RUS  ENG
Full version
JOURNALS // Itogi Nauki i Tekhniki. Sovremennaya Matematika i ee Prilozheniya. Tematicheskie Obzory // Archive

Itogi Nauki i Tekhniki. Sovrem. Mat. Pril. Temat. Obz., 2019 Volume 166, Pages 3–9 (Mi into472)

On a certain learning algorithm for logical neural networks

D. P. Dimitrichenko

Institute of Applied Mathematics and Automation, Nalchik

Abstract: In this paper, we propose an algorithm for constructing variable-valued logical functions in the case of adding new production rules. The algorithm proposed serves as the basis for the method of constructive learning for logical neural networks based on variable-valued predicates.

Keywords: variable-valued predicate, variable-valued logical function, learning sample, production rule, logical neural network, constructive learning algorithm.

UDC: 519.716

MSC: 68T27

DOI: 10.36535/0233-6723-2019-166-3-9



Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024