Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi
One of the factors that influences the recognition ability of a neural network is the initial values given to the weight vector during the training phase. The network may be trapped into a local minima if the initial weights are not chosen carefully. This paper presents an analysis of the ability o...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Language: | English Malay |
Published: |
Universiti Putra Malaysia Press
2000
|
Online Access: | http://psasir.upm.edu.my/id/eprint/3508/1/Analisis_Pengawalan_Pemberat_Rangkaian_Neural_Perambatan.pdf http://psasir.upm.edu.my/id/eprint/3508/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.upm.eprints.3508 |
---|---|
record_format |
eprints |
spelling |
my.upm.eprints.35082013-05-27T07:09:04Z http://psasir.upm.edu.my/id/eprint/3508/ Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi Mahmod, Ramlan Omar, Khairuddin One of the factors that influences the recognition ability of a neural network is the initial values given to the weight vector during the training phase. The network may be trapped into a local minima if the initial weights are not chosen carefully. This paper presents an analysis of the ability of the network to recognise Jawi characters after it was trained using different methods of weight initialization. Three most common methods are zero, random and Nguyen-Widrow random. This paper presents the effect of these three methods on the ability of the network's recognition. Universiti Putra Malaysia Press 2000 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/3508/1/Analisis_Pengawalan_Pemberat_Rangkaian_Neural_Perambatan.pdf Mahmod, Ramlan and Omar, Khairuddin (2000) Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi. Pertanika Journal of Science & Technology, 8 (1). pp. 41-54. ISSN 0128-7680 Malay |
institution |
Universiti Putra Malaysia |
building |
UPM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Putra Malaysia |
content_source |
UPM Institutional Repository |
url_provider |
http://psasir.upm.edu.my/ |
language |
English Malay |
description |
One of the factors that influences the recognition ability of a neural network is the initial values given to the weight vector during the training phase. The network may be trapped into a local minima if the initial weights are not
chosen carefully. This paper presents an analysis of the ability of the network to recognise Jawi characters after it was trained using different methods of
weight initialization. Three most common methods are zero, random and Nguyen-Widrow random. This paper presents the effect of these three methods
on the ability of the network's recognition. |
format |
Article |
author |
Mahmod, Ramlan Omar, Khairuddin |
spellingShingle |
Mahmod, Ramlan Omar, Khairuddin Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi |
author_facet |
Mahmod, Ramlan Omar, Khairuddin |
author_sort |
Mahmod, Ramlan |
title |
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik
untuk Pengecaman Aksara Jawi |
title_short |
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik
untuk Pengecaman Aksara Jawi |
title_full |
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik
untuk Pengecaman Aksara Jawi |
title_fullStr |
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik
untuk Pengecaman Aksara Jawi |
title_full_unstemmed |
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik
untuk Pengecaman Aksara Jawi |
title_sort |
analisis pengawalan pemberat rangkaian neural perambatan balik
untuk pengecaman aksara jawi |
publisher |
Universiti Putra Malaysia Press |
publishDate |
2000 |
url |
http://psasir.upm.edu.my/id/eprint/3508/1/Analisis_Pengawalan_Pemberat_Rangkaian_Neural_Perambatan.pdf http://psasir.upm.edu.my/id/eprint/3508/ |
_version_ |
1643822631460274176 |
score |
13.15806 |