Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s): Grossberg, S. |
Year: 2000
Citation: In Peter Sinc?k and J?n Vasc?k (Eds.), Quo Vadis Computational Intelligence? New Trends and Approaches in Computational Intelligence. In the series Studies in Fuzziness and Soft Computing, New York: Physica-Verlag, 3-12.
Abstract: ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include airplane design and manufacturing, automatic target recognition, financial forecasting, machine tool monitoring, digital circuit design, chemical analysis, and robot vision. Supervised ART architectures, called ARTMAP systems, feature internal control mechanisms that create stable recognition categories of optimal size by maximizing code compression while minimizing predictive error in an on-line setting. Special-purpose requirements of various application domains have led to a number of ARTMAP variants, including fuzzy ARTMAP, ART-EMAP, Gaussian ARTMAP, and distributed ARTMAP. ARTMAP has been used for a variety of applications, including computer-assisted medical diagnosis. Medical databases present many of the challenges found in general information management settings where speed, efficiency, ease of use, and accuracy are at a premium. A direct goal of improved computer-assisted medicine is to help deliver quality emergency care in situations that may be less than ideal. Working with these problems has stimulated a number of ART architecture developments, including ARTMAP-IC [1]. This paper describes a recent collaborative effort, using a new cardiac care database for system development, has brought together medical statisticians and clinicians at the New England Medical Center with researchers developing expert systems and neural networks, in order to create a hybrid method for medical diagnosis. The paper also considers new neural network architectures, including distributed ART (dART), a real-time model of parallel distributed pattern learning that permits fast as well as slow adaptation, without catastrophic forgetting. Local synaptic computations in the dART model quantitatively match the paradoxical phenomenon of Markram-Tsodyks [2] redistribution of synaptic efficacy, as a consequence of global system hypotheses.
