University of Surrey

Test tubes in the lab Research in the ATI Dance Research

LYAPUNOV FUNCTIONS FOR CONVERGENCE OF PRINCIPAL COMPONENT ALGORITHMS

PLUMBLEY, MD (1995) LYAPUNOV FUNCTIONS FOR CONVERGENCE OF PRINCIPAL COMPONENT ALGORITHMS NEURAL NETWORKS, 8 (1). pp. 11-23.

[img]
Preview
Text
Plumbley95-nn_accepted_notice.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (414kB) | Preview
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

Recent theoretical analyses of a class of unsupervized Hebbian principal component algorithms have identified its local stability conditions. The only locally stable solution for the subspace P extracted by the network is the principal component subspace P∗. In this paper we use the Lyapunov function approach to discover the global stability characteristics of this class of algorithms. The subspace projection error, least mean squared projection error, and mutual information I are all Lyapunov functions for convergence to the principal subspace, although the various domains of convergence indicated by these Lyapunov functions leave some of P-space uncovered. A modification to I yields a principal subspace information Lyapunov function I′ with a domain of convergence that covers almost all of P-space. This shows that this class of algorithms converges to the principal subspace from almost everywhere.

Item Type: Article
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
AuthorsEmailORCID
PLUMBLEY, MDUNSPECIFIEDUNSPECIFIED
Date : 1 January 1995
Identification Number : https://doi.org/10.1016/0893-6080(95)91644-9
Copyright Disclaimer : © 1995. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
Uncontrolled Keywords : Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE, NEUROSCIENCES, NEURAL NETWORKS, UNSUPERVIZED LEARNING, PRINCIPAL COMPONENT ANALYSIS, INFORMATION THEORY, HEBBIAN ALGORITHMS, LYAPUNOV FUNCTIONS, OJA RULE
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 02 Nov 2016 17:03
Last Modified : 02 Nov 2016 17:03
URI: http://epubs.surrey.ac.uk/id/eprint/812060

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800