Geodesic
Algebraic properties of recurrent neural networks of discrete time
Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 5 (2005) no. 1-2, pp. 116-128 
I. I. Slepovichev. Algebraic properties of recurrent neural networks of discrete time. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 5 (2005) no. 1-2, pp. 116-128. http://geodesic.mathdoc.fr/item/ISU_2005_5_1-2_a11/
@article{ISU_2005_5_1-2_a11,
     author = {I. I. Slepovichev},
     title = {Algebraic properties of recurrent neural networks of discrete time},
     journal = {Izvestiya of Saratov University. Mathematics. Mechanics. Informatics},
     pages = {116--128},
     year = {2005},
     volume = {5},
     number = {1-2},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ISU_2005_5_1-2_a11/}
}
TY  - JOUR
AU  - I. I. Slepovichev
TI  - Algebraic properties of recurrent neural networks of discrete time
JO  - Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
PY  - 2005
SP  - 116
EP  - 128
VL  - 5
IS  - 1-2
UR  - http://geodesic.mathdoc.fr/item/ISU_2005_5_1-2_a11/
LA  - ru
ID  - ISU_2005_5_1-2_a11
ER  - 
%0 Journal Article
%A I. I. Slepovichev
%T Algebraic properties of recurrent neural networks of discrete time
%J Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
%D 2005
%P 116-128
%V 5
%N 1-2
%U http://geodesic.mathdoc.fr/item/ISU_2005_5_1-2_a11/
%G ru
%F ISU_2005_5_1-2_a11

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

Artificial neural networks сan be used effectively for а quite general class of problems. Still there exists nо formal foundation of some important constructions used in the theory. ln this paper an attempt is undertaken to formalize some concepts of neuroinformatics and consider their properties from the point of view of applied universal algebra. lt is proposed to treat neural networks as heterogeneous algebras which has made it possible to prove for them basic results similar to algebraic theorems оn homomorphisms and congruences.

[1] McCulloc W. S., Pitts W. N., “A logical calculus of the ideas immanent in nervous activity”, Bull. of Math. Biophysics, 5 (1943), 115–133 | DOI | MR | Zbl

[2] Psiola V. V., “Obzor osnovnykh neirosetevykh modelei”, Intellektualnye sistemy, 4:3–4 (1999), 139–172

[3] Bogomolov A. M., Salii V. N., Algebraicheskie osnovy teorii diskretnykh sistem, M., 1997, 11

[4] Carrasco R. C., Mikel J. O., Forcada L., Efficient Encodings of finite automata in discrete-time recurrent neural networks, http://www.dlsi.ua.es/m̃lf/docum/carrasco99p.pdf