Show simple item record

dc.contributor.authorWilliamson, James R.en_US
dc.date.accessioned2011-11-14T18:49:16Z
dc.date.available2011-11-14T18:49:16Z
dc.date.issued1995-02en_US
dc.identifier.urihttps://hdl.handle.net/2144/2180
dc.description.abstractA new neural network architecture for incremental supervised learning of analalog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, is a synthesis of a Gaussian classifier and an Adaptive Resonance Theory (ART) neural network, achieved by defining the ART choice function as the discriminant function of a Gaussian classifer with separable distributions, and the ART match function as the same, but with the a priori probabilities of the distributions discounted. While Gaussian ARTMAP retains the attractive parallel computing and fast learning properties of fuzzy ARTMAP, it learns a more efficient internal representation of a mapping while being more resistant to noise than fuzzy ARTMAP on a number of benchmark databases. Several simulations are presented which demonstrate that Gaussian ARTMAP consistently obtains a better trade-off of classification rate to number of categories than fuzzy ARTMAP. Results on a vowel classiflcation problem are also presented which demonstrate that Gaussian ARTMAP outperforms many other classifiers.en_US
dc.description.sponsorshipNational Science Foundation (IRI 90-00530); Office of Naval Research (N00014-92-J-4015, 40014-91-J-4100)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-1995-003en_US
dc.rightsCopyright 1995 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.subjectPattern recognitionen_US
dc.subjectAdaptive Resonance Theory (ART)en_US
dc.subjectARTMAPen_US
dc.subjectIncremental learningen_US
dc.subjectSelf-organizationen_US
dc.subjectNoisy dataen_US
dc.subjectGaussian classifieren_US
dc.subjectRadial basis functionen_US
dc.titleGaussian Artmap: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Mapsen_US
dc.typeTechnical Reporten_US
dc.rights.holderBoston University Trusteesen_US


This item appears in the following Collection(s)

Show simple item record