The Whitney Reduction Network: A Method for Computing Autoassociative Graphs

Broomhead, D. S. and Kirby, M.J. (2001) The Whitney Reduction Network: A Method for Computing Autoassociative Graphs. Neural Computation, 13. pp. 2595-2616. ISSN 0899-7667

PDF The_Whitney_Reduction.pdf Restricted to Registered users only Download (2MB)

Abstract

This article introduces a new architecture and associated algorithms ideal for implementing the dimensionality reduction of an m-dimensional manifold initially residing in an n-dimensional Euclidean space where n>>m. Motivated by Whitney's embedding theorem, the network is capable of training the identity mapping employing the idea of the graph of a function. In theory, a reduction to a dimension d that retains the differential structure of the original data may be achieved for some d<=2m+1. To implement this network, we propose the idea of a good-projection, which enhances the generalization capabilities of the network, and an adaptive secant basis algorithm to achieve it. The effect of noise on this procedure is also considered. The approach is illustrated with several examples.

Item Type:	Article
Subjects:	MSC 2010, the AMS's Mathematics Subject Classification > 37 Dynamical systems and ergodic theory MSC 2010, the AMS's Mathematics Subject Classification > 53 Differential geometry
Depositing User:	Ms Lucy van Russelt
Date Deposited:	30 Mar 2007
Last Modified:	20 Oct 2017 14:12
URI:	https://eprints.maths.manchester.ac.uk/id/eprint/713

Actions (login required)

View Item