A STUDY OF THE CLASSIFICATION CAPABILITIES OF NEURAL NETWORKS USING UNSUPERVISED LEARNING - A COMPARISON WITH K-MEANS CLUSTERING

Several neural networks have been proposed in the general literature f or pattern recognition and clustering, but little empirical comparison with traditional methods has been done. The results reported here com pare neural networks using Kohonen learning with a traditional cluster ing method (K-means) in an experimental design using simulated data wi th known cluster solutions. Two types of neural networks were examined , both of which used unsupervised learning to perform the clustering. One used Kohonen learning with a conscience and the other used Kohonen learning without a conscience mechanism. The performance of these net s was examined with respect to changes in the number of attributes, th e number of clusters, and the amount of error in the data. Generally, the K-means procedure had fewer points misclassified while the classif ication accuracy of neural networks worsened as the number of clusters in the data increased from two to five.