Sq. Wu et al., A fast approach for automatic generation of fuzzy rules by generalized dynamic fuzzy neural networks, IEEE FUZ SY, 9(4), 2001, pp. 578-594
In this paper, a fast approach for automatically generating fuzzy rules fro
m sample patterns using generalized dynamic fuzzy neural networks (GD-FNNs)
is presented. The GD-FNN is built based on ellipsoidal basis function and
functionally is equivalent to a Takagi-Sugeno-Kang fuzzy system. The salien
t characteristics of the GD-FNN are: 1) structure identification and parame
ters estimation are performed automatically and simultaneously without part
itioning input space and selecting initial parameters a priori; 2) fuzzy ru
les can be recruited or deleted dynamically; 3) fuzzy rules can be generate
d quickly without resorting to the backpropagation (BP) iteration learning,
a common approach adopted by many existing methods. The GD-FNN is employed
in a wide range of applications ranging from static function approximation
and nonlinear system identification to time-varying drug delivery system a
nd multilink robot control. Simulation results demonstrate that a compact a
nd high-performance fuzzy rule-base can be constructed. Comprehensive compa
risons with other latest approaches show that the proposed approach is supe
rior in terms of learning efficiency and performance.