¹Siberian Federal University, Krasnoyarsk, Russian Federation, anm11@rambler.ru

Previously, for each multilayer neural network of direct signal propagation (hereinafter, simply a neural network), finite commutative groupoids were introduced, which were called additive subnet groupoids. These groupoids are closely related to the subnets of the neural network over which they are built. A grupoid is a monoid if and only if it is built over a two-layer neural network. Earlier, endomorphisms and their properties were studied for these groupoids. Some endomorphisms were constructed, but an exhaustive element-by-element description was not received. It was shown that every finite monoid is isomorphic to some submonoid of the monoid of all endomorphisms of a suitable additive subnet groupoid for some suitable neural network.

In this paper, we study endomorphisms of additive groupoids of subnets of twolayer neural networks. The main result of the work is an element-wise description of the monoid of all endomorphisms of additive monoids of subnets built over a two-layer neural network. The item-by-item description is obtained by constructing a general form of endomorphism. The general view of an endomorphism is parameterized by the endomorphisms of suitable booleans with respect to the union operation. Therefore, endomorphisms of these Booleans were studied in this work. In particular, the semirings of endomorphisms of these Booleans with respect to the union were studied. In addition, to describe the general form of the endomorphism of the additive monoid of subnets, homomorphisms of one Boalean into another (with respect to union) were used.

1. Glushkov V.M. Abstract theory of automata. UMN, 1961. vol. 16, no. 5, pp. 3–62. (in Russian)
2. Golovko V.A., Krasnoproshin V.V. Neural network technologies for data processing. Minsk, Publ. house Belarus State University, 2017, 263 p. (in Russian)
3. Gorban’ A.N. Generalized approximation theorem and computational capabilities of neural networks. Sib. zhurn. calculated mathematics, 1998, vol. 1, no. 1, pp. 11–24. (in Russian)
4. Litavrin A.V. Endomorphisms of finite commutative groupoids related with multilayer feedforward neural networks. Trudy IMM UrO RAN, 2021, vol. 27, no. 1, pp. 130–145. https://doi.org/10.21538/0134-4889-2021-27-1-130-145 (in Russian)
5. Litinskii L.B. On the Problem of Decomposition of a Neural Network into Several Subnets. Mat. modeling, 1996, vol. 8, no. 11, pp. 119–127. (in Russian)
6. Plotkin B.I., Greenglaz L.Ya., Gvaramia A.A. Elements of the algebraic theory of automata. Moscow, Higher School Publ., 1994, 192 p. (in Russian)
7. Slepovichev I.I. Algebraic properties of abstract neural networks. Izvestiya Saratov Univ. New series. Series Mathematics. Mechanics. Informatics, 2016, vol. 16, no. 1, pp. 96–103. https://doi.org/10.18500/1816-9791-2016-16-1-96-103(in Russian)
8. Kravtsova O.V. Elementary Abelian 2-subgroups in an Autotopism Group of a Semifield Projective Plane. The Bulletin of Irkutsk State University. Series Mathematics, 2020, vol. 32, pp. 49-63. doi.org/10.26516/1997-7670.2020.32.49
9. Litavrin A.V. Endomorphisms of some groupoids of order 𝑘 + 𝑘². The Bulletin of the Irkutsk State University. Series Mathematics, 2020, vol. 32, pp. 64-78. https://doi.org/10.26516/1997-7670.2020.32.64
10. McCCulloh W., Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin Math. Biophysics, 1943, no. 5, pp. 115–133.
11. Tsarkov O.I. Endomorphisms of the semigroup 𝐺2(𝑟) over partially ordered commutative rings without zero divisors and with 1/2. J. Math. Sc., 2014, vol. 201, no. 4, pp. 534–551.
12. Zhuchok Yu.V. Endomorphism semigroups of some free products. J. Math. Sci., 2012. vol. 187, no. 2, pp. 146–152.