提出自适应重置脉冲神经元，提升能效与精度
AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks
- 设计自适应重置机制，动态关联输入输出与重置
- 在Tiny-ImageNet和CIFAR10-DVS上达当前最优准确率
- 兼顾低功耗特性，适合边缘部署的脉冲神经网络
脉冲神经网络因其事件驱动特性具有低能耗优势。除二值脉冲输出外，其内在浮点动力学值得更多关注。神经元阈值与重置模式显著影响脉冲数量与时间。硬重置导致信息丢失，软重置则对所有神经元统一处理。为此，我们设计了一种自适应重置神经元，建立输入、输出与重置之间的关联，并集成简单有效的阈值调整策略。实验表明，该方法在保持低能耗的同时取得优异性能，在Tiny-ImageNet和CIFAR10-DVS上达到当前最优准确率。代码已开源。
原文摘要 · Abstract (English)
Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically determine spike count and timing. Hard reset cause information loss, while soft reset apply uniform treatment to neurons. To address these issues, we design an adaptive reset neuron that establishes relationships between inputs, outputs, and reset, while integrating a simple yet effective threshold adjustment strategy. Experimental results demonstrate that our method achieves excellent performance while maintaining lower energy consumption. In particular, it attains state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS. Codes are available at https://github.com/2ephyrus/AR-LIF.
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。