Geodesic
On some commutative and idempotent finite groupoids associated with subnets of multilayer feedforward neural networks
Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika, Tome 18 (2025) no. 1, pp. 59-70.

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

The work studies commutative and idempotent finite groupoids that are associated with subnetworks of multilayer feedforward neural networks (hereinafter simply neural networks). Previously, the concept of a neural network subnet was introduced. This paper introduces the concept of a generalized subnetwork of a neural network. This concept generalizes the previously introduced concept. The resulting groupoids are called additive and multiplicative groupoids of generalized subnets of a given neural network. These groupoids model the union and intersection of generalized subnets of a neural network. The conditions that the neural network architecture must satisfy in order for the additive groupoid of generalized subnets to be associative are identified. The conditions that the neural network architecture must satisfy in order for the multiplicative groupoid of generalized subnets to be associative are obtained. Subgroupoids of the constructed groupoids are studied.
Keywords: multilayer neural network of feedforward signal propagation, subnetwork of multilayer neural network of feedforward signal propagation, additive groupoid of generalized subnetworks, multiplicative groupoid of generalized subnetworks, generalized subnetwork.
Mots-clés : groupoid 
@article{JSFU_2025_18_1_a6,
     author = {Andrey V. Litavrin and Tatyana V. Moiseenkova},
     title = {On some commutative and idempotent finite groupoids associated with subnets of multilayer feedforward neural networks},
     journal = {\v{Z}urnal Sibirskogo federalʹnogo universiteta. Matematika i fizika},
     pages = {59--70},
     publisher = {mathdoc},
     volume = {18},
     number = {1},
     year = {2025},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/JSFU_2025_18_1_a6/}
}
TY  - JOUR
AU  - Andrey V. Litavrin
AU  - Tatyana V. Moiseenkova
TI  - On some commutative and idempotent finite groupoids associated with subnets of multilayer feedforward neural networks
JO  - Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika
PY  - 2025
SP  - 59
EP  - 70
VL  - 18
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/JSFU_2025_18_1_a6/
LA  - en
ID  - JSFU_2025_18_1_a6
ER  - 
%0 Journal Article
%A Andrey V. Litavrin
%A Tatyana V. Moiseenkova
%T On some commutative and idempotent finite groupoids associated with subnets of multilayer feedforward neural networks
%J Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika
%D 2025
%P 59-70
%V 18
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/JSFU_2025_18_1_a6/
%G en
%F JSFU_2025_18_1_a6
Andrey V. Litavrin; Tatyana V. Moiseenkova. On some commutative and idempotent finite groupoids associated with subnets of multilayer feedforward neural networks. Žurnal Sibirskogo federalʹnogo universiteta. Matematika i fizika, Tome 18 (2025) no. 1, pp. 59-70. http://geodesic.mathdoc.fr/item/JSFU_2025_18_1_a6/

[1] A.V.Litavrin, “Endomorphisms of finite commutative groupoids associated with multilayer neural networks of direct distribution”, Proceedings of the Institute of Mathematics and Mechanics. Ural Branch of the Russian Academy of Sciences, 27:1 (2021), 130–145 | DOI | MR

[2] A.N.Gorban, “Generalized approximation theorem and computational capabilities of neural networks”, Sib. magazine Comput. mat., 1:1 (1998), 11–24 | MR

[3] I.I.Slepovichev, “Algebraic properties of abstract neural networks”, Izv. Sarat. un-ta. New ser. Ser. Mathematics. Mechanics. Computer Science, 16:1 (2016), 96–103 | DOI | MR | Zbl

[4] A.V.Sozykin, “Review of methods for training deep neural networks”, Bulletin of the South Ural State University. Series “Computational Mathematics and Information Science”, 6:3 (2017), 28–59 | DOI

[5] A.V.Litavrin, “On endomorphisms of the additive monoid of subnets of a two-layer neural network”, The Bulletin of Irkutsk State University. Series Mathematics, 39 (2022), 111–126 | DOI | MR | Zbl

[6] A.V.Litavrin, “On some finite commutative groupoids associated with multilayer feed-forward neural networks”, Proceedings of the XXI International Conference dedicated to the 85th anniversary of the birth of A. A. Karatsuba, TSPU im. L. N. Tolstoy, Tula, 2022, 106–109 | MR

[7] A.V.Litavrin, T.V.Moiseenkova, “About one groupoid associated with the composition of multilayer feedforward neural networks”, Zhurnal Srednevolzhskogo matematicheskogo obshchestva, 26:2 (2024), 111–122 | DOI | MR | Zbl