Show simple item record

dc.contributor.authorCarpenter, Gail A.en_US
dc.contributor.authorGaddam, Sai Chaitanyaen_US
dc.date.accessioned2011-11-14T18:17:09Z
dc.date.available2011-11-14T18:17:09Z
dc.date.issued2009-04en_US
dc.identifier.urihttp://hdl.handle.net/2144/1967
dc.description.abstractMemories in Adaptive Resonance Theory (ART) networks are based on matched patterns that focus attention on those portions of bottom-up inputs that match active top-down expectations. While this learning strategy has proved successful for both brain models and applications, computational examples show that attention to early critical features may later distort memory representations during online fast learning. For supervised learning, biased ARTMAP (bARTMAP) solves the problem of over-emphasis on early critical features by directing attention away from previously attended features after the system makes a predictive error. Small-scale, hand-computed analog and binary examples illustrate key model dynamics. Twodimensional simulation examples demonstrate the evolution of bARTMAP memories as they are learned online. Benchmark simulations show that featural biasing also improves performance on large-scale examples. One example, which predicts movie genres and is based, in part, on the Netflix Prize database, was developed for this project. Both first principles and consistent performance improvements on all simulation studies suggest that featural biasing should be incorporated by default in all ARTMAP systems. Benchmark datasets and bARTMAP code are available from the CNS Technology Lab Website: http://techlab.bu.edu/bART/.en_US
dc.description.sponsorshipSyNAPSE program of the Defense Advanced Projects Research Agency (Hewlett-Packard Company, subcontract under DARPA prime contract HR0011-09-3-0001; HRL Laboratories LLC, subcontract #801881-BS under DARPA prime contract HR0011-09-C-0001); Science of Learning Centers program of the National Science Foundation (SBE-0354378)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-2009-003en_US
dc.rightsCopyright 2009 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.subjectAdaptive Resonance Theory (ART)en_US
dc.subjectARTen_US
dc.subjectARTMAPen_US
dc.subjectFeatural biasingen_US
dc.subjectSupervised learningen_US
dc.subjectTop-down/bottom-up interactionsen_US
dc.titleBiased ART: A Neural Architecture that Shifts Attention Toward Previously Disregarded Features Following an Incorrect Predictionen_US
dc.typeTechnical Reporten_US
dc.rights.holderBoston University Trusteesen_US


Files in this item

This item appears in the following Collection(s)

Show simple item record