Many natural processes consist of networks of interacting elements that, ov
er time, affect each other's state. Their dynamics depend on the pattern of
connections and the updating rules for each element. Genomic regulatory ne
tworks are networks of this sort. In this paper we use artificial neural ne
tworks as a model of the dynamics of gene expression. The significance of t
he regulatory effect of one gene product on the expression of other genes o
f the system is defined by a weight matrix. The model considers multigenic
regulation including positive and/or negative feedback. The process of gene
expression is described by a single network and by two linked networks whe
re transcription and translation are modeled independently. Each of these p
rocesses is described by different network controlled by different weight m
atrices. Methods for computing the parameters of the model from experimenta
l data are discussed. Results computed by means of the model are compared w
ith experimental observations, Generalization to a 'black box' concept, whe
re the molecular processes occurring in the cell are considered as signal p
rocessing units forming a global regulatory network, is discussed.