Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi

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

[img] PDF
2656Kb

Abstract

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.

Item Type:Article
Keyword:Rangkaian neural, perambatan-balik, Rawak Nguyen-Widrow, pengecaman corak
Faculty or Institute:Faculty of Computer Science and Information Technology
Publisher:Universiti Putra Malaysia Press
ID Code:3508
Deposited By: Nur Izzati Mohd Zaki
Deposited On:30 Nov 2009 00:49
Last Modified:27 May 2013 07:09

Repository Staff Only: Edit item detail

Document Download Statistics

This item has been downloaded for since 30 Nov 2009 00:49.

View statistics for "Analisis Pengawalan Pemberat Rangkaian Neural Perambatan Balik untuk Pengecaman Aksara Jawi"


Universiti Putra Malaysia Institutional Repository

Universiti Putra Malaysia Institutional Repository is an on-line digital archive that serves as a central collection and storage of scientific information and research at the Universiti Putra Malaysia.

Currently, the collections deposited in the IR consists of Master and PhD theses, Master and PhD Project Report, Journal Articles, Journal Bulletins, Conference Papers, UPM News, Newspaper Cuttings, Patents and Inaugural Lectures.

As the policy of the university does not permit users to view thesis in full text, access is only given to the first 24 pages only.