Graded Signal Functions for ARTMAP Neural Networks
MetadataShow full item record
This study presents an analysis of a modified ARTMAP neural network in which a graded signal function replaces the standard choice-by-difference function. The modifications are introduced mathematically and the performance of the system is studied on two benchmark examples. It is shown that the modified ARTMAP system achieves classification accuracy superior to that of standard ARTMAP, while retaining comparable complexity of the internal code.