Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To train deep SNNs, recently, spatio-temporal backpropagation (STBP) with surrogate gradient was proposed. Although deep SNNs have been successfully trained with STBP, they cannot fully utilize spike information. In this work, we proposed gradient scaling with local spike information, which is the relation between pre- and post-synaptic spikes. Considering the causality between spikes, we could enhance the training performance of deep SNNs. According to our experiments, we could achieve higher accuracy with lower spikes by adopting the gradient scaling on image classification tasks, such as CIFAR10 and CIFAR100.

翻译：深层脉冲神经网络因其兼具深度神经网络架构的模型容量与脉冲神经网络的能效优势，成为极具前景的神经网络模型。针对深层脉冲神经网络的训练，近期提出了结合替代梯度的时空反向传播算法。尽管该算法已成功实现深层脉冲神经网络的训练，但仍未能充分挖掘脉冲信息。本研究提出利用局部脉冲信息（即突触前/后脉冲之间的关联性）进行梯度缩放。通过考虑脉冲间的因果性，我们能够提升深层脉冲神经网络的训练性能。实验表明，在CIFAR10和CIFAR100等图像分类任务中采用梯度缩放方法后，不仅提高了分类准确率，还显著降低了脉冲发放数量。