Catalog Home Page

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

Wong, K.W., Fung, C.C. and Eren, H. (1996) A study of the use of self-organising map for splitting training and validation sets for backpropagation neural network. In: Proceedings of the 1996 IEEE Region 10 TENCON - Digital Signal Processing Applications Conference, 26 - 29 November, Perth, Western Australia pp. 157-162.

[img]
Preview
PDF - Published Version
Download (649kB)
Link to Published Version: http://dx.doi.org/10.1109/TENCON.1996.608768
*Subscription may be required

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

Publication Type: Conference Paper
URI: http://researchrepository.murdoch.edu.au/id/eprint/16226
Item Control Page Item Control Page

Downloads

Downloads per month over past year