论文标题
VSA：可重新配置的矢量尖峰神经网络加速器
VSA: Reconfigurable Vectorwise Spiking Neural Network Accelerator
论文作者
论文摘要
在边缘设备上实现低功率设计的尖峰神经网络（SNN）最近吸引了大量研究。但是，SNN的时间特征会导致高潜伏期，高带宽和高能量消耗。在这项工作中，我们提出了一个二进制重量尖峰模型，该模型具有少量时间步长的if批准归一化，而使用输入编码层和时空的后退传播（STBP）的直接训练时，则针对小时间步骤和低硬件成本。此外，我们提出了一个矢量硬件加速器，该加速器可用于不同模型，推理时间步骤，甚至支持编码层以接收多位数输入。两层融合机制进一步降低了所需的内存带宽。实施结果显示了仅有8个时间步骤的MNIST和CIFAR-10数据集的竞争精度，并且可以达到25.9 TOPS/W的功率效率。
Spiking neural networks (SNNs) that enable low-power design on edge devices have recently attracted significant research. However, the temporal characteristic of SNNs causes high latency, high bandwidth and high energy consumption for the hardware. In this work, we propose a binary weight spiking model with IF-based Batch Normalization for small time steps and low hardware cost when direct training with input encoding layer and spatio-temporal back propagation (STBP). In addition, we propose a vectorwise hardware accelerator that is reconfigurable for different models, inference time steps and even supports the encoding layer to receive multi-bit input. The required memory bandwidth is further reduced by two-layer fusion mechanism. The implementation result shows competitive accuracy on the MNIST and CIFAR-10 datasets with only 8 time steps, and achieves power efficiency of 25.9 TOPS/W.
