Do biological synapses perform probabilistic computations?

In this paper, the presynaptic rule, a classical model of synaptic reinforcement, is revisited. It is shown that this model is capable of reproducing recently discovered properties of biological synapses such as synaptic directionality, and metaplasticity of the long-term potentiation threshold. With slight modifications, the presynaptic model also reproduces metaplasticity of the long-term depression threshold and Artola, Bröcher and Singer’s experimental model. Two asymptotically equivalent approaches were adopted for this analysis, one with firing rates and another with conditional probabilities. Although both approximations are consistent with biological properties, the results obtained by the probabilistic approach are qualitatively closer to biological experimental results.