受生物钾通道启发，新神经元模型提升脉冲网络容量与抗噪能力。
Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
- 引入钾离子调节机制，动态调整神经元兴奋性与重置
- 在多个数据集上准确率提升，噪声下性能更稳定
- 兼顾生物合理性与低功耗部署，适合边缘计算
脉冲神经网络（SNN）在低功耗实时边缘计算中前景广阔，但传统漏积分放电（LIF）神经元适应性有限，信息容量受限且易受噪声干扰，导致精度下降。受生物钾通道动态调节的启发，本文提出钾离子调控的LIF（KvLIF）神经元模型。KvLIF通过引入辅助电导状态，融合膜电位与放电历史，自适应调节神经元兴奋性和重置机制。该设计扩展了神经元对不同输入强度的响应范围，并有效抑制噪声诱发的误放电。我们在静态图像和类脑数据集上广泛评估，结果表明KvLIF在分类准确率和鲁棒性方面均优于现有LIF模型。本工作实现了生物合理性与计算效率的平衡，为低功耗类脑部署提供了高性能神经元模型。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.
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。