Multi-Dimensional Locally Generalizing Neural Networks for Real Time Control
Multi-Dimensional Locally Generalizing Neural Networks for Real Time Control
Based on the fast learning convergence properties of networks with local generalization (compared to multi-layered networks with global learning interference and possible multi-minima), this paper reviews three locally generalizing neural networks: Radial Basis Functions (RBF), B-Splines (BSPL), and Cerebellar Model Articulated Controller (CMAC). In specific, the learning performance of the CMAC network was evaluated using a non-linear time series with four inputs and two outputs, and compared to those using RBF (Chen, Billings (1991)) and B-Splines (Brown, Harris (1991)). In relation to real-time control tasks, either the plant derivative (or jacobian) or an approximated version of the jacobian is required if the controller is adjusted based on an instantaneous tracking error (instead of the control error). This way the controller becomes sensitive to the estimated plant jacobian. This paper also studies the ability of the CMAC network to approximate a plant made of multi-sinusoids, and estimate the plant jacobian based on the approximated plant model.
741-750
An, P.E.
5dc94657-d009-4d13-9a0f-6645a9d296d9
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
1992
An, P.E.
5dc94657-d009-4d13-9a0f-6645a9d296d9
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
An, P.E. and Harris, C.J.
(1992)
Multi-Dimensional Locally Generalizing Neural Networks for Real Time Control.
Artificial Intelligence and Real Time Control.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
Based on the fast learning convergence properties of networks with local generalization (compared to multi-layered networks with global learning interference and possible multi-minima), this paper reviews three locally generalizing neural networks: Radial Basis Functions (RBF), B-Splines (BSPL), and Cerebellar Model Articulated Controller (CMAC). In specific, the learning performance of the CMAC network was evaluated using a non-linear time series with four inputs and two outputs, and compared to those using RBF (Chen, Billings (1991)) and B-Splines (Brown, Harris (1991)). In relation to real-time control tasks, either the plant derivative (or jacobian) or an approximated version of the jacobian is required if the controller is adjusted based on an instantaneous tracking error (instead of the control error). This way the controller becomes sensitive to the estimated plant jacobian. This paper also studies the ability of the CMAC network to approximate a plant made of multi-sinusoids, and estimate the plant jacobian based on the approximated plant model.
This record has no associated files available for download.
More information
Published date: 1992
Additional Information:
Organisation: IFAC Address: Groningen, Netherlands
Venue - Dates:
Artificial Intelligence and Real Time Control, 1992-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250215
URI: http://eprints.soton.ac.uk/id/eprint/250215
PURE UUID: f3a846be-946d-43dd-8c42-af235a6853bd
Catalogue record
Date deposited: 04 May 1999
Last modified: 10 Dec 2021 20:07
Export record
Contributors
Author:
P.E. An
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