论文标题
Spikemax：基于尖峰的分类损失方法
Spikemax: Spike-based Loss Methods for Classification
论文作者
论文摘要
尖峰神经网络〜（SNN）是低功率基于计算的有前途的研究范例。 SNN返回传播的最新作品使SNN培训了实用任务。但是，由于峰值是二进制事件，因此标准损失公式与峰值输出不直接兼容。结果，当前的作品仅限于使用于点的尖峰计数丢失。在本文中，我们从尖峰计数度量中制定了输出概率解释，并引入了基于尖峰的负模样措施，这更适合分类任务，尤其是在能源效率和推理延迟方面。我们将损失度量与其他现有替代方案进行比较，并在三个神经形态基准数据集上使用分类性能进行评估：NMNIST，DVS手势和N-Tidigits18。此外，我们在这些数据集上展示了最先进的表现，从而实现了更快的推理速度和更少的能耗。
Spiking Neural Networks~(SNNs) are a promising research paradigm for low power edge-based computing. Recent works in SNN backpropagation has enabled training of SNNs for practical tasks. However, since spikes are binary events in time, standard loss formulations are not directly compatible with spike output. As a result, current works are limited to using mean-squared loss of spike count. In this paper, we formulate the output probability interpretation from the spike count measure and introduce spike-based negative log-likelihood measure which are more suited for classification tasks especially in terms of the energy efficiency and inference latency. We compare our loss measures with other existing alternatives and evaluate using classification performances on three neuromorphic benchmark datasets: NMNIST, DVS Gesture and N-TIDIGITS18. In addition, we demonstrate state of the art performances on these datasets, achieving faster inference speed and less energy consumption.
