Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm
The batch back prorogation algorithm is anew style for weight updating. The drawback of the BBP algorithm is its slow learning rate and easy convergence to the local minimum. The learning rate and momentum factor are the are the most significant parameter for increasing the efficiency of the BB...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English English |
Published: |
2020
|
Subjects: | |
Online Access: | http://eprints.unisza.edu.my/7000/1/FH02-FIK-20-40900.pdf http://eprints.unisza.edu.my/7000/2/FH02-FIK-20-40901.pdf http://eprints.unisza.edu.my/7000/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-unisza-ir.7000 |
---|---|
record_format |
eprints |
spelling |
my-unisza-ir.70002022-04-24T02:12:48Z http://eprints.unisza.edu.my/7000/ Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm Fatma Susilawati, Mohamad Mumtazimah, Mohamad Sarhan, AlDuais QA75 Electronic computers. Computer science The batch back prorogation algorithm is anew style for weight updating. The drawback of the BBP algorithm is its slow learning rate and easy convergence to the local minimum. The learning rate and momentum factor are the are the most significant parameter for increasing the efficiency of the BBP algorithm. We created the dynamic learning rate and dynamic momentum factor for increasing the efficiency of the algorithm. We used several data set for testing the effects of the dynamic learning rate and dynamic momentum factor that we created in this paper. All the experiments for both algorithms were performed on Matlab 2016 a. The stop training was determined ten power -5. The average accuracy training is 0.9909 and average processing time improved of dynamic algorithm is 430 times faster than the BBP algorithm. From the experimental results, the dynamic algorithm provides superior performance in terms of faster training with highest accuracy training compared to the manual algorithm. The dynamic parameters which created in this paper helped the algorithm to escape the local minimum and eliminate training saturation, thereby reducing training time and the number of epochs. The dynamic algorithm was achieving a superior level of performance compared with existing works (latest studies). 2020-09 Article PeerReviewed text en http://eprints.unisza.edu.my/7000/1/FH02-FIK-20-40900.pdf text en http://eprints.unisza.edu.my/7000/2/FH02-FIK-20-40901.pdf Fatma Susilawati, Mohamad and Mumtazimah, Mohamad and Sarhan, AlDuais (2020) Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm. International Journal of Intelligent Systems and Applications, 12 (1). pp. 43-54. ISSN 2074-904X 10.5815/ijisa.2020.01.05 |
institution |
Universiti Sultan Zainal Abidin |
building |
UNISZA Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Sultan Zainal Abidin |
content_source |
UNISZA Institutional Repository |
url_provider |
https://eprints.unisza.edu.my/ |
language |
English English |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Fatma Susilawati, Mohamad Mumtazimah, Mohamad Sarhan, AlDuais Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
description |
The batch back prorogation algorithm is anew
style for weight updating. The drawback of the BBP
algorithm is its slow learning rate and easy convergence
to the local minimum. The learning rate and momentum
factor are the are the most significant parameter for
increasing the efficiency of the BBP algorithm. We
created the dynamic learning rate and dynamic
momentum factor for increasing the efficiency of the
algorithm. We used several data set for testing the effects
of the dynamic learning rate and dynamic momentum
factor that we created in this paper. All the experiments
for both algorithms were performed on Matlab 2016 a.
The stop training was determined ten power -5. The
average accuracy training is 0.9909 and average
processing time improved of dynamic algorithm is 430
times faster than the BBP algorithm. From the
experimental results, the dynamic algorithm provides
superior performance in terms of faster training with
highest accuracy training compared to the manual
algorithm. The dynamic parameters which created in this
paper helped the algorithm to escape the local minimum
and eliminate training saturation, thereby reducing
training time and the number of epochs. The dynamic
algorithm was achieving a superior level of performance
compared with existing works (latest studies). |
format |
Article |
author |
Fatma Susilawati, Mohamad Mumtazimah, Mohamad Sarhan, AlDuais |
author_facet |
Fatma Susilawati, Mohamad Mumtazimah, Mohamad Sarhan, AlDuais |
author_sort |
Fatma Susilawati, Mohamad |
title |
Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
title_short |
Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
title_full |
Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
title_fullStr |
Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
title_full_unstemmed |
Enhancement processing time and accuracy training via significant parameters in the batch BP algorithm |
title_sort |
enhancement processing time and accuracy training via significant parameters in the batch bp algorithm |
publishDate |
2020 |
url |
http://eprints.unisza.edu.my/7000/1/FH02-FIK-20-40900.pdf http://eprints.unisza.edu.my/7000/2/FH02-FIK-20-40901.pdf http://eprints.unisza.edu.my/7000/ |
_version_ |
1734304590396915712 |
score |
13.160551 |