Neuroscale: Novel Topographic Feature Extraction Using Rbf Networks 1 `neuroscale': a Feed-forward Neural Network Topographic Transformation

Dimension-reducing feature extraction neural network techniques which also preserve neighbourhood relationships in data have traditionally been the exclusive domain of Kohonen self organising maps. Recently, we introduced a novel dimension-reducing feature extraction process, which is also topographic, based upon a Radial Basis Function architecture. It has been observed that the gener-alisation performance of the system is broadly insensitive to model order complexity and other smoothing factors such as the kernel widths, contrary to intuition derived from supervised neural network models. In this paper we provide an eeective demonstration of this property and give a theoretical justiication for the apparent`self-regularising' behaviour of thèNeuroScale' architecture. Recently an important class of topographic neural network based feature extraction approaches, which can be related to the traditional statistical methods of Sammon These novel alternatives to Kohonen-like approaches for topographic feature extraction possess several interesting properties. For instance, the NeuroScale architecture has the empirically observed property that the generalisation perfor