Siraj, Fadzilah and Partridge, Derek (2002) Improving generalization of neural networks using multilayer perceptron discriminants. International Journal of Systems Science , 42 (7). pp. 1059-1068. ISSN 0020-7721

Full text not available from this repository.

Abstract

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-to-learn (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.

Item Type:	Article
Uncontrolled Keywords:	Multilayer Perceptron; Generalization; Neural Networks; Discriminant; Empirical
Subjects:	Q Science > QA Mathematics
Divisions:	College of Arts and Sciences
Depositing User:	Prof Madya Fadzilah Siraj
Date Deposited:	12 Nov 2010 02:13
Last Modified:	12 Nov 2010 02:13
URI:	https://repo.uum.edu.my/id/eprint/1525

Actions (login required)

View Item