3-D Object Recognition by the ART-EMAP Evidence Accumulation Network


Autoria(s): Carpenter, Gail A.; Ross, William D.
Data(s)

14/11/2011

14/11/2011

01/11/1993

Resumo

ART-EMAP synthesizes adaptive resonance theory (AHT) and spatial and temporal evidence integration for dynamic predictive mapping (EMAP). The network extends the capabilities of fuzzy ARTMAP in four incremental stages. Stage I introduces distributed pattern representation at a view category field. Stage 2 adds a decision criterion to the mapping between view and object categories, delaying identification of ambiguous objects when faced with a low confidence prediction. Stage 3 augments the system with a field where evidence accumulates in medium-term memory (MTM). Stage 4 adds an unsupervised learning process to fine-tune performance after the limited initial period of supervised network training. Simulations of the four ART-EMAP stages demonstrate performance on a difficult 3-D object recognition problem.

Advanced Research Projects Agency (ONR N00014-92-J-4015); National Science Foundation (IRI-90-00530); Office of Naval Research (N00014-91-J-1309); Air Force Office of Scientific Research (90-0083)

Identificador

http://hdl.handle.net/2144/2041

Publicador

Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems

Relação

BU CAS/CNS Technical Reports;CAS/CNS-TR-1993-064

Direitos

Copyright 1993 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.

Boston University Trustees

Tipo

Technical Report