Stochastic resonance in a system of two coupled threshold elements (neurons
) forming a small artificial neural network is investigated. The elements h
ave either antisymmetric or logistic (binary) response Function and are dri
ven by periodic signals and independent noises. Periodic signals at their i
nputs have equal amplitudes and frequencies but are shifted in phase. Depen
ding on the response function and the phase shift, enhancement of stochasti
c resonance in individual elements, characterized by the output signal-to-n
oise ratio, and stochastic resonance with a spatiotemporal input signal, ch
aracterized by the correlation function between the input and output signal
s, are observed for proper coupling between elements.