Title :
Single net indirect learning architecture
Author :
Andersen, H.C. ; Teng, F.C. ; Tsoi, A.C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Queensland Univ., Brisbane, Qld., Australia
fDate :
11/1/1994 12:00:00 AM
Abstract :
This paper presents a novel indirect learning architecture which uses a single neural network in implementation. The new architecture generates the error signal required in training the controller network by an innovative design using a memory element and few switches. The new controller needs only half the number of neurons and connection weights in comparison with the original indirect learning architecture. Also given are the simulation results in controlling a nonlinear plant
Keywords :
intelligent control; learning systems; neural nets; nonlinear systems; error signal; memory element; neural network; nonlinear plant control; single net indirect learning architecture; Adaptive control; Artificial neural networks; Australia Council; Control systems; Error correction; Neural networks; Neurons; Signal design; Signal generators; Switches;
Journal_Title :
Neural Networks, IEEE Transactions on
