Published in IEEE Sensors Journal. Cite this as: S. S. Saha, S. S. Sandha and M. Srivastava, "Machine Learning for Microcontroller-Class Hardware: A Review," in IEEE Sensors Journal, vol. 22, no. 22, pp. 21362-21390, 15 Nov., 2022
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.
PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors
École Polytechnique(巴黎综合理工学院);Freie Universität Berlin(柏林自由大学);Berlin University of Applied Sciences (BHT)(柏林应用科技大学);HES-SO Valais-Wallis(瓦莱州瓦利斯高等专业学院);Inria(法国国家信息与自动化研究所)
Hardware-Aware Neural Feature Extraction for Resource-Constrained Devices
Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano(电子、信息与生物工程系(DEIB),米兰理工学院);Smart Eyewear Lab, EssilorLuxottica(智能眼镜实验室,EssilorLuxottica)
Imperial College London London United Kingdom;Nokia Bell Labs London United Kingdom;Brave Software \& University of Cambridge London United Kingdom;Imperial College London;Nokia Bell Labs;Brave Software \& University of Cambridge
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller
Integrated Systems Laboratory, ETH Zürich(苏黎世联邦理工学院集成系统实验室);DEI, University of Bologna(博洛尼亚大学电气、电子与信息工程系)
Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables