Improving generalization of neural network using length as discriminant
This paper discusses the empirical evaluation of improving generalization performance of neural networks by systematic treatment of training and test failures. As a result of systematic treatment of failures, a discrimination technique using LENGTH was developed. The experiments presented in this pa...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universiti Utara Malaysia
1999
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/90/1/Fadzilah_Siraj.pdf http://repo.uum.edu.my/90/ http://ijms.uum.edu.my |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.90 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.902010-07-04T01:52:11Z http://repo.uum.edu.my/90/ Improving generalization of neural network using length as discriminant Siraj, Fadzilah Partridge, Derek QA76 Computer software This paper discusses the empirical evaluation of improving generalization performance of neural networks by systematic treatment of training and test failures. As a result of systematic treatment of failures, a discrimination technique using LENGTH was developed. The experiments presented in this paper illustrate the application of discrimination technique using LENGTH to neural networks trained to solve supervised learning tasks such as the Launch Interceptor Condition 1 problem. The discriminant LENGTH is used to discriminate between the predicted "hard-to-learn" and predicted "easy-to-learn" patterns before these patterns are fed into the networks. The experimental results reveal that the utilization of LENGTH as discriminant has improved the average generalization of the networks increased. Universiti Utara Malaysia 1999 Article PeerReviewed application/pdf en http://repo.uum.edu.my/90/1/Fadzilah_Siraj.pdf Siraj, Fadzilah and Partridge, Derek (1999) Improving generalization of neural network using length as discriminant. Analisis, 6 (1&2). pp. 75-87. ISSN 0127-8983 http://ijms.uum.edu.my |
institution |
Universiti Utara Malaysia |
building |
UUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Utara Malaysia |
content_source |
UUM Institutionali Repository |
url_provider |
http://repo.uum.edu.my/ |
language |
English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Siraj, Fadzilah Partridge, Derek Improving generalization of neural network using length as discriminant |
description |
This paper discusses the empirical evaluation of improving generalization performance of neural networks by systematic treatment of training and test failures. As a result of systematic treatment of failures, a discrimination technique using LENGTH was developed. The experiments presented in this paper illustrate the application of discrimination technique using LENGTH to neural networks trained to solve supervised learning tasks such as the Launch Interceptor Condition 1 problem. The discriminant LENGTH is used to discriminate between the predicted "hard-to-learn" and predicted "easy-to-learn" patterns before these patterns are fed into the networks. The experimental results reveal that the utilization of LENGTH as discriminant has improved the average generalization of the networks increased.
|
format |
Article |
author |
Siraj, Fadzilah Partridge, Derek |
author_facet |
Siraj, Fadzilah Partridge, Derek |
author_sort |
Siraj, Fadzilah |
title |
Improving generalization of neural network using length as discriminant |
title_short |
Improving generalization of neural network using length as discriminant |
title_full |
Improving generalization of neural network using length as discriminant |
title_fullStr |
Improving generalization of neural network using length as discriminant |
title_full_unstemmed |
Improving generalization of neural network using length as discriminant |
title_sort |
improving generalization of neural network using length as discriminant |
publisher |
Universiti Utara Malaysia |
publishDate |
1999 |
url |
http://repo.uum.edu.my/90/1/Fadzilah_Siraj.pdf http://repo.uum.edu.my/90/ http://ijms.uum.edu.my |
_version_ |
1644277719407525888 |
score |
13.144533 |