Systematic treatment of failures using multilayer perceptrons

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, multilayer perceptron (MLP) discriminants were developed as discrimination techniques. Th...

全面介紹

Saved in:
書目詳細資料
Main Authors: Siraj, Fadzilah, Partridge, Derek
格式: Conference or Workshop Item
語言:English
出版: 2000
主題:
在線閱讀:http://repo.uum.edu.my/1540/1/FLAIRS00-046.pdf
http://repo.uum.edu.my/1540/
http://www.aaai.org/Papers/FLAIRS/2000/FLAIRS00-046.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my.uum.repo.1540
record_format eprints
spelling my.uum.repo.15402010-11-12T06:58:11Z http://repo.uum.edu.my/1540/ Systematic treatment of failures using multilayer perceptrons 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, multilayer perceptron (MLP) discriminants were developed as discrimination techniques. The experiments presented in this paper illustrate the application of discrimination techniques using MLP discriminants to neural networks trained to solve supervised learning task such as the Launch Interceptor Condition 1 problem. The MLP discriminants were constructed from the training and test patterns. The first discriminant is known as the hard-to-learn and easy-to-learn discriminant whilst the second one is known as hard-to-compute and easy-to-compute discriminant. Further treatments were also applied to hard-tolearn (or hard-to-compute) patterns prior to training (or testing). The experimental results reveal that directed splitting or using MLP discriminant is an important strategy in improving generalization of the networks. 2000 Conference or Workshop Item PeerReviewed application/pdf en http://repo.uum.edu.my/1540/1/FLAIRS00-046.pdf Siraj, Fadzilah and Partridge, Derek (2000) Systematic treatment of failures using multilayer perceptrons. In: Proceedings of the Thirteenth International Florida Artificial Intelligence Research Society Conference, 22-24 May 2000, Orlando, Florida USA. http://www.aaai.org/Papers/FLAIRS/2000/FLAIRS00-046.pdf
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
Systematic treatment of failures using multilayer perceptrons
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, multilayer perceptron (MLP) discriminants were developed as discrimination techniques. The experiments presented in this paper illustrate the application of discrimination techniques using MLP discriminants to neural networks trained to solve supervised learning task such as the Launch Interceptor Condition 1 problem. The MLP discriminants were constructed from the training and test patterns. The first discriminant is known as the hard-to-learn and easy-to-learn discriminant whilst the second one is known as hard-to-compute and easy-to-compute discriminant. Further treatments were also applied to hard-tolearn (or hard-to-compute) patterns prior to training (or testing). The experimental results reveal that directed splitting or using MLP discriminant is an important strategy in improving generalization of the networks.
format Conference or Workshop Item
author Siraj, Fadzilah
Partridge, Derek
author_facet Siraj, Fadzilah
Partridge, Derek
author_sort Siraj, Fadzilah
title Systematic treatment of failures using multilayer perceptrons
title_short Systematic treatment of failures using multilayer perceptrons
title_full Systematic treatment of failures using multilayer perceptrons
title_fullStr Systematic treatment of failures using multilayer perceptrons
title_full_unstemmed Systematic treatment of failures using multilayer perceptrons
title_sort systematic treatment of failures using multilayer perceptrons
publishDate 2000
url http://repo.uum.edu.my/1540/1/FLAIRS00-046.pdf
http://repo.uum.edu.my/1540/
http://www.aaai.org/Papers/FLAIRS/2000/FLAIRS00-046.pdf
_version_ 1644278001716690944