Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s): Carpenter, G.A. | Gjaja, N.M. |
Year: 1994
Citation: Proceedings of the World Congress on Neural Networks (WCNN 94), Hillsdale, NJ: Lawrence Erlbaum Associates, I 713-722.
Abstract: Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART and supervised fuzzy ARTMAP networks synthesize fuzzy logic and ART by exploiting the formal similarity between the computations of fuzzy subsethood and the dynamics of ART category choice, search, and learning. Fuzzy ART self-organizes stable recognition categories in response to arbitrary sequences of analog or binary input patterns. It generalizes the binary ART 1 model, replacing the set-theoretic intersection with the fuzzy intersection, or component-wise minimum. A normalization procedure called complement coding leads to a symmetric theory in which the fuzzy intersection and the fuzzy union, or component-wise maximum, play complementary roles. A geometric interpretation of fuzzy ART represents each category as a box that increases in size as weights decrease. This paper analyzes fuzzy ART models that employ various choice functions for category selection. One such function minimizes total weight change during learning. Benchmark simulations compare performance of fuzzy ARTMAP systems that use different choice functions.
Topics:
Machine Learning,
Mathematical Foundations of Neural Networks,
Models:
ART 2 / Fuzzy ART,
Fuzzy ARTMAP,
