arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.14550cs.LG
收藏

面向微处理器级硬件的机器学习

Machine Learning for Microcontroller-Class Hardware: A Review

University of California at Los Angeles(加州大学洛杉矶分校);Amazon(亚马逊)

Swapnil Sayan Saha, Sandeep Singh Sandha, Mani Srivastava

摘要:

机器学习的进步为低端物联网节点(如微控制器)带来了新的机遇。传统的机器学习部署具有较高的内存和计算占用,阻碍了它们在超资源受限的微控制器上的直接部署。本文重点介绍了为微控制器类设备启用板载机器学习的独特要求。研究人员针对资源有限的应用程序使用专门的模型开发工作流程,以确保计算和延迟预算在设备限制范围内,同时仍保持所需的性能。我们描述了微控制器类设备的机器学习模型开发的闭环广泛适用的工作流程,并显示了几类应用程序采用它的特定实例。我们通过展示几个用例,对模型开发的不同阶段提出了定性和数值见解。最后,我们确定了开放的研究挑战和未解决的问题,需要仔细考虑前进。

英文摘要:

The advancements in machine learning opened a new opportunity to bring intelligence to the low-end Internet-of-Things nodes such as microcontrollers. Conventional machine learning deployment has high memory and compute footprint hindering their direct deployment on ultra resource-constrained microcontrollers. This paper highlights the unique requirements of enabling onboard machine learning for microcontroller class devices. Researchers use a specialized model development workflow for resource-limited applications to ensure the compute and latency budget is within the device limits while still maintaining the desired performance. We characterize a closed-loop widely applicable workflow of machine learning model development for microcontroller class devices and show that several classes of applications adopt a specific instance of it. We present both qualitative and numerical insights into different stages of model development by showcasing several use cases. Finally, we identify the open research challenges and unsolved questions demanding careful considerations moving forward.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑