A method for storing and retrieving spatio-temporal patterns in large
systems of coupled delay differential equations is presented. Spatio-t
emporal patterns are sets of finite sequences of binary variables of f
ixed period that are embedded in the network dynamics as stable limit
cycles. An input signal converges to the limit cycle that represents i
t best. A given set of limit cycles is constructed using a generalizat
ion of the correlation learning rule in the definition of the coupling
s.