Show simple item record

dc.contributor.authorCarpenter, Gail A.en_US
dc.contributor.authorGrossberg, Stephenen_US
dc.contributor.authorMarkuzon, Natalyaen_US
dc.contributor.authorReynolds, John H.en_US
dc.contributor.authorRosen David B.en_US
dc.date.accessioned2011-11-14T18:21:48Z
dc.date.available2011-11-14T18:21:48Z
dc.date.issued1991-08
dc.identifier.urihttps://hdl.handle.net/2144/2071
dc.description.abstractA new neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors. The architecture, called Fuzzy ARTMAP, achieves a synthesis of fuzzy logic and Adaptive Resonance Theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Fuzzy ARTMAP also realizes a new Minimax Learning Rule that conjointly minimizes predictive error and maximizes code compression, or generalization. This is achieved by a match tracking process that increases the ART vigilance parameter by the minimum amount needed to correct a predictive error. As a result, the system automatically learns a minimal number of recognition categories, or "hidden units", to met accuracy criteria. Category proliferation is prevented by normalizing input vectors at a preprocessing stage. A normalization procedure called complement coding leads to a symmetric theory in which the MIN operator (Λ) and the MAX operator (v) of fuzzy logic play complementary roles. Complement coding uses on-cells and off-cells to represent the input pattern, and preserves individual feature amplitudes while normalizing the total on-cell/off-cell vector. Learning is stable because all adaptive weights can only decrease in time. Decreasing weights correspond to increasing sizes of category "boxes". Smaller vigilance values lead to larger category boxes. Improved prediction is achieved by training the system several times using different orderings of the input set. This voting strategy can also be used to assign probability estimates to competing predictions given small, noisy, or incomplete training sets. Four classes of simulations illustrate Fuzzy ARTMAP performance as compared to benchmark back propagation and genetic algorithm systems. These simulations include (i) finding points inside vs. outside a circle; (ii) learning to tell two spirals apart; (iii) incremental approximation of a piecewise continuous function; and (iv) a letter recognition database. The Fuzzy ARTMAP system is also compared to Salzberg's NGE system and to Simpson's FMMC system.en_US
dc.description.sponsorshipBritish Petroleum (89-A-1204); Defense Advanced Research Projects Agency (90-0083); National Science Foundation (IRI 90-00530); Office of Naval Research (N00014-91-J-4100); Air Force Office of Scientific Research (90-0175)en_US
dc.language.isoen_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-1991-016
dc.rightsCopyright 1991 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.titleFuzzy ARTMAP: A Neural Network Architecture for Incremental Supervised Learning of Analog 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