Multiple categorization using fuzzy ART
Pierre Lavoie, J.-F. Crespo, Yvon Savaria · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
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.