Tempotron-like learning with ReSuMe
Răzvan V. Florian
The tempotron is a model of supervised learning that allows a spiking neuron to discriminate between different categories of spike trains, by firing or not as function of the category. We show that tempotron learning is quasi-equivalent to an application for a specific problem of a previously proposed, more general and biologically plausible, supervised learning rule (ReSuMe). Moreover, we show through simulations that by using ReSuMe one can train neurons to categorize spike trains not only by firing or not, but also by firing given spike trains, in contrast to the original tempotron proposal.