DocumentCode :
288704
Title :
Universal neural controllers
Author :
Chen, Cheng-Liang ; Chang, Feng-Yung
Author_Institution :
Dept. of Chem. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Volume :
4
fYear :
1994
fDate :
27 Jun-2 Jul 1994
Firstpage :
2592
Abstract :
A collection Γ of a neural controller is a universal neural controller if and only if any given controllable process P can also be controlled by a specific neural controller in Γ. Given any continuous real valued function on a compact set, we show that the collection Γ of the inverse Gaussian and the Gaussian potential function neural controllers (IGFNC, GPFNC) that will approximate the given function to any degree of accuracy. An application of this result shows that this type of radial basis function neural controller (RBFNC) is a universal neural controller. Hence, any given controllable process can be controlled by this RBFNC operating simultaneously
Keywords :
feedforward neural nets; intelligent control; neurocontrollers; Gaussian potential function neural controllers; inverse Gaussian; radial basis function neural net; universal neural controllers; Feedforward neural networks; Integral equations; Multi-layer neural network; Multilayer perceptrons; Neural networks; Process control; Radial basis function networks; Shape; Transfer functions;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
Type :
conf
DOI :
10.1109/ICNN.1994.374629
Filename :
374629
Link To Document :
بازگشت