The dynamics of simple neural systems is of interest to both biologist
s and physicists. One of the possible roles of such systems is the pro
duction of rhythmic patterns, and their alterations (modification of b
ehavior, processing of sensory information, adaptation, control). In t
his paper, the neural systems are considered as a subject of modeling
by the dynamical systems approach. In particular, we analyze how a sta
ble, ordinary behavior of a small neural system can be described by si
mple finite automata models, and how more complicated dynamical system
s modeling can be used. The approach is illustrated by biological and
numerical examples: experiments with and numerical simulations of the
stomatogastric central pattern generators network of the California sp
iny lobster. (C) 1996 American Institute of Physics.