论文标题
T2FSNN：带有时间第一跨度编码的深尖峰神经网络
T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding
论文作者
论文摘要
尖峰神经网络（SNN）由于能节能的特征而引起了极大的兴趣，但是缺乏可扩展的培训算法限制了它们在实用机器学习问题中的适用性。深处的神经网络转换方法已被广泛研究以扩大SNN的适用性。但是，大多数先前的研究都没有完全利用SNN的时空方面，这导致峰值数量和推理潜伏期的效率低下。在本文中，我们介绍了T2FSNN，该T2FSNN使用基于内核的动态阈值和树突来克服上述缺陷，将跨度尖峰编码的概念引入了深SNN。此外，我们提出了基于梯度的优化和早期射击方法，以进一步提高T2FSNN的效率。根据我们的结果，与爆发编码相比，所提出的方法可以将推理潜伏期和峰值数量减少到22％和小于1％，这是CIFAR-100的最新结果。
Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep neural network-to-SNN conversion approach has been widely studied to broaden the applicability of SNNs. Most previous studies, however, have not fully utilized spatio-temporal aspects of SNNs, which has led to inefficiency in terms of number of spikes and inference latency. In this paper, we present T2FSNN, which introduces the concept of time-to-first-spike coding into deep SNNs using the kernel-based dynamic threshold and dendrite to overcome the aforementioned drawback. In addition, we propose gradient-based optimization and early firing methods to further increase the efficiency of the T2FSNN. According to our results, the proposed methods can reduce inference latency and number of spikes to 22% and less than 1%, compared to those of burst coding, which is the state-of-the-art result on the CIFAR-100.
