The ART of adaptive pattern recognition by a self-organizing neural network
The Adaptive Resonance Theory (ART) architectures discussed here are neural networks that self-organize stable recognition codes in real time in response to arbitrary sequences of input patterns. Within such an ART architecture, the process of adaptive pattern recognition is a special case of the more general cognitive process of hypothesis discovery, testing, search, classification, and learning. This property opens up the possibility of applying ART systems to more general problems of adaptively processing large abstract information sources and databases. This article outlines the main computational properties of these ART architectures, while comparing and contrasting these properties with those of alternative learning and recognition systems. Technical details are described in greater detail elsewhere, and several books collect articles in which the theory was developed through the analysis and prediction of interdisciplinary data about the brain and behavior.
- Research Organization:
- Boston Univ. (US)
- OSTI ID:
- 5299331
- Journal Information:
- Computer; (United States), Vol. 21:3
- Country of Publication:
- United States
- Language:
- English
Similar Records
Adaptive pattern recognition and neural networks
Feature discovery via neural networks for object recognition in SAR imagery
Related Subjects
ARTIFICIAL INTELLIGENCE
BIOLOGICAL MODELS
COMPUTER ARCHITECTURE
PATTERN RECOGNITION
COMPARATIVE EVALUATIONS
COMPUTER CALCULATIONS
HUMAN FACTORS ENGINEERING
LEARNING
REAL TIME SYSTEMS
ENGINEERING
990210* - Supercomputers- (1987-1989)