Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

arXiv:2301.09522v3 Announce Type: replace
Abstract: Spiking neural network (SNN), next generation of artificial neural network (ANN) that more closely mimic natural neural networks offers promising improvements in computational efficiency. However, current SNN training methodologies predominantly employ a fixed timestep approach, overlooking the potential of dynamic inference in SNN. In this paper, we strengthen the marriage between SNN and event-driven processing with a proposal to consider cutoff in SNN, which can terminate SNN anytime during the inference to achieve efficient inference. …

arxiv cs.cv event network neural network spiking neural network type