Training feed forward neural network with modified Fletcher-Reeves method
In this research, a modified Fletcher-Reeves (FR) conjugate gradient algorithm for training large scale feed forward neural network (FFNN) is presented. Under mild conditions, we establish that the proposed method satisfies the sufficient descent condition, and it is globally convergent under wolfe...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Journal of Multidisciplinary Modeling and Optimization
2018-08-01
|
Series: | Journal of Multidisciplinary Modeling and Optimization |
Subjects: | |
Online Access: | http://dergipark.org.tr/jmmo/issue/38716/392124?publisher=http-w3-sdu-edu-tr-personel-00606-prof-dr-ahmet-sahiner |
id |
doaj-7bf40f989afc47d99dc12bac3cd4d103 |
---|---|
record_format |
Article |
spelling |
doaj-7bf40f989afc47d99dc12bac3cd4d1032020-11-25T01:32:33ZengJournal of Multidisciplinary Modeling and OptimizationJournal of Multidisciplinary Modeling and Optimization2645-923X2018-08-011114221135Training feed forward neural network with modified Fletcher-Reeves methodYoksal A. LaylaniKhalil K. AbboHisham M. KhudhurIn this research, a modified Fletcher-Reeves (FR) conjugate gradient algorithm for training large scale feed forward neural network (FFNN) is presented. Under mild conditions, we establish that the proposed method satisfies the sufficient descent condition, and it is globally convergent under wolfe line search condition. The evidence which is provided by experimental results showed that our proposed method is preferable and superior to the classic methods.http://dergipark.org.tr/jmmo/issue/38716/392124?publisher=http-w3-sdu-edu-tr-personel-00606-prof-dr-ahmet-sahinerConjugate gradientNeural networkGlobal optimization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yoksal A. Laylani Khalil K. Abbo Hisham M. Khudhur |
spellingShingle |
Yoksal A. Laylani Khalil K. Abbo Hisham M. Khudhur Training feed forward neural network with modified Fletcher-Reeves method Journal of Multidisciplinary Modeling and Optimization Conjugate gradient Neural network Global optimization |
author_facet |
Yoksal A. Laylani Khalil K. Abbo Hisham M. Khudhur |
author_sort |
Yoksal A. Laylani |
title |
Training feed forward neural network with modified Fletcher-Reeves method |
title_short |
Training feed forward neural network with modified Fletcher-Reeves method |
title_full |
Training feed forward neural network with modified Fletcher-Reeves method |
title_fullStr |
Training feed forward neural network with modified Fletcher-Reeves method |
title_full_unstemmed |
Training feed forward neural network with modified Fletcher-Reeves method |
title_sort |
training feed forward neural network with modified fletcher-reeves method |
publisher |
Journal of Multidisciplinary Modeling and Optimization |
series |
Journal of Multidisciplinary Modeling and Optimization |
issn |
2645-923X |
publishDate |
2018-08-01 |
description |
In this research, a modified Fletcher-Reeves
(FR) conjugate gradient algorithm for training large scale feed forward neural
network (FFNN) is presented. Under mild conditions, we establish that the
proposed method satisfies the sufficient descent condition, and it is globally
convergent under wolfe line search condition. The evidence which is provided by
experimental results showed that our proposed method is preferable and superior
to the classic methods. |
topic |
Conjugate gradient Neural network Global optimization |
url |
http://dergipark.org.tr/jmmo/issue/38716/392124?publisher=http-w3-sdu-edu-tr-personel-00606-prof-dr-ahmet-sahiner |
work_keys_str_mv |
AT yoksalalaylani trainingfeedforwardneuralnetworkwithmodifiedfletcherreevesmethod AT khalilkabbo trainingfeedforwardneuralnetworkwithmodifiedfletcherreevesmethod AT hishammkhudhur trainingfeedforwardneuralnetworkwithmodifiedfletcherreevesmethod |
_version_ |
1725081239505862656 |