DocumentCode :
2972061
Title :
A neural network controller based on autotuning the gain of the activation function
Author :
Song, Kai-Tai ; Shieh, Jang-Hang
Author_Institution :
Inst. of Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Volume :
3
fYear :
1993
fDate :
25-29 Oct. 1993
Firstpage :
2787
Abstract :
A design of neural network controller based on autotuning the gain of the activation function of neurons is accomplished. Such a gain-tuning procedure is combined with the conventional weight-tuning backpropagation algorithm in the learning phase to provide more efficient and faster learning of a neural network. Satisfactory results are obtained when using this method to control a nonlinear plant.
Keywords :
backpropagation; neurocontrollers; nonlinear control systems; tuning; activation function; autotuning; gain-tuning procedure; neural network controller; nonlinear plant; weight-tuning backpropagation algorithm; Artificial neural networks; Control engineering; Cost function; Learning systems; Neural networks; Neurons; Performance gain; Predictive models; Servomechanisms; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
Type :
conf
DOI :
10.1109/IJCNN.1993.714302
Filename :
714302
Link To Document :
بازگشت