Backpropagation for Population-Temporal Coded Spiking Neural Networks

Supervised learning rules for spiking neural networks are currently only able to use time-to-first-spike coding and are plagued by very irregular learning curves due to their inability to model spike creation and deletion by weight changes. This paper presents a new learning rule for spiking neurons that uses the general population-temporal coding model. It is inspired by learning rules for locally recurrent analog neural networks. As a result we have a very fast learning rule that is able to operate on a wide class of decoding schemes.