Title :
Neural network controller using autotuning method for nonlinear functions
Author :
Yamada, Takayuki ; Yabuta, Tetsuro
Author_Institution :
NTT Telecommun. Field Syst., R&D Center, Ibaraki, Japan
fDate :
7/1/1992 12:00:00 AM
Abstract :
An autotuning method for the optimum sigmoid function of neural networks is proposed. It is based on the steepest descent method. Simulated results using a learning-type direct controller confirm both the practicality and the characteristics of the autotuning method
Keywords :
learning systems; neural nets; self-adjusting systems; autotuning; learning systems; learning-type direct controller; neural network controllers; nonlinear functions; optimum sigmoid function; Control systems; Convergence; Cost function; Design methodology; Difference equations; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Robots; Shape;
Journal_Title :
Neural Networks, IEEE Transactions on
