Geodesic
Algebraic properties of abstract neural network
Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 16 (2016) no. 1, pp. 96-103.

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

The modern level of neuroinformatics allows to use artificial neural networks for the solution of various applied problems. However many neural network methods put into practice have no strict formal mathematical substantiation, being heuristic algorithms. It imposes certain restrictions on development of neural network methods of the solution of problems. At the same time there is a wide class of mathematical models which are well studied within such disciplines as theory of abstract algebras, graph theory, automata theory. Opportunity to use results received within these disciplines in relation to neural network models can be a good help in studying of artificial neural networks, their properties and functionality. In this work formulations and definitions of neural network models from the point of view of universal algebra and the theory of graphs are given. The main theorems of universal algebra are provided in neural network treatment. In article is also offered the way of the formal description of a neuronet by graph-schemes which allows to use results of graph theory for the analysis of neural network structures. 
@article{ISU_2016_16_1_a8,
     author = {I. I. Slepovichev},
     title = {Algebraic properties of abstract neural network},
     journal = {Izvestiya of Saratov University. Mathematics. Mechanics. Informatics},
     pages = {96--103},
     publisher = {mathdoc},
     volume = {16},
     number = {1},
     year = {2016},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ISU_2016_16_1_a8/}
}
TY  - JOUR
AU  - I. I. Slepovichev
TI  - Algebraic properties of abstract neural network
JO  - Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
PY  - 2016
SP  - 96
EP  - 103
VL  - 16
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ISU_2016_16_1_a8/
LA  - ru
ID  - ISU_2016_16_1_a8
ER  - 
%0 Journal Article
%A I. I. Slepovichev
%T Algebraic properties of abstract neural network
%J Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
%D 2016
%P 96-103
%V 16
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ISU_2016_16_1_a8/
%G ru
%F ISU_2016_16_1_a8
I. I. Slepovichev. Algebraic properties of abstract neural network. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 16 (2016) no. 1, pp. 96-103. http://geodesic.mathdoc.fr/item/ISU_2016_16_1_a8/

[1] Golovko V. A., Neural networks: training, and organizing your application, v. 4, Manual for High Schools, ed. A. I. Galushkin, IPRZhR, M., 2001 (in Russian)

[2] Gorban A. N., “Generalized approximation theorem and computational capabilities of neural networks”, Sib. Zh. Vychisl. Mat., 1:1 (1998), 11–24 (in Russian)

[3] Kruglov V. V., Dli M. I., Golunov R. U., Fuzzy Logic and Artificial Neural Network, Fizmatlit, M., 2001 (in Russian)

[4] Tarhov D. A., Neural network. Models and Algorithms, Radiotehnika, M., 2005 (in Russian)

[5] Haykin S., Neural Networks. A Comprehensive Foundation, Hamilton, Ontario, Canada, 1999

[6] Bogomolov A. M., Salii V. N., Algebraic foundations of the theory of discrete systems, Nauka, M., 1997 (in Russian) | MR

[7] Kolmogorov A. N., “On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition”, Dokl. Akad. Nauk SSSR, 114:5 (1957), 953–956 (in Russian) | MR | Zbl

[8] Gorban A. N., Training neural networks, USSR-USA JV “Paragraph”, M., 1990 (in Russian)

[9] Alekseev V. B., Lozhkin S. A., Elements of the theory of graphs, charts and machines, Izdat. otdel fakulteta VMiK MGU, M., 2000 (in Russian)

[10] Mitrofanov Yu. I., System analysis, Nauchnaia kniga, Saratov, 2000 (in Russian)