Format

Send to

Choose Destination
Neural Comput. 2001 Nov;13(11):2595-616.

The Whitney reduction network: a method for computing autoassociative graphs.

Author information

1
Department of Mathematics, University of Manchester Institute of Science and Technology, Manchester M60 1QD, UK.

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 < or = 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.

PMID:
11674853
DOI:
10.1162/089976601753196049

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center