mlsanityData to 7 Oct 2026

μNAS: Constrained Neural Architecture Search for Microcontrollers

arXiv 2010.14246 ↗First posted 27 Oct 2020cs.LG cs.ARcited by 54

Not on the map. Why?

Abstract (arXiv)

IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer computational resources than is typically required for deep learning. Designing neural networks for such a platform requires an intricate balance between keeping high predictive performance (accuracy) while achieving low memory and storage usage and inference latency. This is extremely challenging to achieve manually, so in this work, we build a neural architecture search (NAS) system, called μNAS, to automate the design of such small-yet-powerful MCU-level networks. μNAS explicitly targets the three primary aspects of resource scarcity of MCUs: the size of RAM, persistent storage and processor speed. μNAS represents a significant advance in resource-efficient models, especially for "mid-tier" MCUs with memory requirements ranging from 0.5 KB to 64 KB. We show that on a variety of image classification datasets μNAS is able to (a) improve top-1 classification accuracy by up to 4.8%, or (b) reduce memory footprint by 4--13x, or (c) reduce the number of multiply-accumulate operations by at least 2x, compared to existing MCU specialist literature and resource-efficient models.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 14; 2024: 10; 2025: 9; 2026: 6.

54 papers.

Sort:

By area:

  1. 2022On-Device Training Under 256KB Memorycited by 158
  2. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 87
  3. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  4. 2024Tiny Machine Learning: Progress and Futurescited by 40
  5. 2022Compute-Efficient Deep Learning: Algorithmic Trends and Opportunitiescited by 38
  6. 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
  7. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 26
  8. 2021Differentiable Network Pruning for Microcontrollerscited by 15
  9. 2023Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOcited by 15
  10. 2023Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systemscited by 11
  11. 2023LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platformscited by 11
  12. 2022UDC: Unified DNAS for Compressible TinyML Modelscited by 10
38 more
  1. 2023AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computingcited by 10
  2. 2023PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimizationcited by 9
  3. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  4. 2021Measuring what Really Matters: Optimizing Neural Networks for TinyMLcited by 8
  5. 2023Enabling Resource-efficient AIoT System with Cross-level Optimization: A surveycited by 8
  6. 2023Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devicescited by 7
  7. 2023MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollerscited by 7
  8. 2024Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networkscited by 6
  9. 2024MicroNAS: Zero-Shot Neural Architecture Search for MCUscited by 5
  10. 2021TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNTcited by 4
  11. 2023BOMP-NAS: Bayesian Optimization Mixed Precision NAScited by 4
  12. 2024UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollerscited by 4
  13. 2024MONAS: Efficient Zero-Shot Neural Architecture Search for MCUscited by 4
  14. 2025From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devicescited by 4
  15. 2022Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clusteringcited by 3
  16. 2022Tackling Neural Architecture Search With Quality Diversity Optimizationcited by 3
  17. 2022Pex: Memory-efficient Microcontroller Deep Learning through Partial Executioncited by 3
  18. 2025msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyMLcited by 3
  19. 2025Energy-Aware Deep Learning on Resource-Constrained Hardwarecited by 3
  20. 2022Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Imagescited by 2
  21. 2022Enhancing Efficiency in Multidevice Federated Learning through Data Selectioncited by 2
  22. 2023REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraintscited by 2
  23. 2024TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Searchcited by 2
  24. 2024Designing Extremely Memory-Efficient CNNs for On-device Vision Taskscited by 2
  25. 2024Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Searchcited by 2
  26. 2024DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Acceleratorscited by 2
  27. 2025Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluationcited by 2
  28. 2026InstMeter: An Instruction-Level Method to Predict Energy and Latency of DL Model Inference on MCUscited by 2
  29. 2026An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platformscited by 2
  30. 2023Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearablescited by 1
  31. 2025MicroNAS: An Automated Framework for Developing a Fall Detection Systemcited by 1
  32. 2025Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Trainingcited by 1
  33. 2025AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networkscited by 1
  34. 2026Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devicescited by 1
  35. 2021Adaptive Subsampling for ROI-based Visual Tracking: Algorithms and FPGA Implementationcited by 0
  36. 2023DietCNN: Multiplication-free Inference for Quantized CNNscited by 0
  37. 2024emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognitioncited by 0
  38. 2025Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classificationcited by 0

50 most cited of 54 All 54 (JSON)