Carpenter, Gail A.Milenova, Boriana L.2011-11-142011-11-141999-05https://hdl.handle.net/2144/2230Distributed coding at the hidden layer of a multi-layer perceptron (MLP) endows the network with memory compression and noise tolerance capabilities. However, an MLP typically requires slow off-line learning to avoid catastrophic forgetting in an open input environment. An adaptive resonance theory (ART) model is designed to guarantee stable memories even with fast on-line learning. However, ART stability typically requires winner-take-all coding, which may cause category proliferation in a noisy input environment. Distributed ARTMAP (dARTMAP) seeks to combine the computational advantages of MLP and ART systems in a real-time neural network for supervised learning. This system incorporates elements of the unsupervised dART model as well as new features, including a content-addressable memory (CAM) rule. Simulations show that dARTMAP retains fuzzy ARTMAP accuracy while significantly improving memory compression. The model's computational learning rules correspond to paradoxical cortical data.en-USCopyright 1999 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.Technical ReportBoston University Trustees