Title :
Neural net versus control theory
Author :
Jin, Yichuang ; Pipe, Tony
Author_Institution :
Dept. of Eng., Bristol Polytech., UK
Abstract :
The authors present some results on neural controllers. They summarize five neural controller architectures, which can be divided into two classes: general learning and special learning. In the general learning architecture examples, one neural net is trained to simulate the PUMA 560 inverse kinematics and another neural net is used to control the PUMA 560 writing in chalk. The authors then use control theory to analyze special learning architectures. It is found that a simple PID (proportional plus integral plus derivative) controller can provide a momentum factor in backpropagation (BP) learning laws. However, it is found that momentum may make BP convergence unstable, but that one can redesign the PID controller to avoid this problem
Keywords :
control system analysis; controllers; kinematics; learning systems; neural nets; robots; three-term control; PID; PUMA 560 inverse kinematics; backpropagation; control system analysis; control theory; general learning; momentum factor; neural controller architectures; robots; special learning; three term control; writing; Backpropagation; Control theory; Convergence; Kinematics; Neural networks; PD control; Pi control; Proportional control; Three-term control; Writing;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170622