A framework for multi-backpropagation
Backpropagation algorithm is one of the most popular learning algorithms in the Neural Network. It has been successfully implemented in many applications. However, training Neural Networks involve a large amount of data. Therefore, training the network is time consuming as each training session req...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universiti Utara Malaysia
2003
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/94/1/Fadzilah_Siraj_2.pdf http://repo.uum.edu.my/94/ http://ijms.uum.edu.my |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.94 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.942010-07-04T02:06:04Z http://repo.uum.edu.my/94/ A framework for multi-backpropagation Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib QA76 Computer software Backpropagation algorithm is one of the most popular learning algorithms in the Neural Network. It has been successfully implemented in many applications. However, training Neural Networks involve a large amount of data. Therefore, training the network is time consuming as each training session requires several epochs, which usually takes smeral seconds or even minutes.This paper proposes a multi-backpropagation approach to minimize the complexity of the network. The approach does not require an alteration of the algorithm. Instead, the large network is split into several smaller networks. An integrating network is then constructed to integrate the output from the smaller networks. Universiti Utara Malaysia 2003 Article PeerReviewed application/pdf en http://repo.uum.edu.my/94/1/Fadzilah_Siraj_2.pdf Wan Ishak, Wan Hussain and Siraj, Fadzilah and Othman, Abu Talib (2003) A framework for multi-backpropagation. Analisis, 10 (1). pp. 59-68. ISSN 0127-8983 http://ijms.uum.edu.my |
institution |
Universiti Utara Malaysia |
building |
UUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Utara Malaysia |
content_source |
UUM Institutionali Repository |
url_provider |
http://repo.uum.edu.my/ |
language |
English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib A framework for multi-backpropagation |
description |
Backpropagation algorithm is one of the most popular learning algorithms in the Neural Network. It has been successfully implemented in many applications. However, training Neural Networks involve a large amount of data.
Therefore, training the network is time consuming as each training session requires several epochs, which usually takes smeral seconds or even minutes.This paper proposes a multi-backpropagation approach to minimize the complexity
of the network. The approach does not require an alteration of the algorithm. Instead, the large network is split into several smaller networks. An integrating network is then constructed to integrate the output from the smaller networks.
|
format |
Article |
author |
Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib |
author_facet |
Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib |
author_sort |
Wan Ishak, Wan Hussain |
title |
A framework for multi-backpropagation |
title_short |
A framework for multi-backpropagation |
title_full |
A framework for multi-backpropagation |
title_fullStr |
A framework for multi-backpropagation |
title_full_unstemmed |
A framework for multi-backpropagation |
title_sort |
framework for multi-backpropagation |
publisher |
Universiti Utara Malaysia |
publishDate |
2003 |
url |
http://repo.uum.edu.my/94/1/Fadzilah_Siraj_2.pdf http://repo.uum.edu.my/94/ http://ijms.uum.edu.my |
_version_ |
1644277719984242688 |
score |
13.145126 |