面向资源受限的微控制器的机器学习和推断技术

May, 2023

面向资源受限的微控制器的机器学习和推断技术

Towards Machine Learning and Inference for Resource-constrained MCUs

Yushan Huang, Hamed Haddadi

TL;DR本文提出了一种适用于微控制器单元(MCUs)的无电池ML推理和模型个性化管道，使用此管道在深海中进行了鱼类图像识别并比较其准确性，运行时长，功率和能源消耗等优劣，结果表明，在MCUs上可以实现97.78％的精度，达到了无电池ML推理的可行性。

Abstract

machine learning (ML) is moving towards edge devices. However, ML models with high computational demands and energy consumption pose challenges for ML inference in resource-constrained environments, such as the <