Spiking neural networks (SNNs), a variant of artificial neural networks (ANNs) with the benefit of energy efficiency, have achieved the accuracy close to its ANN counterparts, on benchmark datasets such as CIFAR10/100 and ImageNet. However, comparing with frame-based input (e.g., images), event-based inputs from e.g., Dynamic Vision Sensor (DVS) can make a better use of SNNs thanks to the SNNs' asynchronous working mechanism. In this paper, we strengthen the marriage between SNNs and event-based inputs with a proposal to consider anytime optimal inference SNNs, or AOI-SNNs, which can terminate anytime during the inference to achieve optimal inference result. Two novel optimisation techniques are presented to achieve AOI-SNNs: a regularisation and a cutoff. The regularisation enables the training and construction of SNNs with optimised performance, and the cutoff technique optimises the inference of SNNs on event-driven inputs. We conduct an extensive set of experiments on multiple benchmark event-based datasets, including CIFAR10-DVS, N-Caltech101 and DVS128 Gesture. The experimental results demonstrate that our techniques are superior to the state-of-the-art with respect to the accuracy and latency.

翻译：脉冲神经网络（SNN）作为人工神经网络（ANN）的一种变体，凭借其能效优势，在CIFAR10/100和ImageNet等基准数据集上已达到与ANN相近的精度。然而，相较于基于帧的输入（如图像），动态视觉传感器（DVS）等事件驱动输入因SNN的异步工作机制而能更充分地发挥其优势。本文通过提出任意时刻最优推理脉冲神经网络（AOI-SNN）——该网络可在推理过程中随时中断并取得最优推理结果，进一步强化了SNN与事件驱动输入的结合。我们提出了两种实现AOI-SNN的新型优化技术：正则化与截断。正则化技术使得具有优化性能的SNN训练与构建成为可能，而截断技术则优化了SNN对事件驱动输入的推理过程。我们在CIFAR10-DVS、N-Caltech101和DVS128 Gesture等多个事件驱动基准数据集上进行了大量实验。实验结果表明，我们的方法在准确率和延迟方面均优于现有最优技术。