用阻变存储器实现低功耗神经脉冲计算，实时自适应提升可穿戴设备性能。
Low-power Spike-based Wearable Analytics on RRAM Crossbars
- 在阻变存储器上用脉冲神经网络实现内存计算，支持实时在线调整。
- 相比传统反向传播，能量降低64.1%，面积减少10.1%，延迟减半，准确率提高7.55%。
- 适合资源受限的可穿戴设备，尤其适用于人体动作识别场景。
本文提出一种基于阻变存储器交叉阵列的内存计算架构，部署脉冲神经网络（SNNs）实现低功耗可穿戴分析。针对硬件限制与噪声特性，采用直接反馈对齐（DFA）实现预训练SNN的实时在线适应，替代传统反向传播（BP）。DFA支持分层并行梯度计算，具备快速、低能耗、小面积优势。通过自研硬件评估工具DFA_Sim的大量仿真表明，相比BP，DFA在人体动作识别（HAR）任务中能耗降低64.1%，面积开销减少10.1%，延迟降低2.1倍，同时推理准确率最高提升7.55%。
原文摘要 · Abstract (English)
This work introduces a spike-based wearable analytics system utilizing Spiking Neural Networks (SNNs) deployed on an In-memory Computing engine based on RRAM crossbars, which are known for their compactness and energy-efficiency. Given the hardware constraints and noise characteristics of the underlying RRAM crossbars, we propose online adaptation of pre-trained SNNs in real-time using Direct Feedback Alignment (DFA) against traditional backpropagation (BP). Direct Feedback Alignment (DFA) learning, that allows layer-parallel gradient computations, acts as a fast, energy & area-efficient method for online adaptation of SNNs on RRAM crossbars, unleashing better algorithmic performance against those adapted using BP. Through extensive simulations using our in-house hardware evaluation engine called DFA_Sim, we find that DFA achieves upto 64.1% lower energy consumption, 10.1% lower area overhead, and a 2.1x reduction in latency compared to BP, while delivering upto 7.55% higher inference accuracy on human activity recognition (HAR) tasks.
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。