Skip to the content

Improving the performance of multilayer perceptrons where limited training data are available for some classes

Parikh, CR, Pont, MJ, Li, Y and Jones, NB 1999, Improving the performance of multilayer perceptrons where limited training data are available for some classes , in: 9th International Conference on Artificial Neural Networks: ICANN '99, 7-10 September 1999, Edinburgh.

Full text not available from this repository. (Request a copy)

Abstract

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.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: 9th International Conference on Artificial Neural Networks: ICANN '99
Publisher: The Institution of Engineering and Technology (IET)
Refereed: Yes
Funders: Non funded research
Depositing User: Yuhua Li
Date Deposited: 27 Jul 2015 16:56
Last Modified: 05 Apr 2016 19:29
URI: http://usir.salford.ac.uk/id/eprint/35443

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)