Spikingformer：基于脉冲的剩余学习用于基于 Transformer 的脉冲神经网络（英文版）

英文标题：Spikingformer: Spike-driven Residual Learning for Transformer-based Spiking Neural Network中文摘要：本研究提出了一种硬件友好的、基于残差设计的、全新的、纯变压器型脉冲神经网络 ——Spikingformer，它能够避免非脉冲计算并使能耗降低 60.34％。Spikingformer 在图像分类任务的表现优于之前的纯 SNN，并且是首次开发出全脉冲驱动的变压器型 SNN。英文摘要：Spiking neural networks (SNNs) offer a promising energy-efficient alternativeto artificial neural networks, due to their event-driven spiking computation.However, state-of-the-art deep SNNs (including Spikformer and SEW ResNet)suffer from non-spike computati