| | |
Summary: NetworksinControlSystems
The state of the art inthearea of neural
networks in control systems is reflected in this
specialissue.Theneed to meetdemanding
control requirements in increasingly complex
dynamicalcontrolsystemsundersignificant
uncertainties makes neural networks very at-
tractive,because of theirabilitytolearn.to
approximatefunctions?toclassifypatterns
and because of theirpotentialformassively
parallel hardware implementation. Neural net-
works do appear to be ableto implement many
functionsessential to controlsystemswith
higher degreeof autonomy.
This isthesecond special issueof thelEEE
Control Systems Muquzine devoted to Neural
'Networks in Control Systems; the first special
issue was two years ago: in April1990 [I]. In
fact. this is the fourth issue of the Magazine
with a collection of articles specifically aimed
|
