RUS  ENG
Full version
JOURNALS // News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences // Archive

News of the Kabardin-Balkar scientific center of RAS, 2017 Issue 6-1, Pages 15–20 (Mi izkab169)

MATH MODELING. PHYSICS

Application of the neural network approach to the tasks of logical data processing in the construction of cognitive maps

D. P. Dimitrichenko, R. A. Zhilov

Institute of Applied Mathematics and Automation – branch of the FSBSE "Federal Scientific Center "Kabardin-Balkar Scientific Center of the Russian Academy of Sciences", 360000, KBR, Nalchik, Shortanov street, 89 A

Abstract: In this paper, we propose the use of logical neural networks for constructing cognitive maps. Cognitive maps are successfully used for data structuring. This allows to reduce the internal dimension of data, which contributes to the successful construction of information systems with a large number of parameters. Additional flexibility is provided by the use of various-valued logic functions as a basis for constructing logical neural net-works. A procedure for constructing cognitive maps using logical neural networks is proposed.

Keywords: predicate, the predicate atomicity, various-valued logical function logical neural network, fuzzy logic variable, cognitive map, cluster analysis, neural network training set, fuzzy sets.

UDC: 519.71

Received: 12.10.2017



© Steklov Math. Inst. of RAS, 2024