Improving generalization of neural networks using multilayer perceptron discriminants

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...

Full description

Bibliographic Details
Main Authors: Siraj, Fadzilah, Partridge, Derek
Format: Article
Published: Taylor & Francis 2002
Subjects: