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. Two novel optimisation techniques are presented to achieve inference efficient SNN: a Top-K cutoff and a regularisation. The Top-K cutoff technique optimises the inference of SNN, and the regularisation are proposed to affect the training and construct SNN with optimised performance for cutoff. We conduct an extensive set of experiments on multiple benchmark frame-based datsets, such as Cifar10/100, Tiny-ImageNet and event-based datasets, including CIFAR10-DVS, N-Caltech101 and DVS128 Gesture. The experimental results demonstrate the effectiveness of our techniques in both ANN-to-SNN conversion and direct training, affirming their compatibility and potential benefits in enhancing accuracy and reducing inference timestep when integrated with existing methods. Code available: https://github.com/Dengyu-Wu/SNN-Regularisation-Cutoff

翻译：脉冲神经网络(SNN)作为模拟自然神经网络的新一代人工神经网络(ANN)，在计算效率方面展现出显著潜力。然而，当前SNN训练方法主要采用固定时间步长策略，忽视了SNN中动态推理的潜能。本文通过引入脉冲神经网络的截断机制，强化了SNN与事件驱动处理的融合，可在推理过程中随时终止网络运行以实现高效推理。我们提出两种新型优化技术以构建高效推理SNN：Top-K截断技术与正则化方法。Top-K截断技术优化SNN推理过程，正则化方法则通过影响训练过程构建适合截断的优化网络结构。我们在多个基准帧数据集（如Cifar10/100、Tiny-ImageNet）及事件数据集（包括CIFAR10-DVS、N-Caltech101和DVS128 Gesture）上进行了广泛实验。实验结果表明，我们的技术在ANN-SNN转换和直接训练两种模式中均表现优异，证实了其与现有方法结合时在提升精度和减少推理时间步长方面的兼容性与潜在优势。代码开源地址：https://github.com/Dengyu-Wu/SNN-Regularisation-Cutoff