Generalization, discrimination, and multiple categorization using adaptiveresonance theory

The internal competition between categories in the adaptive resonance theor y (ART) neural model can be biased by replacing the original choice functio n by one that contains an attentional tuning parameter under external contr ol. For the same input but different values of the attentional tuning param eter, the network can learn and recall different categories with different degrees of generality, thus permitting the coexistence of both general and specific categorizations of the same set of data. Any number of these categ orizations can be learned within one and the same network by virtue of gene ralization and discrimination properties. A simple model in which the atten tional tuning parameter and the vigilance parameter of ART are linked toget her is described. The self-stabilization property is shown to be preserved for an arbitrary sequence of analog inputs, and for arbitrary orderings of arbitrarily chosen vigilance levels.