提出PASCAL方法，让脉冲神经网络用更少步数达到媲美人工神经网络的精度。
PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activation
- 通过脉冲累积和自适应分层激活，实现脉冲网络与量化激活网络数学等价
- ResNet-34在ImageNet上达74%准确率，推理步数减少64倍
- 适合追求低功耗高效率的边缘设备部署场景
脉冲神经网络（SNN）因其稀疏累加操作，被视为人工神经网络（ANN）的节能替代方案。近年来，基于量化-截断-下取整-移位（QCFS）激活函数的ANN-SNN转换方法被广泛采用，以实现接近ANN精度的深度SNN。然而，现有方法在真实数据集上仍需大量推理时间步才能匹配原ANN精度。本文提出PASCAL方法，使转换后的SNN在数学上等价于使用QCFS激活的ANN，从而在极小推理步数下保持相近精度。此外，我们提出一种分层配置QCFS量化步长的系统化方法，有效确定每层最优推理步数。实验表明，使用PASCAL转换的ResNet-34在ImageNet上达到约74%准确率，相比现有方法推理步数减少64倍。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) have been put forward as an energy-efficient alternative to Artificial Neural Networks (ANNs) since they perform sparse Accumulate operations instead of the power-hungry Multiply-and-Accumulate operations. ANN-SNN conversion is a widely used method to realize deep SNNs with accuracy comparable to that of ANNs.~\citeauthor{bu2023optimal} recently proposed the Quantization-Clip-Floor-Shift (QCFS) activation as an alternative to ReLU to minimize the accuracy loss during ANN-SNN conversion. Nevertheless, SNN inferencing requires a large number of timesteps to match the accuracy of the source ANN for real-world datasets. In this work, we propose PASCAL, which performs ANN-SNN conversion in such a way that the resulting SNN is mathematically equivalent to an ANN with QCFS-activation, thereby yielding similar accuracy as the source ANN with minimal inference timesteps. In addition, we propose a systematic method to configure the quantization step of QCFS activation in a layerwise manner, which effectively determines the optimal number of timesteps per layer for the converted SNN. Our results show that the ResNet-34 SNN obtained using PASCAL achieves an accuracy of $\approx$74\% on ImageNet with a 64$\times$ reduction in the number of inference timesteps compared to existing approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。