Neural network architectures for learning, prediction, and probability estimation

摘要: A new neural network architecture, called ARTMAP, is developed for incremental, nonparametric, supervised learning of recognition categories, multidimensional maps, and probability estimates. ARTMAP extends Adaptive Resonance Theory (ART) into the domain of supervised learning by incorporating environmental feedback and associative learning into the ART learning processes. Tested on benchmark classification problems such as distinguishing poisonous and edible mushrooms based on their visual features, ARTMAP outperforms a variety of systems in terms of speed, accuracy, and code compression. ARTMAP is also successfully applied to the incremental approximation of piecewise continuous functions, and to three probability estimation problems. The ARTMAP network includes a pair of Adaptive Resonance Theory modules, ART and ART During training, input patterns are presented to ART and output …