NeuroScale: Novel Topographic Feature Extraction Using RBF Networks
Abstract
Dimension-reducing feature extraction neural network techniques which also preserve neighbourhood relationships in data have tra(cid:173) ditionally 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(cid:173) 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 net(cid:173) work 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.
Cite
Text
Lowe and Tipping. "NeuroScale: Novel Topographic Feature Extraction Using RBF Networks." Neural Information Processing Systems, 1996.Markdown
[Lowe and Tipping. "NeuroScale: Novel Topographic Feature Extraction Using RBF Networks." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/lowe1996neurips-neuroscale/)BibTeX
@inproceedings{lowe1996neurips-neuroscale,
title = {{NeuroScale: Novel Topographic Feature Extraction Using RBF Networks}},
author = {Lowe, David and Tipping, Michael E.},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {543-549},
url = {https://mlanthology.org/neurips/1996/lowe1996neurips-neuroscale/}
}