通过噪声群体神经元实现同步重置，提升脉冲神经网络性能
Noisy group neurons with synchronous resetting for high-performance spiking neural networks
- 引入噪声群体神经元模型，结合群体同步重置与随机性机制
- 在CIFAR10-DVS上10步推理达87.35%准确率，优于现有方法
- 适合追求高能效脉冲神经网络的硬件部署与类脑计算研究者
脉冲神经网络（SNN）因其生物启发的神经动力学和事件驱动通信，在近年取得显著进展。然而，由于时空信息丢失和梯度不匹配，训练深层SNN仍具挑战。为此，我们提出噪声群体神经元（NGN）模型，将群体级同步重置与神经随机性作为核心计算机制。进而构建基于均场动力学反向传播的NGN方法。通过理论分析与实验验证，我们在CIFAR-10、CIFAR-100、Tiny-ImageNet、DVS-Gesture、N-Caltech101和CIFAR10-DVS数据集上展示了该方法的优势。在CIFAR10-DVS上仅用10个推理时间步即达到87.35%准确率，证明了NGN在高性能类脑计算中的实用性。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs), characterized by bio-inspired neuronal dynamics and event-driven communication, have attained significant progress in recent years. Nevertheless, training deep SNNs remains challenging due to spatiotemporal information loss and gradient mismatching. To simultaneously address these issues, we propose a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms. We then develop the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics. We demonstrate the advantages of the NGN method through theoretical analysis and experimental validation on CIFAR-10, CIFAR-100, Tiny-ImageNet, DVS-Gesture, N-Caltech101, and CIFAR10-DVS. The proposed approach achieves an accuracy of 87.35% on CIFAR10-DVS within 10 inference time steps. These results support NGN as a practical approach to high-performance neuromorphic computing.
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。