Cover Image

Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems

The back propagation (BP) algorithm is a very popular learning approach in feedforward multilayer perceptron networks. However, the most serious problem associated with the BP is local minima problem and slow convergence speeds. Over the years, many improvements and modifications of the back...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul Hamid, Norhamreeza, Mohd Nawi, Nazri, Ghazali, Rozaida, Mohd Salleh, Mohd Najib
Format: Article
Language:English
Published: 2011
Subjects:
T Technology (General)
Online Access:http://eprints.uthm.edu.my/7955/1/J3714_e277896270c61202b64daf13c7d0f992.pdf
http://eprints.uthm.edu.my/7955/
https://doi.org/10.1007/978-3-642-20998-7_62
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uthm.eprints.7955
record_format eprints
spelling my.uthm.eprints.79552022-11-02T06:43:43Z http://eprints.uthm.edu.my/7955/ Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems Abdul Hamid, Norhamreeza Mohd Nawi, Nazri Ghazali, Rozaida Mohd Salleh, Mohd Najib T Technology (General) The back propagation (BP) algorithm is a very popular learning approach in feedforward multilayer perceptron networks. However, the most serious problem associated with the BP is local minima problem and slow convergence speeds. Over the years, many improvements and modifications of the back propagation learning algorithm have been reported. In this research, we propose a new modified back propagation learning algorithm by introducing adaptive gain together with adaptive momentum and adaptive learning rate into weight update process. By computer simulations, we demonstrate that the proposed algorithm can give a better convergence rate and can find a good solution in early time compare to the conventional back propagation. We use two common benchmark classification problems to illustrate the improvement in convergence time. 2011 Article PeerReviewed text en http://eprints.uthm.edu.my/7955/1/J3714_e277896270c61202b64daf13c7d0f992.pdf Abdul Hamid, Norhamreeza and Mohd Nawi, Nazri and Ghazali, Rozaida and Mohd Salleh, Mohd Najib (2011) Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems. International Journal of Software Engineering and its Applications, 5 (4). pp. 31-44. https://doi.org/10.1007/978-3-642-20998-7_62
institution Universiti Tun Hussein Onn Malaysia
building UTHM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tun Hussein Onn Malaysia
content_source UTHM Institutional Repository
url_provider http://eprints.uthm.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Abdul Hamid, Norhamreeza
Mohd Nawi, Nazri
Ghazali, Rozaida
Mohd Salleh, Mohd Najib
Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
description The back propagation (BP) algorithm is a very popular learning approach in feedforward multilayer perceptron networks. However, the most serious problem associated with the BP is local minima problem and slow convergence speeds. Over the years, many improvements and modifications of the back propagation learning algorithm have been reported. In this research, we propose a new modified back propagation learning algorithm by introducing adaptive gain together with adaptive momentum and adaptive learning rate into weight update process. By computer simulations, we demonstrate that the proposed algorithm can give a better convergence rate and can find a good solution in early time compare to the conventional back propagation. We use two common benchmark classification problems to illustrate the improvement in convergence time.
format Article
author Abdul Hamid, Norhamreeza
Mohd Nawi, Nazri
Ghazali, Rozaida
Mohd Salleh, Mohd Najib
author_facet Abdul Hamid, Norhamreeza
Mohd Nawi, Nazri
Ghazali, Rozaida
Mohd Salleh, Mohd Najib
author_sort Abdul Hamid, Norhamreeza
title Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
title_short Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
title_full Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
title_fullStr Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
title_full_unstemmed Accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
title_sort accelerating learning performance of back propagation algorithm by using adaptive gain together with adaptive momentum and adaptive learning rate on classification problems
publishDate 2011
url http://eprints.uthm.edu.my/7955/1/J3714_e277896270c61202b64daf13c7d0f992.pdf
http://eprints.uthm.edu.my/7955/
https://doi.org/10.1007/978-3-642-20998-7_62
_version_ 1748704854062137344
score 13.211869

Similar Items