Cj. Harris et al., ADVANCES IN NEUROFUZZY ALGORITHMS FOR REAL-TIME MODELING AND CONTROL, Engineering applications of artificial intelligence, 9(1), 1996, pp. 1-16
This paper reviews the architecture, representation capability, traini
ng and learning ability of a class of adaptive neurofuzzy systems for
real-time modelling and control of unknown nonlinear dynamic processes
. Issues relating to learning stability, training laws and parametric
convergence, network conditioning, gradient noise, the curse of dimens
ionality associated with associative memory networks, automatic networ
k construction algorithms, and a series of neurofuzzy control design l
aws, are discussed, together with future critical research issues asso
ciated with neurofuzzy systems.