Improvement the Back-propagation Technique

Error backpropagation neural network (EBP)  used training algorithm for feedforward artificial neural networks (FFANNs). The main problem with the EBP algorithm that it is very slow and the converge to the optimal solution is not guaranteed. This problem leads to search for improvements to speed up...

Full description

Saved in:
Bibliographic Details
Main Authors: Nidhal AL-Assady, Baydaa Khaleel, Shahbaa Khaleel
Format: Article
Language:English
Published: Mosul University 2004-12-01
Series:Al-Rafidain Journal of Computer Sciences and Mathematics
Subjects:
Online Access:https://csmj.mosuljournals.com/article_164115_06b1b3bba286b36777e7a68c4cab741d.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145319730282496
author Nidhal AL-Assady
Baydaa Khaleel
Shahbaa Khaleel
author_facet Nidhal AL-Assady
Baydaa Khaleel
Shahbaa Khaleel
author_sort Nidhal AL-Assady
collection DOAJ
description Error backpropagation neural network (EBP)  used training algorithm for feedforward artificial neural networks (FFANNs). The main problem with the EBP algorithm that it is very slow and the converge to the optimal solution is not guaranteed. This problem leads to search for improvements to speed up this algorithm. In this research we use several methods to speed up the EBP algorithm. A many layer neural network was designed for building pattern compression system, encoding and recognition. We also used many methods to speed up this algorithm (EBP) and comparison between them.
format Article
id doaj-art-98fd18ca95ed4a579728e7184de01807
institution OA Journals
issn 1815-4816
2311-7990
language English
publishDate 2004-12-01
publisher Mosul University
record_format Article
series Al-Rafidain Journal of Computer Sciences and Mathematics
spelling doaj-art-98fd18ca95ed4a579728e7184de018072025-08-20T02:28:08ZengMosul UniversityAl-Rafidain Journal of Computer Sciences and Mathematics1815-48162311-79902004-12-011212715110.33899/csmj.2004.164115164115Improvement the Back-propagation TechniqueNidhal AL-Assady0Baydaa Khaleel1Shahbaa Khaleel2Dept. of Computer Science College of Computer Sciences and Mathematics University of Mosul, IraqDept. of Computer Science College of Computer Sciences and Mathematics University of Mosul, IraqCollege of Computer Sciences and Mathematics University of MosulError backpropagation neural network (EBP)  used training algorithm for feedforward artificial neural networks (FFANNs). The main problem with the EBP algorithm that it is very slow and the converge to the optimal solution is not guaranteed. This problem leads to search for improvements to speed up this algorithm. In this research we use several methods to speed up the EBP algorithm. A many layer neural network was designed for building pattern compression system, encoding and recognition. We also used many methods to speed up this algorithm (EBP) and comparison between them.https://csmj.mosuljournals.com/article_164115_06b1b3bba286b36777e7a68c4cab741d.pdfartificial neural networksbackpropagationimage recognitionpattern compression
spellingShingle Nidhal AL-Assady
Baydaa Khaleel
Shahbaa Khaleel
Improvement the Back-propagation Technique
Al-Rafidain Journal of Computer Sciences and Mathematics
artificial neural networks
backpropagation
image recognition
pattern compression
title Improvement the Back-propagation Technique
title_full Improvement the Back-propagation Technique
title_fullStr Improvement the Back-propagation Technique
title_full_unstemmed Improvement the Back-propagation Technique
title_short Improvement the Back-propagation Technique
title_sort improvement the back propagation technique
topic artificial neural networks
backpropagation
image recognition
pattern compression
url https://csmj.mosuljournals.com/article_164115_06b1b3bba286b36777e7a68c4cab741d.pdf
work_keys_str_mv AT nidhalalassady improvementthebackpropagationtechnique
AT baydaakhaleel improvementthebackpropagationtechnique
AT shahbaakhaleel improvementthebackpropagationtechnique