Approximate solutions by artificial neural network of hybrid fuzzy differential equations

Approximate solutions by artificial neural network of hybrid fuzzy differential equations

In this article, we propose a new approach to solve the hybrid fuzzy differential equations based on the feed-forward neural networks. We first replace it by a system of ordinary differential equations. A trial solution of this system involves two parts. The first part satisfies the initial conditio...

Full description

Bibliographic Details
Main Authors: Mahmoud Paripour, Massimiliano Ferrara, Mehdi Salimi
Format: Article
Language:English
Published: SAGE Publishing 2017-09-01
Series:Advances in Mechanical Engineering
Online Access:https://doi.org/10.1177/1687814017717429
id doaj-a4ba112a0a42498ea47fe13d9601943c
record_format Article
spelling doaj-a4ba112a0a42498ea47fe13d9601943c2020-11-25T02:23:02ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402017-09-01910.1177/1687814017717429Approximate solutions by artificial neural network of hybrid fuzzy differential equationsMahmoud Paripour0Massimiliano Ferrara1Mehdi Salimi2Department of Computer Engineering and Information Technology, Hamedan University of Technology, Hamedan, IranDepartment of Law and Economics, Mediterranea University of Reggio Calabria, Reggio Calabria, ItalyDepartment of Mathematics, Tuyserkan Branch, Islamic Azad University, Tuyserkan, IranIn this article, we propose a new approach to solve the hybrid fuzzy differential equations based on the feed-forward neural networks. We first replace it by a system of ordinary differential equations. A trial solution of this system involves two parts. The first part satisfies the initial condition and contains no adjustable parameters; however, the second part involves a feed-forward neural network containing adjustable parameters (the weights). This method shows that using neural networks provides solutions with good generalization and the high accuracy.https://doi.org/10.1177/1687814017717429
collection DOAJ
language English
format Article
sources DOAJ
author Mahmoud Paripour
Massimiliano Ferrara
Mehdi Salimi
spellingShingle Mahmoud Paripour
Massimiliano Ferrara
Mehdi Salimi
Approximate solutions by artificial neural network of hybrid fuzzy differential equations
Advances in Mechanical Engineering
author_facet Mahmoud Paripour
Massimiliano Ferrara
Mehdi Salimi
author_sort Mahmoud Paripour
title Approximate solutions by artificial neural network of hybrid fuzzy differential equations
title_short Approximate solutions by artificial neural network of hybrid fuzzy differential equations
title_full Approximate solutions by artificial neural network of hybrid fuzzy differential equations
title_fullStr Approximate solutions by artificial neural network of hybrid fuzzy differential equations
title_full_unstemmed Approximate solutions by artificial neural network of hybrid fuzzy differential equations
title_sort approximate solutions by artificial neural network of hybrid fuzzy differential equations
publisher SAGE Publishing
series Advances in Mechanical Engineering
issn 1687-8140
publishDate 2017-09-01
description In this article, we propose a new approach to solve the hybrid fuzzy differential equations based on the feed-forward neural networks. We first replace it by a system of ordinary differential equations. A trial solution of this system involves two parts. The first part satisfies the initial condition and contains no adjustable parameters; however, the second part involves a feed-forward neural network containing adjustable parameters (the weights). This method shows that using neural networks provides solutions with good generalization and the high accuracy.
url https://doi.org/10.1177/1687814017717429
work_keys_str_mv AT mahmoudparipour approximatesolutionsbyartificialneuralnetworkofhybridfuzzydifferentialequations
AT massimilianoferrara approximatesolutionsbyartificialneuralnetworkofhybridfuzzydifferentialequations
AT mehdisalimi approximatesolutionsbyartificialneuralnetworkofhybridfuzzydifferentialequations
_version_ 1724860220750954496

Similar Items