让神经网络提前退出，大幅降低边缘设备的能耗与计算量。
SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
- 用强化学习控制神经网络提前退出，动态减少计算量。
- 在多个模型上实现能耗降90%以上，准确率比同类高5.15%。
- 适合对功耗敏感的实时边缘AI应用，如智能传感与可穿戴设备。
脉冲神经网络（SNN）因其事件驱动的计算模式具有天然能效优势，适合部署于边缘AI场景。然而，深层架构带来的计算开销以及缺乏输入自适应控制限制了其实际应用。本文提出SPARQ框架，统一整合脉冲计算、量化感知训练与强化学习引导的早退机制，实现高效自适应推理。在MLP、LeNet和AlexNet等架构上的评估表明，所提出的量化动态SNN（QDSNN）持续优于传统SNN与QSNN，在不同数据集上相比基准SNN系统能耗降低超330倍，突触操作减少超过90%，准确率相较QSNN最高提升5.15%。结果验证了SPARQ作为硬件友好、能效优越的边缘实时AI解决方案的有效性。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep architectures and the absence of input-adaptive control. This work presents SPARQ, a unified framework that integrates spiking computation, quantization-aware training, and reinforcement learning-guided early exits for efficient and adaptive inference. Evaluations across MLP, LeNet, and AlexNet architectures demonstrated that the proposed Quantised Dynamic SNNs (QDSNN) consistently outperform conventional SNNs and QSNNs, achieving up to 5.15% higher accuracy over QSNNs, over 330 times lower system energy compared to baseline SNNs, and over 90 percent fewer synaptic operations across different datasets. These results validate SPARQ as a hardware-friendly, energy-efficient solution for real-time AI at the edge.
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。