A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat

Till today, it has been a great challenge in optimizing the training time in neural networks. This paper presents Local Adaptive Techniques and Dynamic Adaptation Methods as acceleration techniques for neural networks. The first technique is based on weight-specific information such as the temporal...

Full description

Bibliographic Details
Main Author:	Mahat, Norpah
Format:	Article
Language:	English
Published:	Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA) 2011
Subjects:	Electronic computers. Computer science
Online Access:	http://ir.uitm.edu.my/id/eprint/8852/ http://ir.uitm.edu.my/id/eprint/8852/1/AJ_NORPAH%20MAHAT%20ESTEEM%2011.pdf

id	uitm-8852
recordtype	eprints
spelling	uitm-88522017-03-14T04:42:42Z http://ir.uitm.edu.my/id/eprint/8852/ A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat Mahat, Norpah Electronic computers. Computer science Till today, it has been a great challenge in optimizing the training time in neural networks. This paper presents Local Adaptive Techniques and Dynamic Adaptation Methods as acceleration techniques for neural networks. The first technique is based on weight-specific information such as the temporal behavior of the partial derivative of the current weight. The second technique is dynamically adapts the momentum factor, a, and learning rate, ᶯ with respect to the iteration number or gradient. Some of the most popular learning algorithms are described and discussed. Simulations on a real world application problem are conducted to evaluate and compare the performance of a local adaptive strategies with various popular training algorithms include global adaptive strategies. These techniques have been compared and measured in terms of gradient and error function evaluations, and percentage of success. Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA) 2011 Article PeerReviewed text en http://ir.uitm.edu.my/id/eprint/8852/1/AJ_NORPAH%20MAHAT%20ESTEEM%2011.pdf Mahat, Norpah (2011) A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat. Esteem Academic Journal, 7 (2). pp. 35-51. ISSN 1675-7939
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Teknologi MARA
building	UiTM Institutional Repository
collection	Online Access
language	English
topic	Electronic computers. Computer science
spellingShingle	Electronic computers. Computer science Mahat, Norpah A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
description	Till today, it has been a great challenge in optimizing the training time in neural networks. This paper presents Local Adaptive Techniques and Dynamic Adaptation Methods as acceleration techniques for neural networks. The first technique is based on weight-specific information such as the temporal behavior of the partial derivative of the current weight. The second technique is dynamically adapts the momentum factor, a, and learning rate, ᶯ with respect to the iteration number or gradient. Some of the most popular learning algorithms are described and discussed. Simulations on a real world application problem are conducted to evaluate and compare the performance of a local adaptive strategies with various popular training algorithms include global adaptive strategies. These techniques have been compared and measured in terms of gradient and error function evaluations, and percentage of success.
format	Article
author	Mahat, Norpah
author_facet	Mahat, Norpah
author_sort	Mahat, Norpah
title	A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
title_short	A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
title_full	A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
title_fullStr	A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
title_full_unstemmed	A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat
title_sort	study of acceleration techniques in training neural networks - local adaptive techniques / norpah mahat
publisher	Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA)
publishDate	2011
url	http://ir.uitm.edu.my/id/eprint/8852/ http://ir.uitm.edu.my/id/eprint/8852/1/AJ_NORPAH%20MAHAT%20ESTEEM%2011.pdf
first_indexed	2023-09-18T22:47:32Z
last_indexed	2023-09-18T22:47:32Z
_version_	1777417325124780032

A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat

Similar Items