DelGrad: Exact gradients in spiking networks for learning transmission delays and weights

arXiv:2404.19165v1 Announce Type: cross
Abstract: Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information. Transmission delays play an important role in shaping these temporal characteristics. Recent work has demonstrated the substantial advantages of learning these delays along with synaptic weights, both in terms of accuracy and memory efficiency. However, these approaches suffer from drawbacks in terms of precision and efficiency, as they operate in discrete time and with approximate gradients, while also requiring …

abstract advantages arxiv cs.et cs.lg cs.ne information networks neural networks processing role spiking neural networks temporal type work