Author: Guszti Bartfai
Source: GZipped PostScript (86kb); Adobe PDF (335kb)
This article analyses the match tracking anomaly (MTA) of the ARTMAP neural network. The anomaly arises when an input pattern exactly matches its category prototype that the network has previously learned, and the network generates a prediction (through a previously learned associative link) that contradicts the output category that was selected upon presentation of the corresponding target output. Carpenter at al. claimed that such anomalous situation will never arise if the (binary) input vectors have the same number of 1's [Carpenter 91b].
This paper shows that such situations can in fact occur. The timing according to which inputs are presented to the network in each learning trial is crucial: if the target output is presented to the network before the corresponding input pattern, certain pattern sequences will lead the network to the MTA. Two kinds of MTA are distinguished: one that is independent of the choice parameter (beta) of the ARTb module, and another that is not. Results of experiments that were carried out on a machine learning database demonstrate the existence of the match tracking anomaly as well as support the analytical results presented here.