%0 Journal Article
%T Flagged and Compact Fuzzy ART: Fuzzy ART in more efficient forms
%A Kamal R. Al-Rawi
%A Consuelo Gonzalo
%J International Journal of ACM Jordan
%D 2010
%I ACM Jordan ISWSA Professional Chapter
%X Two new simplified algorithms for Fuzzy ART have been developed. Onlycommitted category nodes C rather than the full capacity of the category nodes N (N>>C) are involved in the determination of the winning categoy node. In addition tothat, the initialization for weights and choice values has been eliminated.This reduces a lot the training time without altering the categorazation accuracy.Although, the new architectures are presented toward the fuzzy ART ANN in this work.However, they can be applied to all module of ART.
%K Compact fuzzy ART
%K Flagged fuzzy ART
%K ART ANN
%K Unsupervised ART
%K Unsupervised learning
%U http://iswsa2010.acm.org/volumes/volume1/no3/ijjvol1no3p10.pdf