将共振放电神经元扩展为深度脉冲网络，3小时达成新纪录
Scaling Up Resonate-and-Fire Networks for Fast Deep Learning
- 将共振放电神经元重构为结构化状态空间模型，支持深层架构
- 4层网络在语音命令数据集上达78.8%准确率，训练<3小时
- 相比同类模型，同等性能下减少大量脉冲操作，适合低功耗场景
脉冲神经网络（SNN）为事件驱动传感器数据的类脑处理提供了前景。其中，共振放电（RF）神经元因其生物合理性、复杂动态与计算简洁性备受关注。尽管理论上优势显著，但参数初始化与高效学习难题长期限制其应用仅限单层。本文通过将RF神经元从HiPPO框架推导为结构化状态空间模型（SSM），提出S5-RF——一种基于S5模型的新型SSM层，具备通用初始化方案与快速训练能力。S5-RF首次实现4层深度RF网络，于不到3小时训练时间内，在Spiking Speech Commands数据集上达到78.8%的新记录准确率。相较基准SNN模型，其在相同任务上表现相当，但脉冲操作数大幅减少。代码已公开于https://github.com/ThomasEHuber/s5-rf。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。