Auto-association by multilayer perceptrons and singular value decomposition

The multilayer perceptron, when working in auto-association mode, is sometimes considered as an interesting candidate to perform data compression or dimensionality reduction of the feature space in information processing applications. The present paper shows that, for auto-association, the nonlinear...

Full description

Saved in:
Bibliographic Details
Published in:Biological cybernetics 1988-01, Vol.59 (4-5), p.291-294
Main Authors: BOURLARD, H, KAMP, Y
Format: Article
Language:English
Subjects:
Applied sciences
Circuit properties
Electric, optical and optoelectronic circuits
Electronic circuits
Electronics
Exact sciences and technology
Mathematics
Miscellaneous
Models, Neurological
Nerve Net - physiology
Nervous System Physiological Phenomena
Neural networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The multilayer perceptron, when working in auto-association mode, is sometimes considered as an interesting candidate to perform data compression or dimensionality reduction of the feature space in information processing applications. The present paper shows that, for auto-association, the nonlinearities of the hidden units are useless and that the optimal parameter values can be derived directly by purely linear techniques relying on singular value decomposition and low rank matrix approximation, similar in spirit to the well-known Karhunen-Loève transform. This approach appears thus as an efficient alternative to the general error back-propagation algorithm commonly used for training multilayer perceptrons. Moreover, it also gives a clear interpretation of the rôle of the different parameters.
ISSN:0340-1200
1432-0770
DOI:10.1007/bf00332918