Show simple item record

dc.contributor.authorKopco, Norberten_US
dc.contributor.authorCarpenter, Gailen_US
dc.date.accessioned2011-11-14T19:00:17Z
dc.date.available2011-11-14T19:00:17Z
dc.date.issued2000-03en_US
dc.identifier.urihttps://hdl.handle.net/2144/2254
dc.description.abstractThis 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.en_US
dc.description.sponsorshipOffice of Naval Research and the Defense Advanced Research Projects Agency (N00014-95-1-0409, N00014-1-95-0657)en_US
dc.language.isoen_USen_US
dc.publisherBoston University Center for Adaptive Systems and Department of Cognitive and Neural Systemsen_US
dc.relation.ispartofseriesBU CAS/CNS Technical Reports;CAS/CNS-TR-2000-006en_US
dc.rightsCopyright 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.en_US
dc.subjectARTMAP
dc.subjectFast learning
dc.subjectGraded signal function
dc.subjectNeural networks
dc.titleGraded Signal Functions for ARTMAP Neural Networksen_US
dc.typeTechnical Reporten_US
dc.rights.holderBoston University Trusteesen_US


This item appears in the following Collection(s)

Show simple item record