Graded Signal Functions for ARTMAP Neural Networks
OA Version
Citation
Abstract
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.
Description
License
Copyright 2000 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.