An improved learning algorithm for the fuzzy ARTMAP neural network

Abstract

This article introduces two improvements to the learning algorithm of the fuzzy ARTMAP neural network. One of them is concerned with the timing according to which input patterns and their corresponding target output are processed by the network. The other one is the explicit overwriting of an existing association between an input and an output category in case the input is matched perfectly and yet the network's prediction is wrong. Both of these modifications are needed to reduce the occurrence of the "match tracking anomaly" (or MTA) during learning, and eliminate MTA altogether in a trained network. As a result, training time is also reduced, which is demonstrated through the performance of the network on a machine learning benchmark database.