Development of an algorithm based on logical operations
News of the Kabardin-Balkar scientific center of RAS, no. 6 (2023), pp. 109-115.

Voir la notice de l'article provenant de la source Math-Net.Ru

This paper presents a method of local interpretation of solutions of a trained neural network by functions of multivalued predicate logic. The local interpretation of a neural network refers to the process of explaining the decisions made by the model on a specific example or in the vicinity of a specific input. The proposed approach is based on a set of functions of multivalued logic, which are generalized operations that meet certain requirements. By combining these functions, it is possible to detect internal patterns in the data and even correct the results obtained with the help of neural networks. The proposed method was investigated in the context of classification problems using multidimensional discrete features. In such cases, each attribute can take one of k possible values and have equal importance for class identification. This approach opens up new possibilities for understanding and explaining the rules underlying the data, which are not always obvious when using conventional neural networks.
Keywords: interpretation, multivalued logic, neural network, generalized addition, data
@article{IZKAB_2023_6_a10,
     author = {L. A. Lyutikova},
     title = {Development of an algorithm based on logical operations},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {109--115},
     publisher = {mathdoc},
     number = {6},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a10/}
}
TY  - JOUR
AU  - L. A. Lyutikova
TI  - Development of an algorithm based on logical operations
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2023
SP  - 109
EP  - 115
IS  - 6
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a10/
LA  - ru
ID  - IZKAB_2023_6_a10
ER  - 
%0 Journal Article
%A L. A. Lyutikova
%T Development of an algorithm based on logical operations
%J News of the Kabardin-Balkar scientific center of RAS
%D 2023
%P 109-115
%N 6
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a10/
%G ru
%F IZKAB_2023_6_a10
L. A. Lyutikova. Development of an algorithm based on logical operations. News of the Kabardin-Balkar scientific center of RAS, no. 6 (2023), pp. 109-115. http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a10/

[1] Yu. I. Zhuravlev, “On the algebraic approach to solving problems of recognition or classification”, Problems of cybernetics, 33 (1978), 5–68 (In Russian)

[2] Z. Sh. Zhibzukhov, “Correct algorithms for aggregating operations”, Pattern recognition and image analysis, 2014, no. 3-24, 377–382 (In Russian)

[3] A. I. Naimi, L. B. Balzer, “Multilevel generalization: an introduction to super learning”, European Journal of Epidemiology, 33 (2018), 459–464 | DOI

[4] H. Wang, S. Smith, “Big data analysis and perturbation using a data mining algorithm”, Journal of Soft Computing Paradigm, 2021, no. 3-01, 19–28 | Zbl

[5] Joe MrK Vijesh, S. Jennifer, “Raj User Recommendation System Dependent on Location Based Orientation Context”, Journal of Trends in Computer Science and Smart Technology, 2021, no. 3-01, 14–23

[6] M. Grabisch, Marichal J-L, E. Pap, Aggregation functions, v. 127, Cambridge University Press, 2009, 16 pp. | MR | Zbl

[7] T. Calvo, G. Belyakov, “Aggregating functions based on penalties”, Fuzzy sets and systems, 2010, no. 10-161, 1420–1436 | DOI | MR | Zbl

[8] R. Mesiar, M. Komornikova, A. Kolesarova, T. Calvo, “Fuzzy aggregation functions: a revision”, Sets and their extensions: representation, aggregation and models, 2008, Springer-Verlag

[9] F. Yang, Zh. Yang, W. W. Cohen, “Differentiable learning of logical rules for reasoning in the knowledge base”, Advances in the field of neural information processing systems, 2017, 2320–2329

[10] P. Flakh, Mashinnoe obuchenie: nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannykh, DMK Press, Moskva, 2015, 400 pp.

[11] L. A. Lyutikova, E. V. Shmatova, “Algorithm for constructing logical operations to identify patterns in data”, E3S Web of Conferences, 224 (November 25-27, 2020), 01009, Moscow | DOI