论文标题
TCL：可训练的剪裁层的ANN-SNN转换
TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers
论文作者
论文摘要
由于SNN的事件驱动的操作可与模拟神经网络（ANN）（ANN）相比，峰值神经网络（SNNS）在边缘设备上很有希望。尽管很难有效地训练SNN，但是已经开发了许多将训练有素的ANN转换为SNN的技术。但是，转换后，SNN中存在准确性和潜伏期之间的权衡关系，从而在大型数据集（例如ImageNet）中导致相当大的延迟。我们提出了一种称为TCL的技术，以减轻权衡问题，使Imagenet的准确性为73.87％（VGG-16）和70.37％（RESNET-34），用于Imagenet，SNN中有250个周期的中等延迟。
Spiking-neural-networks (SNNs) are promising at edge devices since the event-driven operations of SNNs provides significantly lower power compared to analog-neural-networks (ANNs). Although it is difficult to efficiently train SNNs, many techniques to convert trained ANNs to SNNs have been developed. However, after the conversion, a trade-off relation between accuracy and latency exists in SNNs, causing considerable latency in large size datasets such as ImageNet. We present a technique, named as TCL, to alleviate the trade-off problem, enabling the accuracy of 73.87% (VGG-16) and 70.37% (ResNet-34) for ImageNet with the moderate latency of 250 cycles in SNNs.
