Algebraic properties of recurrent neural networks of discrete time

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.