NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:4223
Title:Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

The authors propose a variant of the backpropagation through time (BPTT) algorithm for spiking neural networks (SNNs). An interesting aspect is that, instead of unrolling the network computation over time, backpropagation over spike trains is performed. The algorithm is tested on various datasets, achieving state-of-the-art results for SNNs. The approach is very original and innovative. The results are very good and of interest for the community interested in spiking neural networks. We therefore agreed that the manuscript is suitable for publication at NeurIPS. The authors are advised to re-work the abstract and introduction. There, one gets the impression that the algorithm is biologically plausible, which is not the case according to the Author's feedback.