Adaptive Resonance Theory: Stable Self-Organization of Neural Recognition Codes In Response to Arbitrary Lists of Input Patterns
Year: 1986
Type: article
Abstract: A neural network, called an adaptive resonance theory (ART) architecture, for the learning of recognition categories is described herein.Real-time network dynamics for this model have been completely characterized through mathematical analysis and computer simulations.The architecture self-organizes and self-stabilizes its recognition codes in response to arbitrary orderings of arbitrarily many and arbitrarily complex binary input patterns.Top-down attentional and matching mechanisms are critical in self-stabilizing the code learning process.The architecture embodies a parallel search scheme which updates itself adaptively as the learning process unfolds.After learning self-stabilizes, the search process is automatically disengaged.Thereafter input patterns directly access their recognition codes without any search.Thus recognition time does not grow as a function of code complexity.A novel input pattern can directly access a category if it shares invariant properties with the set of familiar exemplars of that category.These invariant properties emerge in the form of learned critical feature patterns, or prototypes.The architecture possesses a context-sensitive self-scaling property which enables its emergent critical feature patterns to form.They detect and remember statistically predictive configurations of featural elements which are derived from the set of all input patterns that are ever experit Supported in part by the Air Force Office of Scientific Research (
Authors: Carpenter, Gail A., Grossberg, Stephen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G177218894
OpenAlex ID: W7026287455