The generalization capabilities of ARTMAP
Gregory L. Heileman, Michael Georgiopoulos, M. J. R. Healy, Stephen Verzi · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
Bounds on the number of training examples needed to guarantee a certain level of generalization performance in the ARTMAP architecture are derived. Conditions are derived under which ARTMAP can achieve a specific level of performance assuming any unknown, but fixed, probability distribution on the training data.