Single net indirect learning architecture
- 1 January 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 5 (6) , 1003-1005
- https://doi.org/10.1109/72.329701
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
This publication has 4 references indexed in Scilit:
- Forward models: Supervised learning with a distal teacherCognitive Science, 1992
- An adaptive control for CARMA systems using linear neural networksInternational Journal of Control, 1992
- Back-propagation neural networks for nonlinear self-tuning adaptive controlIEEE Control Systems Magazine, 1990
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988