Citation: In M.A. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks, Second Edition, Cambridge, MA: MIT Press, 87-90.
Abstract: Principles derived from an analysis of experimental literatures in vision, speech, cortical development, and reinforcement learning, including attentional blocking and cognitive-emotional interactions, led to the introduction of adaptive resonance as a theory of human cognitive information processing (Grossberg, 1976). The theory has evolved as a series of real-time neural network models that perform unsupervised and supervised learning, pattern recognition, and prediction (Duda, Hart, and Stork, 2001; Levine, 2000). Models of unsupervised learning include ART1 (Carpenter and Grossberg, 1987) for binary input patterns and fuzzy ART (Carpenter, Grossberg, and Rosen, 1991) for analog input patterns. ARTMAP models (Carpenter et al., 1992) combine two unsupervised modules to carry out supervised learning. Many variations of the basic supervised and unsupervised networks have since been adapted for technological applications and biological analyses.