Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains a challenge to train SNNs due to their undifferentiable spiking mechanism. The surrogate gradients method is commonly used to train SNNs, but often comes with an accuracy disadvantage over ANNs counterpart. We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the training process of Leaky Integrate-and-Fire (LIF) Neuron-based SNNs. Moreover, we propose the Complementary Leaky Integrate-and-Fire (CLIF) Neuron. CLIF creates extra paths to facilitate the backpropagation in computing temporal gradient while keeping binary output. CLIF is hyperparameter-free and features broad applicability. Extensive experiments on a variety of datasets demonstrate CLIF's clear performance advantage over other neuron models. Moreover, the CLIF's performance even slightly surpasses superior ANNs with identical network structure and training conditions.

翻译：脉冲神经网络（SNNs）是一种有前景的脑启发式节能模型。与传统深度人工神经网络（ANNs）相比，SNNs在处理时间信息方面表现出卓越的效率和能力。然而，由于其不可微的脉冲机制，训练SNNs仍是一个挑战。代理梯度法常用于训练SNNs，但通常会导致精度低于对应的ANNs。通过对基于漏积分激发（LIF）神经元的SNNs训练过程进行分析和实验研究，我们将精度下降归因于时间维度上的梯度消失问题。此外，我们提出了互补漏积分激发（CLIF）神经元。CLIF创建了额外路径以促进计算时间梯度时的反向传播，同时保持二进制输出。CLIF无需超参数且具有广泛适用性。在多种数据集上的大量实验表明，CLIF的性能明显优于其他神经元模型。此外，在相同网络结构和训练条件下，CLIF的性能甚至略超先进的ANNs。