Neurofuzzy networks for online modelling and control with provable learning and stability conditions
Neurofuzzy networks for online modelling and control with provable learning and stability conditions
This paper considers a wide class of basis associative memory networks and their learning and network conditioning for online modelling and control. It is shown that the networks parameter convergence rate, stability and gradient noise all depend upon the condition number C(R) of the basis function autocorrelation function R. This analysis shows that for online modelling networks should be locally generalising and have condition number tending to unity.
1469--1474
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
1994
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
Harris, C.J. and Brown, M.
(1994)
Neurofuzzy networks for online modelling and control with provable learning and stability conditions.
Int. Conf. on Systems, Man, and Cybernetics.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
This paper considers a wide class of basis associative memory networks and their learning and network conditioning for online modelling and control. It is shown that the networks parameter convergence rate, stability and gradient noise all depend upon the condition number C(R) of the basis function autocorrelation function R. This analysis shows that for online modelling networks should be locally generalising and have condition number tending to unity.
This record has no associated files available for download.
More information
Published date: 1994
Additional Information:
Organisation: IEEE Address: San Antonio, Texas
Venue - Dates:
Int. Conf. on Systems, Man, and Cybernetics, 1994-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250265
URI: http://eprints.soton.ac.uk/id/eprint/250265
PURE UUID: 9221b0bb-2b3c-4d89-adf9-03d3d64efbed
Catalogue record
Date deposited: 04 May 1999
Last modified: 10 Dec 2021 20:07
Export record
Contributors
Author:
C.J. Harris
Author:
M. Brown
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics