SINGLE NET INDIRECT LEARNING ARCHITECTURE

Authors
ANDERSEN HC TENG FC TSOI AC
Citation
Hc. Andersen et al., SINGLE NET INDIRECT LEARNING ARCHITECTURE, IEEE transactions on neural networks, 5(6), 1994, pp. 1003-1005
Citations number
8
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
5
Issue
6
Year of publication
1994
Pages
1003 - 1005
Database
ISI
SICI code
1045-9227(1994)5:6<1003:SNILA>2.0.ZU;2-R
Abstract
This letter presents a novel indirect learning architecture which uses a single neural network in implementation. The new architecture gener ates the error signal required in training the controller network by a n innovative design using a memory element and few switches. The new c ontroller 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.