A logical architecture for supervised learning

Summary form only given, as follows. The author discusses a neural network architecture for supervised learning with inherent stability properties. The architecture employs two ART 1 (adaptive resonance theory) unsupervised systems with supervision through interconnects. The supervised learning system, trained in a particular manner, responds properly to the training set of patterns and responds to novel inputs in a well-defined manner. A formal model characterizes the network in a system of logic. This system has potential applications in multisensor analysis, adaptive control, and neural network knowledge systems.<<ETX>>