et@eng.cam.ac.uk (Eli Tzirkel-Hancock) (05/03/91)
The following report has been placed in the neuroprose archives at
Ohio State University:
A Direct Control Method For a Class
of Nonlinear Systems Using Neural Networks
Eli Tzirkel-Hancock & Frank Fallside
Technical Report CUED/F-INFENG/TR.65
Cambridge University
Engineering Department
Trumpington Street
Cambridge CB2 1PZ
England
Abstract
A direct control scheme for a class of continuous time nonlinear
systems using neural networks is presented. The objective of the
control is to track a desired reference signal. This objective is
achieved through input/output linearization of the system with neural
networks. Learning, based on a stability type algorithm, takes place
simultaneously with control. As such, the method is closely related
to adaptive control methods. Indeed, the algorithm's properties are
analysed with the aid of adaptive control tools. This analysis provides
an interesting bridge between well studied, adaptive control methods and the
field of neural network training. In particular, the importance of
the property of persistent excitation and its implications to learning
with networks of localized receptive fields is discussed.
************************ How to obtain a copy ************************
a) via FTP:
% ftp cheops.cis.ohio-state.edu
...
Name (cheops.cis.ohio-state.edu:your-id): anonymous
...
Password: neuron
...
ftp> cd pub/neuroprose
...
ftp> binary
...
ftp> get tzirkel.control.ps.Z
...
ftp> quit
% uncompress tzirkel.control.ps.Z
% lp tzirkel.control.ps
b) via postal mail (only if the above is impossible, please)
Request a hardcopy from
Eli Tzirkel-Hancock, et@uk.ac.cam.eng
Speech Laboratory
Cambridge University Engineering Department
Trumpington Street, Cambridge CB2 1PZ
England