Neuro-fuzzy systems have been in the focus of recent research as a solution
to jointly exploit the main features of fuzzy logic systems and neural net
works. Within the application literature, neuro-fuzzy systems can be found
as methods for function identification. This approach is supported by theor
ems that guarantee the possibility of representing arbitrary functions by f
uzzy systems. However, due to the fact that real data are often noisy, gene
ration of accurate identifiers is presented as an important problem. Within
the Adaptive Resonance Theory (ART), PROBART architecture has been propose
d as a solution to this problem. After a detailed comparison of these archi
tectures based on their design principles, the FasArt and FasBack models ar
e proposed. They are neuro-fuzzy identifiers that offer a dual interpretati
on, as fuzzy logic systems or neural networks. FasArt and FasBack can be tr
ained on noisy data without need of change in their structure or data prepr
ocessing. In the simulation work, a comparative study is carried out on the
performances of Fuzzy ARTMAP, PROBART. FasArt and FasBack, focusing on pre
diction error and network complexity. Results show that FasArt and FasBack
clearly enhance the performance of other models in this important problem.
(C) 2001 Elsevier Science Ltd. All rights reserved.