We study a stochastic neural-network model in which neurons and synapses ch
ange with a priori probability p and 1 - p, respectively, in the limit p --
> 0. This implies neuron activity competing with fast fluctuations of the s
ynaptic connections-in fact, random oscillations around values given by a l
earning (for example, Hebb's) rule. The consequences for the system perform
ance of a dynamics constantly checking at random the set of memorized patte
rns is thus studied both analytically and numerically. We describe various
nonequilibrium phase transitions whose nature depends on the properties of
fluctuations. We find. in particular, that under rather general conditions
locally stable mixture states do not occur, and pattern recognition and ret
rieval processes are substantially improved for some classes of synaptic fl
uctuations.