FEEDFORWARD NEURAL NETWORKS AND TOPOGRAPHIC MAPPINGS FOR EXPLORATORY DATA-ANALYSIS

A recent novel approach to the visualisation and analysis of datasets, and one which is particularly applicable to those of a high dimension , is discussed in the context of real applications. A feed-forward neu ral network is utilised to effect a topographic, structure-preserving, dimension-reducing transformation of the data, with an additional fac ility to incorporate different degrees of associated subjective inform ation. The properties of this transformation are illustrated on synthe tic and real datasets, including the 1992 UK Research Assessment Exerc ise for funding in higher education. The method is compared and contra sted to established techniques for feature extraction, and related to topographic mappings, the Sammon projection and the statistical field of multidimensional scaling.