Sparse Spiking Gradient Descent. (arXiv:2105.08810v2 [cs.NE] UPDATED)

There is an increasing interest in emulating Spiking Neural Networks (SNNs)
on neuromorphic computing devices due to their low energy consumption. Recent
advances have allowed training SNNs to a point where they start to compete with
traditional Artificial Neural Networks (ANNs) in terms of accuracy, while at
the same time being energy efficient when run on neuromorphic hardware.
However, the process of training SNNs is still based on dense tensor operations
originally developed for ANNs which do not leverage the …

arxiv gradient