mlsanityData to 14 Oct 2026

Machine Learning for Microcontroller-Class Hardware: A Review

arXiv 2205.14550 ↗First posted 29 May 2022cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 139 of its 269 references that are in the map. First posted on arXiv 29 May 2022.

Builds on

139 of 269 references.

References · 139

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  11. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  12. 2019Searching for MobileNetV3cited by 1,994
38 more
  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  3. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  8. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  9. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
  10. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  12. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  13. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  14. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  15. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  16. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  17. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  18. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  19. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  20. 2019Hamiltonian Neural Networkscited by 712
  21. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  22. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  23. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
  24. 2018Rethinking the Value of Network Pruningcited by 599
  25. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  26. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  27. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  28. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 479
  29. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
  30. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  31. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  32. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  33. 2020Lagrangian Neural Networkscited by 398
  34. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  35. 2015Deep Learning with Limited Numerical Precisioncited by 376
  36. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  37. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  38. 2015Unitary Evolution Recurrent Neural Networkscited by 294

50 most cited of 139 All 139 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 4; 2025: 10; 2026: 6.

28 papers.

Sort:

By area:

  1. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 27
  2. 2022On-device Training: A First Overview on Existing Systemscited by 19
  3. 2023Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOcited by 15
  4. 2023Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systemscited by 11
  5. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  6. 2023Enabling Resource-efficient AIoT System with Cross-level Optimization: A surveycited by 8
  7. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  8. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 7
  9. 2025Benchmarking Ultra-Low-Power μNPUscited by 6
  10. 2023U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoTcited by 5
  11. 2025From Tiny Machine Learning to Tiny Deep Learning: A Surveycited by 5
  12. 2024DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Unitscited by 4
16 more
  1. 2025Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluationcited by 3
  2. 2025msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyMLcited by 3
  3. 2025EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Toolscited by 2
  4. 2025Robust Support Vector Machines for Imbalanced and Noisy Data via Benders Decompositioncited by 2
  5. 2025Floating-Point Neural Network Verification at the Software Levelcited by 2
  6. 2022Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razorcited by 1
  7. 2024OpTC -- A Toolchain for Deployment of Neural Networks on AURIX TC3xx Microcontrollerscited by 1
  8. 2024SepAl: Sepsis Alerts On Low Power Wearables With Digital Biomarkers and On-Device Tiny Machine Learningcited by 1
  9. 2025MambaLite-Micro: Memory-Optimized Mamba Inference on MCUscited by 1
  10. 2026FEATHer: Fourier-Efficient Adaptive Temporal Hierarchy Forecaster for Time-Series Forecastingcited by 1
  11. 2025Efficient and Accurate Downfacing Visual Inertial Odometrycited by 0
  12. 2026EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learningcited by 0
  13. 2026Towards Resilient Intrusion Detection in CubeSats: Challenges, TinyML Solutions, and Future Directionscited by 0
  14. 2026Towards Real-Time ECG and EMG Modeling on μNPUscited by 0
  15. 2026Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Camerascited by 0
  16. 2026tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobotscited by 0