The tremendous energy consumption of deep neural networks (DNNs) has become a serious problem in deep learning. Spiking neural networks (SNNs), which mimic the operations in the human brain, have been studied as prominent energy-efficient neural networks. Due to their event-driven and spatiotemporally sparse operations, SNNs show possibilities for energy-efficient processing. To unlock their potential, deep SNNs have adopted temporal coding such as time-to-first-spike (TTFS)coding, which represents the information between neurons by the first spike time. With TTFS coding, each neuron generates one spike at most, which leads to a significant improvement in energy efficiency. Several studies have successfully introduced TTFS coding in deep SNNs, but they showed restricted efficiency improvement owing to the lack of consideration for efficiency during training. To address the aforementioned issue, this paper presents training methods for energy-efficient deep SNNs with TTFS coding. We introduce a surrogate DNN model to train the deep SNN in a feasible time and analyze the effect of the temporal kernel on training performance and efficiency. Based on the investigation, we propose stochastically relaxed activation and initial value-based regularization for the temporal kernel parameters. In addition, to reduce the number of spikes even further, we present temporal kernel-aware batch normalization. With the proposed methods, we could achieve comparable training results with significantly reduced spikes, which could lead to energy-efficient deep SNNs.
翻译:深神经网络(DNNS)的巨大能源消耗已成为深层学习的一个严重问题。 模仿人脑操作的神经网络(SNNS)被研究为显著的节能神经网络。 由于其由事件驱动和间歇性零星的操作,SNNIS展示了节能加工的可能性。 为了释放其潜力,深神经网络采用了时间编码方法,如时间到第一次跳跃(TTFS)编码(TTFS)编码,这代表了神经在第一次跳跃时之间的信息。随着TTTFS编码的建立,每个神经网络(SNNN)最多产生一次激增,从而导致能源效率的显著提高。 几项研究成功地将TTFS编码引入了深度智能神经网络(SNNIS)的编码,但由于在培训过程中对效率的考虑不足,效率也有限。 为了解决上述问题,本文件提出了节能深度的深SNNIS(TFS)编码(TTFS)的进一步编码。 我们引入了一种秘密的DNNN模型,以在可行的时间里培训深度SNNN(E), 分析可比的温度训练结果的影响,我们甚至可以大幅降低SKERNNNNER(S) 的初始温度温度调整的值,我们提出S-K(S-ralker(S)的温度)的测试)的测试,我们建议了S-tradestral-tradestral-tradustrationaltoal)的进度和效率。