Abstract. For a network of spiking neurons with reasonable postsynaptic potentials, we derive a supervised learning rule akin to traditional error-back-propagation, SpikeProp and show how to overcome the discontinuities introduced by thresholding. Using this learning algorithm, we demonstrate how networks of spiking neurons with biologically plausible time-constants can perform complex non-linear classification in fast temporal coding just as well as rate-coded networks. When comparing the (implicit) number of neurons required for the respective encodings, it is empirically demonstrated that temporal coding potentially requires significantly less neurons.
Sander M. Bohte, Joost N. Kok, Johannes A. La Pout