ART 2-A: an adaptive resonance algorithm for rapid category learning and recognition

The authors introduce ART 2-A, an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders of magnitude faster. Analysis and simulation show how the ART 2-A systems correspond to ART 2 dynamics both at the fast-learn limit and at intermediate learning rates. Intermediate learning rates permit fast commitment of category nodes but slow recoding, analogous to properties of word frequency effects, encoding specificity effects, and episodic memory. Better noise tolerance is achieved without a loss of learning stability. The speed of ART 2-A makes practical the use of ART 2 modules in large-scale neural computation