Improving the performance of multi-layer perceptrons where limited training data are available for some classes

The standard multi-layer perceptron (MLP) training algorithm implicitly assumes that equal numbers of examples are available to train each of the network classes. However, in many condition monitoring and fault diagnosis (CMFD) systems, data representing fault conditions can only be obtained with gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Parikh, C.R, Pont, M.J, Jones, N.B
Format: Conference Proceeding
Language:English
Subjects:
Engineering computing
Learning in AI
Neural computing techniques
Neural nets
Pattern recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The standard multi-layer perceptron (MLP) training algorithm implicitly assumes that equal numbers of examples are available to train each of the network classes. However, in many condition monitoring and fault diagnosis (CMFD) systems, data representing fault conditions can only be obtained with great difficulty: as a result, training classes may vary greatly in size, and the overall performance of an MLP classifier may be comparatively poor. We describe two techniques which can help ameliorate the impact of unequal training set sizes. We demonstrate the effectiveness of these techniques using simulated fault data representative of that found in a broad class of CMFD problems.
ISSN:0537-9989
DOI:10.1049/cp:19991113