提出动态权重量化方法，让脉冲神经网络更省电且几乎不丢精度。
Temporal-adaptive Weight Quantization for Spiking Neural Networks
- 根据时间动态分配极低比特权重，模拟生物神经调节机制。
- ImageNet上仅损失0.22%精度，能效达4.12M次操作、0.63mJ能耗。
- 适合追求极致能效的类脑计算与边缘智能部署场景。
脉冲神经网络（SNNs）中的权重量化可进一步降低能耗。然而，不牺牲精度地进行量化仍具挑战。受生物神经系统中星形胶质细胞介导的突触调制启发，本文提出时间自适应权重量化（TaWQ），将权重量化与时间动态结合，沿时间维度自适应分配超低比特权重。在静态数据集（如ImageNet）和类脑数据集（如CIFAR10-DVS）上的大量实验表明，所提方法在保持高能效（4.12M次操作，0.63mJ）的同时，仅带来0.22%的量化损失。
原文摘要 · Abstract (English)
Weight quantization in spiking neural networks (SNNs) could further reduce energy consumption. However, quantizing weights without sacrificing accuracy remains challenging. In this study, inspired by astrocyte-mediated synaptic modulation in the biological nervous systems, we propose Temporal-adaptive Weight Quantization (TaWQ), which incorporates weight quantization with temporal dynamics to adaptively allocate ultra-low-bit weights along the temporal dimension. Extensive experiments on static (e.g., ImageNet) and neuromorphic (e.g., CIFAR10-DVS) datasets demonstrate that our TaWQ maintains high energy efficiency (4.12M, 0.63mJ) while incurring a negligible quantization loss of only 0.22% on ImageNet.
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。