|
Itogi Nauki i Tekhniki. Sovremennaya Matematika i ee Prilozheniya. Tematicheskie Obzory, 2018, Volume 154, Pages 81–88
(Mi into381)
|
|
|
|
This article is cited in 5 scientific papers (total in 5 papers)
Construction of a Logical-Algebraic Corrector for Increasing Adaptive Properties of the $\Sigma\Pi$-Neuron
L. A. Lyutikova Institute of Applied Mathematics and Automation, Nalchik
Abstract:
In this paper, we consider the problem of constructing a correction algorithm for increasing adaptive properties of the $\Sigma\Pi$-neuron, based solely on the structure of the $\Sigma\Pi$-neuron itself. The logical-algebraic method of data analysis is used for the construction of the corrector. Comparison of advantages of the neural-network approach and the logical-algebraic method leads to the conclusion that the combined approach to the organization of neural networks improves their efficiency and allows one to state rules that reveal hidden patterns in a given subject area and thus to improve the quality of the recognition system.
Keywords:
$\Sigma\Pi$-neuron, algorithm, corrector, classifier, predicate, disjunctive normal form, logical function.
Citation:
L. A. Lyutikova, “Construction of a Logical-Algebraic Corrector for Increasing Adaptive Properties of the $\Sigma\Pi$-Neuron”, Proceedings of the International Conference “Actual Problems of Applied Mathematics and Physics,” Kabardino-Balkaria, Nalchik, May 17–21, 2017, Itogi Nauki i Tekhniki. Sovrem. Mat. Pril. Temat. Obz., 154, VINITI, Moscow, 2018, 81–88; J. Math. Sci. (N. Y.), 253:4 (2021), 539–546
Linking options:
https://www.mathnet.ru/eng/into381 https://www.mathnet.ru/eng/into/v154/p81
|
Statistics & downloads: |
Abstract page: | 89 | Full-text PDF : | 48 | References: | 14 |
|