Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics, yet computational simplicity. Despite theoretically predicted benefits, challenges in parameter initialization and efficient learning inhibited the implementation of RF networks, constraining their use to a single layer. In this paper, we address these shortcomings by deriving the RF neuron as a structured state space model (SSM) from the HiPPO framework. We introduce S5-RF, a new SSM layer comprised of RF neurons based on the S5 model, that features a generic initialization scheme and fast training within a deep architecture. S5-RF scales for the first time a RF network to a deep SNN with up to four layers and achieves with 78.8% a new state-of-the-art result for recurrent SNNs on the Spiking Speech Commands dataset in under three hours of training time. Moreover, compared to the reference SNNs that solve our benchmarking tasks, it achieves similar performance with much fewer spiking operations. Our code is publicly available at https://github.com/ThomasEHuber/s5-rf.

翻译：脉冲神经网络（SNNs）为基于事件传感器数据的神经形态处理提供了一种有前景的计算范式。其中，共振激发（RF）神经元因其生物合理性、复杂动力学特性及计算简洁性而备受关注。尽管理论上具有优势，但参数初始化与高效学习方面的挑战阻碍了RF网络的实现，使其长期局限于单层结构。本文通过从HiPPO框架推导出RF神经元作为结构化状态空间模型（SSM），解决了这些缺陷。我们提出了S5-RF——一种基于S5模型、由RF神经元构成的新型SSM层，该层具备通用初始化方案并能实现深层架构下的快速训练。S5-RF首次将RF网络扩展至多达四层的深度SNN，在Spiking Speech Commands数据集上以不足三小时的训练时间取得了78.8%的准确率，为循环SNN创造了新的最优结果。此外，与解决我们基准测试任务的参考SNN相比，S5-RF仅需更少的脉冲操作即可达到同等性能。我们的代码已公开于https://github.com/ThomasEHuber/s5-rf。