English

Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks

Neural and Evolutionary Computing 2022-10-13 v2

Abstract

Spiking neural networks (SNNs), particularly the single-spike variant in which neurons spike at most once, are considerably more energy efficient than standard artificial neural networks (ANNs). However, single-spike SSNs are difficult to train due to their dynamic and non-differentiable nature, where current solutions are either slow or suffer from training instabilities. These networks have also been critiqued for their limited computational applicability such as being unsuitable for time-series datasets. We propose a new model for training single-spike SNNs which mitigates the aforementioned training issues and obtains competitive results across various image and neuromorphic datasets, with up to a 13.98×13.98\times training speedup and up to an 81%81\% reduction in spikes compared to the multi-spike SNN. Notably, our model performs on par with multi-spike SNNs in challenging tasks involving neuromorphic time-series datasets, demonstrating a broader computational role for single-spike SNNs than previously believed.

Keywords

Cite

@article{arxiv.2205.15286,
  title  = {Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks},
  author = {Luke Taylor and Andrew King and Nicol Harper},
  journal= {arXiv preprint arXiv:2205.15286},
  year   = {2022}
}

Comments

18 pages, 6 figures, under review at ICLR 2023

R2 v1 2026-06-24T11:33:30.091Z