Title :
Neural networks in control systems
Author :
S. Saksida;F. Bremsak
Author_Institution :
Fac. of Electr. & Comput. Eng., Ljubljana Univ., Yugoslavia
fDate :
6/13/1905 12:00:00 AM
Abstract :
A modified backpropagation algorithm with a linear output function is discussed from the viewpoint of its convenience in control tasks. Two methods are presented for teaching neural networks to act as an inverse plant. In the simulation example a discrete integrator was used as the plant. The best results were obtained by a combination of both methods.
Keywords :
"Neural networks","Intelligent networks","Control systems","Neurons","Artificial neural networks","Pattern recognition","Transfer functions","Backpropagation algorithms","Signal generators","H infinity control"
Conference_Titel :
Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean
Print_ISBN :
0-87942-655-1
DOI :
10.1109/MELCON.1991.161966
