mlsanityData to 7 Oct 2026

TinyOL: TinyML with Online-Learning on Microcontrollers

arXiv 2103.08295 ↗First posted 15 Mar 2021cs.LG cs.DC cs.SYcited by 65

Not on the map. Why?

Abstract (arXiv)

Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved significant advancement in the last few years. However, the current TinyML solutions are based on batch/offline settings and support only the neural network's inference on MCUs. The neural network is first trained using a large amount of pre-collected data on a powerful machine and then flashed to MCUs. This results in a static model, hard to adapt to new data, and impossible to adjust for different scenarios, which impedes the flexibility of the Internet of Things (IoT). To address these problems, we propose a novel system called TinyOL (TinyML with Online-Learning), which enables incremental on-device training on streaming data. TinyOL is based on the concept of online learning and is suitable for constrained IoT devices. We experiment TinyOL under supervised and unsupervised setups using an autoencoder neural network. Finally, we report the performance of the proposed solution and show its effectiveness and feasibility.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 12 of its 25 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

12 of 25 references.

References · 12

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  3. 2018End-to-End Incremental Learningcited by 596
  4. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 269
  5. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 161
  6. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 116
  7. 2020River: machine learning for streaming data in Pythoncited by 96
  8. 2018BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOScited by 10
  9. 2018Deep Active Learning for Anomaly Detectioncited by 10
  10. 2019Training on the Edge: The why and the howcited by 9
  11. 2020The Case for Retraining of ML Models for IoT Device Identification at the Edgecited by 6
  12. 2020Enabling Incremental Knowledge Transfer for Object Detection at the Edgecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 7; 2023: 9; 2024: 24; 2025: 12; 2026: 9.

65 papers.

Sort:

  1. 2022On-Device Training Under 256KB Memorycited by 158
  2. 2024Tiny Machine Learning: Progress and Futurescited by 40
  3. 2021A TinyML Platform for On-Device Continual Learning with Quantized Latent Replayscited by 37
  4. 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
  5. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 26
  6. 2022On-device Training: A First Overview on Existing Systemscited by 18
  7. 2023TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edgecited by 18
  8. 2023TinyML: Tools, Applications, Challenges, and Future Research Directionscited by 14
  9. 2022Intelligence at the Extreme Edge: A Survey on Reformable TinyMLcited by 13
  10. 2024On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systemscited by 13
  11. 2023Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllerscited by 10
  12. 2024On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Casecited by 9
38 more
  1. 2021Tiny Machine Learning for Concept Driftcited by 7
  2. 2024QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Versioncited by 7
  3. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  4. 2021The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoTcited by 6
  5. 2022How to Manage Tiny Machine Learning at Scale: An Industrial Perspectivecited by 5
  6. 2024Lifelong Intelligence Beyond the Edge using Hyperdimensional Computingcited by 5
  7. 2024On-device Online Learning and Semantic Management of TinyML Systemscited by 5
  8. 2024TinySV: Speaker Verification in TinyML with On-device Learningcited by 5
  9. 2024On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollerscited by 5
  10. 2024A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaptioncited by 5
  11. 2024Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approachcited by 5
  12. 2025From Tiny Machine Learning to Tiny Deep Learning: A Surveycited by 5
  13. 2022Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensorscited by 4
  14. 2023RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Accelerationcited by 4
  15. 2023TinyReptile: TinyML with Federated Meta-Learningcited by 4
  16. 2023TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learningcited by 4
  17. 2024Enabling On-device Continual Learning with Binary Neural Networkscited by 4
  18. 2024On-device Self-supervised Learning of Visual Perception Tasks aboard Hardware-limited Nano-quadrotorscited by 4
  19. 2024Boosting keyword spotting through on-device learnable user speech characteristicscited by 4
  20. 2024Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mWcited by 4
  21. 2023MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaptioncited by 3
  22. 202412 mJ per Class On-Device Online Few-Shot Class-Incremental Learningcited by 3
  23. 20241-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bitcited by 3
  24. 2024On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interfacecited by 3
  25. 2024Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagationcited by 3
  26. 2021TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarioscited by 2
  27. 2023TinyMetaFed: Efficient Federated Meta-Learning for TinyMLcited by 2
  28. 2025EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Toolscited by 2
  29. 2025Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learningcited by 2
  30. 2022SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoTcited by 1
  31. 2024Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Taskscited by 1
  32. 2024StreamTinyNet: video streaming analysis with spatial-temporal TinyMLcited by 1
  33. 2024A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognitioncited by 1
  34. 2024Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devicescited by 1
  35. 2024DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computingcited by 1
  36. 2025A 1-D CNN inference engine for constrained platformscited by 1
  37. 2025TActiLE: Tiny Active LEarning for wearable devicescited by 1
  38. 2025RockNet: Distributed Learning on Ultra-Low-Power Devicescited by 1

50 most cited of 65 All 65 (JSON)