Title :
Multiple categorization using fuzzy ART
Author :
Lavoie, Pierre ; Crespo, Jean-François ; Savaria, Yvon
Author_Institution :
Defence Res. Establ., Ottawa, Ont., Canada
Abstract :
The internal competition between categories in the fuzzy adaptive resonance theory (ART) neural model can be biased by replacing the original choice function with one that contains a tuning parameter under external control. The competition can be biased, so that, for example, categories of a desired size can be favored. This attentional tuning mechanism allows recalling for a same input different categories under different circumstances, even when no additional learning tabes place. A new tuning parameter is unnecessary, since the readily available vigilance parameter can control both attentional tuning and vigilance. The modified fuzzy ART has the self-stabilization property for analog inputs, whether vigilance is fixed or variable
Keywords :
ART neural nets; category theory; fuzzy neural nets; search problems; unsupervised learning; attentional tuning mechanism; fuzzy ART; fuzzy adaptive resonance theory neural model; internal competition; multiple categorization; recall; self-stabilization property; vigilance parameter; Adaptive control; Adaptive filters; Business; Fuzzy control; Humans; Information processing; Neural networks; Programmable control; Resonance; Subspace constraints;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614203