Machine Learning for Microcontroller-Class Hardware: A Review

Abstract

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.

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

References in corpus (16)

• Deep Learning in Neural Networks: An Overview
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Neural Architecture Search with Reinforcement Learning
• WaveNet: A Generative Model for Raw Audio
• Deep Learning with Limited Numerical Precision
• To prune, or not to prune: exploring the efficacy of pruning for model compression
• Lite Transformer with Long-Short Range Attention
• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
• Visual Wake Words Dataset
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks
• Zero-Cost Proxies for Lightweight NAS
• Rethinking Generalization in American Sign Language Prediction for Edge Devices with Extremely Low Memory Footprint
• Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)
• Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks
• The Ramifications of Making Deep Neural Networks Compact

Cited by in corpus (13)

• Intelligence at the Extreme Edge: A Survey on Reformable TinyML
• On-device Training: A First Overview on Existing Systems
• Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
• SepAl: Sepsis Alerts On Low Power Wearables With Digital Biomarkers and On-Device Tiny Machine Learning
• DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units
• Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
• EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Tools
• U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT
• Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors
• Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
• Design and implementation of intelligent packet filtering in IoT microcontroller-based devices
• Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
• From Tiny Machine Learning to Tiny Deep Learning: A Survey