NeuroScale: Novel Topographic Feature Extraction using RBF Networks
David G. Lowe, Michael E. Tipping · 1996
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 generalisation 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 effective demonstration of this property and give a theoretical justification for the apparent `self-regularising' behaviour of the `NeuroScale' architecture.