2007.58: The Whitney Reduction Network: A Method for Computing Autoassociative Graphs

2007.58: D. S. Broomhead and M.J. Kirby (2001) The Whitney Reduction Network: A Method for Computing Autoassociative Graphs. Neural Computation, 13. pp. 2595-2616. ISSN 0899-7667

Full text available as:

PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader 2413 Kb

DOI: 10.1162/089976601753196049

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.

Download Statistics: last 4 weeks
Repository Staff Only: edit this item