Interactions in an art neural system
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This work continues a series of papers about a neural network that incorporates adaptive resonance theory (ART) as a system of ordinary differential equations. The original, Exact ART, requires huge computational resources even for small-scale tasks. However, for technological applications it is necessary to devise more efficient computing algorithms. Here we propose simplifications of the original subsystem responsible for bottom-up and top-down data matching. In effect we formulate and solve a substitution problem that preserves only those features, which are essential for the overall system dynamics.
Abstract
This work continues a series of papers about a neural network that incorporates adaptive resonance theory (ART) as a system of ordinary differential equations. The original, Exact ART, requires huge computational resources even for small-scale tasks. However, for technological applications it is necessary to devise more efficient computing algorithms. Here we propose simplifications of the original subsystem responsible for bottom-up and top-down data matching. In effect we formulate and solve a substitution problem that preserves only those features, which are essential for the overall system dynamics.
참고문헌 (8)
- Carpenter, G.A., "ART-2: Self-organization of stable category recognition codes for analog input patterns", Applied Optics, 26, pp.4919~4930 (1988)
- Carpenter, G.A., "Adaptive resonance theory;The Handbook of Brain Theory and Neural Networks" (2002), MIT Press
- Georgiev, K., "Efficient orienting subsystem in an adaptive resonance theory (ART) neural network", Proceedings of the Bulgarian Academy of Sciences, pp.531~536 (2005)
- Grossberg, S., "Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors. Biological Cybernetics 23, 121-134. II. Feedback, expectation, olfaction, and illusions", Biological Cybernetics, 23, pp.187~202 (1976)
- Grossberg, S., "How does a brain build a cognitive code?", Psychological Review, 87, pp.1~51 (1980)
- Mengov, G., "Modelling neural signals with a generalized net", Advanced Studies in Contemporary Mathematics, 7(2), pp.155~166 (2003)
- Mengov, G., "Analytical solution of the resonance in an adaptive resonance theory (ART) neural system", Advanced Studies in Contemporary Mathematics, 10(1), pp.45~52 (2005)
- Raijmakers, M., "Exact ART: A complete implementation of an ART network", Neural Networks, 10(4), pp.649~669 (1997)