Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest due to their low power features, high biological plausibility, and strong spatiotemporal information processing capability. Although adopting a surrogate gradient (SG) makes the non-differentiability SNN trainable, achieving comparable accuracy for ANNs and keeping low-power features simultaneously is still tricky. In this paper, we proposed an energy-efficient spike-train level spiking neural network (SLSSNN) with low computational cost and high accuracy. In the SLSSNN, spatio-temporal conversion blocks (STCBs) are applied to replace the convolutional and ReLU layers to keep the low power features of SNNs and improve accuracy. However, SLSSNN cannot adopt backpropagation algorithms directly due to the non-differentiability nature of spike trains. We proposed a suitable learning rule for SLSSNNs by deducing the equivalent gradient of STCB. We evaluate the proposed SLSSNN on static and neuromorphic datasets, including Fashion-Mnist, Cifar10, Cifar100, TinyImageNet, and DVS-Cifar10. The experiment results show that our proposed SLSSNN outperforms the state-of-the-art accuracy on nearly all datasets, using fewer time steps and being highly energy-efficient.

翻译：受大脑启发的尖峰神经网络（SNNs）凭借其低功耗特性、高生物合理性和强大的时空信息处理能力，已引起广泛研究兴趣。尽管采用替代梯度（SG）解决了SNNs不可微的训练难题，但同时实现与人工神经网络（ANNs）相当的精度并保持低功耗特性仍具挑战性。本文提出了一种兼具低计算开销与高精度的能效型脉冲序列尖峰神经网络（SLSSNN）。在该网络中，使用时空转换模块（STCBs）替代卷积层和ReLU层，以保持SNNs的低功耗特性并提升精度。然而，由于脉冲序列的不可微性，SLSSNN无法直接应用反向传播算法。通过推导STCB的等效梯度，我们为SLSSNN提出了适配的学习规则。在静态数据集（Fashion-Mnist、Cifar10、Cifar100、TinyImageNet）和神经形态数据集（DVS-Cifar10）上的评估表明，所提SLSSNN在几乎所有数据集上均实现了最优精度，同时以更少的时间步长实现了高能效运行。