The Modelling Abilities of the Binary CMAC
The Modelling Abilities of the Binary CMAC
The Albus CMAC (Cerebellar Model Articulation Controller), has been widely used for signal processing and adaptive control tasks, although it is only recently that the learning rules have been properly understood and convergence results derived. The CMAC is a multi-dimensional tabular storage scheme which generates piecewise constant models. However, despite its simplicity the modelling capabilities of this network are very complex and many incorrect theories have recently been proposed. The foundations for a correct theory were recently proposed by the authors, and this paper extends these results by showing that the modelling capibilities of different CMACs (varying the generalisation parameter or the overlay displacement vector) are different. It is also shown that the binary CMAC is able to model any additive mapping exactly, but is unable to reproduce a multiplicative function. This is achieved using the consistency equations and orthogonal functions which define the space of functions which a binary CMAC can and cannot model respectively, and they can also be used to generate a lower bound for the network's modelling error.
1335--1339
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
1994
Brown, M.
52cf4f52-6839-4658-8cc5-ec51da626049
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Brown, M. and Harris, C.J.
(1994)
The Modelling Abilities of the Binary CMAC.
Int. Conf. Neural Networks.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
The Albus CMAC (Cerebellar Model Articulation Controller), has been widely used for signal processing and adaptive control tasks, although it is only recently that the learning rules have been properly understood and convergence results derived. The CMAC is a multi-dimensional tabular storage scheme which generates piecewise constant models. However, despite its simplicity the modelling capabilities of this network are very complex and many incorrect theories have recently been proposed. The foundations for a correct theory were recently proposed by the authors, and this paper extends these results by showing that the modelling capibilities of different CMACs (varying the generalisation parameter or the overlay displacement vector) are different. It is also shown that the binary CMAC is able to model any additive mapping exactly, but is unable to reproduce a multiplicative function. This is achieved using the consistency equations and orthogonal functions which define the space of functions which a binary CMAC can and cannot model respectively, and they can also be used to generate a lower bound for the network's modelling error.
This record has no associated files available for download.
More information
Published date: 1994
Additional Information:
Organisation: IEEE Address: Orlando, FL
Venue - Dates:
Int. Conf. Neural Networks, 1994-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250254
URI: http://eprints.soton.ac.uk/id/eprint/250254
PURE UUID: 2bcd8008-57c5-4613-99ef-5ea937bebdd2
Catalogue record
Date deposited: 04 May 1999
Last modified: 10 Dec 2021 20:07
Export record
Contributors
Author:
M. Brown
Author:
C.J. Harris
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