用极低功耗的DWN模型实现高精度人体活动识别。
nanoML for Human Activity Recognition
- 采用可微分无权重网络（DWNs）实现高效推理
- 每样本仅耗电56nJ，比现有方法节能92.6万倍
- 适合对功耗和体积敏感的可穿戴设备
人体活动识别（HAR）在医疗、健身和物联网中至关重要，但将高精度模型部署到资源受限设备仍面临能耗与内存需求高的挑战。本文展示了可微分无权重神经网络（DWNs）在HAR中的应用，实现了96.34%和96.67%的竞争力准确率，每样本仅消耗56nJ和104nJ能量，单样本推理时间仅为5ns。DWNs在FPGA上实现并评估，验证了其在能效硬件部署中的可行性。相比当前最先进的深度学习方法，DWNs实现了高达926,000倍的能效提升和260倍的内存压缩。这些成果使DWNs成为面向边缘与可穿戴设备的纳米机器学习（nanoML）新范式，为超低功耗边缘AI树立了新基准。
原文摘要 · Abstract (English)
Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due to high energy and memory demands. This paper demonstrates the application of Differentiable Weightless Neural Networks (DWNs) to HAR, achieving competitive accuracies of 96.34% and 96.67% while consuming only 56nJ and 104nJ per sample, with an inference time of just 5ns per sample. The DWNs were implemented and evaluated on an FPGA, showcasing their practical feasibility for energy-efficient hardware deployment. DWNs achieve up to 926,000x energy savings and 260x memory reduction compared to state-of-the-art deep learning methods. These results position DWNs as a nano-machine learning nanoML model for HAR, setting a new benchmark in energy efficiency and compactness for edge and wearable devices, paving the way for ultra-efficient edge AI.
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。