用穿孔反向传播让关键词识别模型更小更快还更准
Perforated Neural Networks for Keyword Spotting
- 在卷积网络中加入人工树突节点，提升模型表达能力
- 仅1500参数就达93.3%准确率，优于4000参数的基准模型
- 适合资源受限的边缘设备部署，尤其看重效率的AI工程师
边缘机器学习面临严格的内存限制、计算资源匮乏和不可妥协的精度要求。现有压缩优化技术通常只能在资源间权衡，很少能同时提升精度和缩小模型。本文将穿孔反向传播应用于Edge Impulse平台的关键词识别任务，在2025年12月举办的Edge Impulse 2025黑客松中获得最佳模型奖。通过在标准卷积神经网络中添加人工树突节点，并在800次超参数试验中验证，树突模型在所有参数量级和精度阈值下均优于传统架构。最优树突模型仅用1,500个参数即达到93.3%测试准确率，而基线模型需约4,000参数才能达到92.1%准确率。结果表明，穿孔反向传播是边缘AI工程师工具箱中的有力补充，可同时提升模型质量与部署效率。
原文摘要 · Abstract (English)
Edge machine learning presents a unique set of constraints not encountered in cloud-scale model deployment: strict memory budgets, limited compute, and non-negotiable accuracy thresholds must all be satisfied simultaneously. Existing compression and optimization techniques can trade one resource for another, but rarely improve both accuracy and model size at the same time. This paper presents the application of Perforated Backpropagation to keyword spotting on the Edge Impulse platform, an experiment that won the Best Model award at the Edge Impulse 2025 Hackathon in December 2025. By adding artificial Dendrite Nodes to a standard convolutional neural network trained on the Edge Impulse keyword spotting tutorial pipeline, we demonstrate that dendritic models outperform traditional architectures at every level of parameter count and at every accuracy threshold tested across 800 hyperparameter trials. The best dendritic model achieved a test accuracy of 0.933 with only 1,500 parameters, versus the baseline accuracy of 0.921 requiring approximately 4,000 parameters. These results suggest that Perforated Backpropagation is a powerful addition to the edge AI engineer's toolkit, offering simultaneous gains in both model quality and deployment efficiency.
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。