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/}
}
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/