Geodesic
About one groupoid associated with the composition of multilayer feedforward neural networks
Žurnal Srednevolžskogo matematičeskogo obŝestva, Tome 26 (2024) no. 2, pp. 111-122.

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

The authors construct a groupoid whose elements are associated with multilayer feedforward neural networks. This groupoid is called the complete groupoid of the composition of neural networks. Multilayer feedforward neural networks (hereinafter referred to as neural networks) are modelled by defining a special type of tuple. Its components define layers of neurons and structural mappings that specify weights of synaptic connections, activation functions and threshold values. Using the artificial neuron model (that of McCulloch-Pitts) for each such tuple it is possible to define a mapping that models the operation of a neural network as a computational circuit. This approach differs from defining a neural network using abstract automata and related constructions. Modeling neural networks using the proposed method makes it possible to describe the architecture of the network (that is, the network graph, the synaptic weights, etc.). The operation in the full neural network composition groupoid models the composition of two neural networks. A network, obtained as the product of a pair of neural networks, operates on input signals by sequentially applying original networks and contains information about their structure. It is proved that the constructed groupoid is a free.
Mots-clés : groupoid
Keywords: free groupoid, multilayer feedforward neural network, complete groupoid composition of multilayer neural networks 
@article{SVMO_2024_26_2_a0,
     author = {A. V. Litavrin and T. V. Moiseenkova},
     title = {About one groupoid associated with the composition of multilayer feedforward neural networks},
     journal = {\v{Z}urnal Srednevol\v{z}skogo matemati\v{c}eskogo ob\^{s}estva},
     pages = {111--122},
     publisher = {mathdoc},
     volume = {26},
     number = {2},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/SVMO_2024_26_2_a0/}
}
TY  - JOUR
AU  - A. V. Litavrin
AU  - T. V. Moiseenkova
TI  - About one groupoid associated with the composition of multilayer feedforward neural networks
JO  - Žurnal Srednevolžskogo matematičeskogo obŝestva
PY  - 2024
SP  - 111
EP  - 122
VL  - 26
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SVMO_2024_26_2_a0/
LA  - ru
ID  - SVMO_2024_26_2_a0
ER  - 
%0 Journal Article
%A A. V. Litavrin
%A T. V. Moiseenkova
%T About one groupoid associated with the composition of multilayer feedforward neural networks
%J Žurnal Srednevolžskogo matematičeskogo obŝestva
%D 2024
%P 111-122
%V 26
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SVMO_2024_26_2_a0/
%G ru
%F SVMO_2024_26_2_a0
A. V. Litavrin; T. V. Moiseenkova. About one groupoid associated with the composition of multilayer feedforward neural networks. Žurnal Srednevolžskogo matematičeskogo obŝestva, Tome 26 (2024) no. 2, pp. 111-122. http://geodesic.mathdoc.fr/item/SVMO_2024_26_2_a0/

[1] Golovko V. A., Krasnoproshin V. V., Neirosetevye tekhnologii obrabotki dannykh, ucheb. posobie, Izd-vo Belarus. gos. un-ta, Minsk, 2017, 263 s. pp.

[2] Gorban A. N., “Obobschennaya approksimatsionnaya teorema i vychislitelnye vozmozhnosti neironnykh setei”, Sibirskii zhurnal vychislitelnoi matematiki, 1:1 (1998), 11–24 pp. | Zbl

[3] Rozenblatt F., Printsipy neirodinamiki: perseptron i teoriya mekhanizmov mozga, per. s angl., Mir, M., 1965, 478 s. pp.

[4] Sozykin A. V., “Obzor metodov obucheniya glubokikh neironnykh setei”, Vestnik Yuzhno-Uralskogo gosudarstvennogo universiteta. Seriya «Vychislitelnaya matematika i informatika», 6:3 (2017), 28–59 pp. | DOI

[5] Litavrin A. V., “Endomorfizmy konechnykh kommutativnykh gruppoidov, svyazannykh s mnogosloinymi neironnymi setyami pryamogo raspredeleniya”, Tr. IMM UrO RAN, 27:1 (2021), 130–145 pp. | DOI | MR

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

[7] Slepovichev I. I., “Algebraicheskie svoistva abstraktnykh neironnykh setei”, Izvestiya Saratovskogo universiteta. Novaya seriya. Seriya: «Matematika. Mekhanika. Informatika», 16:1 (2016), 96–103 pp. | DOI | MR | Zbl

[8] Glushkov V. M., “Abstraktnaya teoriya avtomatov”, Uspekhi matematicheskikh nauk, 16:5 (1961), 3–62 pp.