This paper presents a new hybrid learning algorithm for unsupervised classification tasks. We combined Fuzzy c-means learning algorithm and a supervised version of Minimerror to develop a hybrid incremental strategy allowing unsupervised classifications. We applied this new approach to a real-world database in order to know if the information contained in unlabeled features of a Geographic Information System (GIS), allows to well classify it. Finally, we compared our results to a classical supervised classification obtained by a multilayer perceptron.
@article{arxiv.0905.2347,
title = {Combining Supervised and Unsupervised Learning for GIS Classification},
author = {Juan-Manuel Torres-Moreno and Laurent Bougrain and Frdéric Alexandre},
journal= {arXiv preprint arXiv:0905.2347},
year = {2009}
}