C.: Bagging and bumping self-organising maps

In this paper, we apply the combination method of bagging which has been developed in the context of supervised learning of classifiers and regressors to the unsupervised artificial neural network known as the Self Organising Map. We show that various initialisation techniques can be used to create maps which are comparable by humans by eye. We then use a semi-supervised version of the SOM to classify data sets and show how bagging may be used to improve classification. We then compare bumping and bagging on this data set.