2518-1092Research result. Information technologies2518-109210.18413/2518-1092-2016-1-1-4-1125COMPUTER SIMULATIONNEW ARCHITECTURES AND ALGORITMS OF TRAINING THE ADAPTIVE RESONANCE THEORY TO NEURAL NETWORKSNEW ARCHITECTURES AND ALGORITMS OF TRAINING THE ADAPTIVE RESONANCE THEORY TO NEURAL NETWORKSZаkоvоrоtniyAleksander YurievichZаkоvоrоtniyAleksander YurievichArcade@i.ua20161100

The article analyzes the advantages and disadvantages of architectures and algorithms of training the Adaptive Resonance Theory (ART) to discrete neural networks. The authors propose some new architectures of ART neural networks and training algorithms of these networks without adaptation of link weights of distributed recognizing neurons.

The article analyzes the advantages and disadvantages of architectures and algorithms of training the Adaptive Resonance Theory (ART) to discrete neural networks. The authors propose some new architectures of ART neural networks and training algorithms of these networks without adaptation of link weights of distributed recognizing neurons.

adaptive resonance theory of discrete neural networkstraining algorithmsadaptive resonance theory of discrete neural networkstraining algorithmsСписок литературы1. Komashinskiy V.I. Neural Networks and their Application in the Systems of Management and Communication. Moscow: Goryachaja liniya – Telekom. 2002. 94 p.2. Neural networks for control. Edited by W. Thomas Miller III, Richard S. Sutton, and Paul J. Werbos. Cambridge, Massachusetts, London: MIT Press, 1996. 524 p.3. Barskiy A.B. Neural Networks: Identification, Management, Decision Making. Moscow: Finansy i statistika, 2004. 176 p.4. Galushkin A.I. Neurocomputers and their Application at the Turn of the Millennium in China. In 2 volumes. Vol. 2. Moscow: Goryachaya liniya – Telekom. 2004. 464 p.5. Haikin S. Neural Networks: a Complete Course. Moscow: Izdatel'skij dom «Vil'jams», 2006. 1104 p.6. Komartsova L.G. Neurocomputers: a Manual for Higher Institutions Moscow: Izd-vo im. N.Je. Baumana, 2002. 320 p.7. Grossberg S. Competitive learning: From interactive activation to adaptive resonance. Cognitive Science. 1987. Vol. 11. P. 23 – 63.8. Carpenter G.A., Grossberg S. A massively parallel architecture for selforganizing neural pattern recognition machine. Computing, Vision, Graphics and Image Processing. 1987. Vol. 37. Pp. 54-115.9. Dmitrienko V.D., Korsunov N.I. Theoratical Basics of Neural Networks. Belgorod: BIIMMAP, 2001. 159 p.10. Fausett L. Fundamentals of Neural Networks. Architectures, Algorithms and Applications. New Jersey: Prentice Hall International, Inc., 1994. 461 p.11. Noskov V.I. Modelling and Optimization of the Command and Control Systems in Locomotives. Kharkiv: HFI Transport Ukrainy, 2003. 248 p.