Logo image
A study of the use of self-organising map for splitting training and validation sets for backpropagation neural network
Conference paper   Open access

A study of the use of self-organising map for splitting training and validation sets for backpropagation neural network

K.W. Wong, C.C. Fung and H. Eren
Proceedings of Digital Processing Applications (TENCON '96), Vol.1, pp.157-162
Proceedings of the 1996 IEEE Region 10 TENCON - Digital Signal Processing Applications Conference (Perth, Western Australia, 26/11/1996–29/11/1996)
1996
pdf
use_of_self-organising_map.pdfDownloadView
Published (Version of Record) Open Access
url
Link to Published Version *Subscription may be requiredView

Abstract

Validation has been used for the estimation of generalisation error of the backpropagation networks. The simplest way is to divide the available data into training and validation data sets. An approach using the self-organising map is proposed for the selection of the training and validation data sets. The results obtained from this study has shown that the proposed method provides a quick and reliable selection criteria and the overall training time is also reduced by applying the split-sample early stopping approach

Details

Metrics

207 File views/ downloads
72 Record Views
Logo image