Title :
Neurofuzzy networks for online modelling and control with provable learning and stability conditions
Author :
Harris, C.J. ; Brown, M.
Author_Institution :
Dept. of Aeronaut. & Astronaut., Southampton Univ., UK
Abstract :
This paper considers a wide class of basis associative memory networks and their learning and network conditioning for online modelling and control. It is shown that the networks parameter convergence rate, stability, and gradient noise all depend upon the condition number C(R) of the basis function autocorrelation function R. This analysis shows that for online modelling networks should be locally generalising and have condition number tending to unity
Keywords :
content-addressable storage; correlation methods; fuzzy neural nets; generalisation (artificial intelligence); learning (artificial intelligence); neurocontrollers; stability; basis associative memory networks; basis function autocorrelation function; condition number; gradient noise; local generalisation; neurofuzzy networks; online control; online modelling; parameter convergence rate; provable learning conditions; stability conditions; Associative memory; Autocorrelation; Convergence; Fuzzy logic; Intelligent networks; Magnesium compounds; Nonlinear systems; Safety; Spline; Stability analysis;
Conference_Titel :
Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-2129-4
DOI :
10.1109/ICSMC.1994.400053
