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...

Full description

Bibliographic Details
Main Authors: Mahmod, Ramlan, Omar, Khairuddin
Format: Article
Language:English
Malay
Published: Universiti Putra Malaysia Press 2000
Online Access:http://psasir.upm.edu.my/id/eprint/3508/
http://psasir.upm.edu.my/id/eprint/3508/1/Analisis_Pengawalan_Pemberat_Rangkaian_Neural_Perambatan.pdf
_version_ 1848839550146707456
author Mahmod, Ramlan
Omar, Khairuddin
author_facet Mahmod, Ramlan
Omar, Khairuddin
author_sort Mahmod, Ramlan
building UPM Institutional Repository
collection Online Access
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.
first_indexed 2025-11-15T07:13:14Z
format Article
id upm-3508
institution Universiti Putra Malaysia
institution_category Local University
language English
Malay
last_indexed 2025-11-15T07:13:14Z
publishDate 2000
publisher Universiti Putra Malaysia Press
recordtype eprints
repository_type Digital Repository
spelling upm-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
spellingShingle Mahmod, Ramlan
Omar, Khairuddin
Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi
title 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_short Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi
title_sort analisis pengawalan pemberat rangkaian neural perambatan balik untuk pengecaman aksara jawi
url http://psasir.upm.edu.my/id/eprint/3508/
http://psasir.upm.edu.my/id/eprint/3508/1/Analisis_Pengawalan_Pemberat_Rangkaian_Neural_Perambatan.pdf