaozhou 521041, ChinaDepartment of Basic Education, Hanshan Normal University, Chaozhou 521041, ChinaWe present a new method for solving the fractional differential equations of initial value problems by using neural networks which are constructed from cosine basis functions with adjustable parameters. By training the neural networks repeatedly the numerical solutions for the fractional differential equations were obtained. Moreover, the technique is still applicable for the coupled differential equations of fractional order. The computer graphics and numerical solutions show that the proposed method is very effective.http://dx.doi.org/10.1155/2015/439526
spellingShingle Haidong Qu
Xuan Liu
A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
Advances in Mathematical Physics
title A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
title_full A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
title_fullStr A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
title_full_unstemmed A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
title_short A Numerical Method for Solving Fractional Differential Equations by Using Neural Network
title_sort numerical method for solving fractional differential equations by using neural network
url http://dx.doi.org/10.1155/2015/439526
work_keys_str_mv AT haidongqu anumericalmethodforsolvingfractionaldifferentialequationsbyusingneuralnetwork
AT xuanliu anumericalmethodforsolvingfractionaldifferentialequationsbyusingneuralnetwork
AT haidongqu numericalmethodforsolvingfractionaldifferentialequationsbyusingneuralnetwork
AT xuanliu numericalmethodforsolvingfractionaldifferentialequationsbyusingneuralnetwork