Dynamic training rate for backpropagation learning algorithm
In this paper, we created a dynamic function training rate for the Back propagation learning algorithm to avoid the local minimum and to speed up training.The Back propagation with dynamic training rate (BPDR) algorithm uses the sigmoid function.The 2-dimensional XOR problem and iris data were used...
Saved in:
Main Authors: | , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/19123/1/MICC%202013%20277-282.pdf http://repo.uum.edu.my/19123/ http://doi.org/10.1109/MICC.2013.6805839 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.19123 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.191232016-11-10T03:29:55Z http://repo.uum.edu.my/19123/ Dynamic training rate for backpropagation learning algorithm Al-Duais, M. S. Yaakub, Abdul Razak Yusoff, Nooraini QA75 Electronic computers. Computer science In this paper, we created a dynamic function training rate for the Back propagation learning algorithm to avoid the local minimum and to speed up training.The Back propagation with dynamic training rate (BPDR) algorithm uses the sigmoid function.The 2-dimensional XOR problem and iris data were used as benchmarks to test the effects of the dynamic training rate formulated in this paper.The results of these experiments demonstrate that the BPDR algorithm is advantageous with regards to both generalization performance and training speed. The stop training or limited error was determined by1.0 e-5 2013-11-26 Conference or Workshop Item PeerReviewed application/pdf en http://repo.uum.edu.my/19123/1/MICC%202013%20277-282.pdf Al-Duais, M. S. and Yaakub, Abdul Razak and Yusoff, Nooraini (2013) Dynamic training rate for backpropagation learning algorithm. In: IEEE 11th Malaysia International Conference on Communications (MICC), 26-28 Nov. 2013, Kuala Lumpur, Malaysia. http://doi.org/10.1109/MICC.2013.6805839 doi:10.1109/MICC.2013.6805839 |
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 |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Al-Duais, M. S. Yaakub, Abdul Razak Yusoff, Nooraini Dynamic training rate for backpropagation learning algorithm |
description |
In this paper, we created a dynamic function training rate for the Back propagation learning algorithm to avoid the local minimum and to speed up training.The Back propagation with dynamic training rate (BPDR) algorithm uses the sigmoid function.The 2-dimensional XOR problem and iris data were used as benchmarks to test the effects of the dynamic training rate formulated in this paper.The results of these experiments demonstrate that the BPDR algorithm is advantageous with regards to both generalization performance and training speed. The stop training or limited error was determined by1.0 e-5 |
format |
Conference or Workshop Item |
author |
Al-Duais, M. S. Yaakub, Abdul Razak Yusoff, Nooraini |
author_facet |
Al-Duais, M. S. Yaakub, Abdul Razak Yusoff, Nooraini |
author_sort |
Al-Duais, M. S. |
title |
Dynamic training rate for backpropagation learning algorithm |
title_short |
Dynamic training rate for backpropagation learning algorithm |
title_full |
Dynamic training rate for backpropagation learning algorithm |
title_fullStr |
Dynamic training rate for backpropagation learning algorithm |
title_full_unstemmed |
Dynamic training rate for backpropagation learning algorithm |
title_sort |
dynamic training rate for backpropagation learning algorithm |
publishDate |
2013 |
url |
http://repo.uum.edu.my/19123/1/MICC%202013%20277-282.pdf http://repo.uum.edu.my/19123/ http://doi.org/10.1109/MICC.2013.6805839 |
_version_ |
1644282623563923456 |
score |
13.154949 |