Default ARTMAP 2

Default ARTMAP combines winner-take-all category node activation during training, distributed activation during testing, and a set of default parameter values that define a ready-to-use, general-purpose neural network system for supervised learning and recognition. Winner-take-all ARTMAP learning is designed so that each input would make a correct prediction if re-presented immediately after its training presentation, passing the "next-input test." Distributed activation has been shown to improve test set prediction on many examples, but an input that made a correct winner-take-all prediction during training could make a different prediction with distributed activation. Default ARTMAP 2 introduces a distributed next-input test during training. On a number of benchmarks, this additional feature of the default system increases accuracy without significantly decreasing code compression. This paper includes a self-contained default ARTMAP 2 algorithm for implementation.

[1]  Paulo J,et al.  Industrial use of safety-related artificial neural networks , 2001 .

[2]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[3]  James R. Williamson,et al.  Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps , 1996, Neural Networks.

[4]  Michael Anderson,et al.  NIRS: Large scale ART-1 neural architectures for engineering design retrieval , 1994, Neural Networks.

[5]  Gail A. Carpenter,et al.  Distributed ARTMAP: a neural network for fast distributed supervised learning , 1998, Neural Networks.

[6]  Gail A. Carpenter,et al.  ART-EMAP: A neural network architecture for object recognition by evidence accumulation , 1995, IEEE Trans. Neural Networks.

[7]  S. Grossberg.  How does the cerebral cortex work? Development, learning, attention, and 3-D vision by laminar circuits of visual cortex. , 2003, Behavioral and cognitive neuroscience reviews.

[8]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[9]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[10]  Gail A. Carpenter,et al.  Fuzzy ART Choice Functions , 1993 .

[11]  Gail A. Carpenter,et al.  ARTMAP-IC and medical diagnosis: Instance counting and inconsistent cases , 1998, Neural Networks.

[12]  S. Grossberg.  The Link between Brain Learning, Attention, and Consciousness , 1999, Consciousness and Cognition.

[13]  G. Carpenter.  Default ARTMAP , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[14]  Gail A. Carpenter,et al.  ARTMAP neural networks for information fusion and data mining: map production and target recognition methodologies , 2003, Neural Networks.

[15]  Gail A. Carpenter,et al.  Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks , 1997, Neural Networks.

[16]  Gail A. Carpenter,et al.  Self-organizing information fusion and hierarchical knowledge discovery: a new framework using ARTMAP neural networks , 2005, Neural Networks.

[17]  Allen M. Waxman,et al.  Fused multi-sensor image mining for feature foundation data , 2000, Proceedings of the Third International Conference on Information Fusion.