# μNAS: Constrained Neural Architecture Search for Microcontrollers

arXiv: https://arxiv.org/abs/2010.14246 · HTML: https://mlsanity.com/paper/2010.14246/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 30 of 55)

- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities](https://mlsanity.com/paper/2210.06640/) (2022)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [A Machine Learning-oriented Survey on Tiny Machine Learning](https://mlsanity.com/paper/2309.11932/) (2023)
- [Differentiable Network Pruning for Microcontrollers](https://mlsanity.com/paper/2110.08350/) (2021)
- [Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO](https://mlsanity.com/paper/2311.01057/) (2023)
- [Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems](https://mlsanity.com/paper/2307.05999/) (2023)
- [LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms](https://mlsanity.com/paper/2311.11420/) (2023)
- [UDC: Unified DNAS for Compressible TinyML Models](https://mlsanity.com/paper/2201.05842/) (2022)
- [AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing](https://mlsanity.com/paper/2305.10459/) (2023)
- [PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization](https://mlsanity.com/paper/2307.09488/) (2023)
- [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://mlsanity.com/paper/2311.11883/) (2023)
- [Measuring what Really Matters: Optimizing Neural Networks for TinyML](https://mlsanity.com/paper/2104.10645/) (2021)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers](https://mlsanity.com/paper/2310.18384/) (2023)
- [Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices](https://mlsanity.com/paper/2310.07217/) (2023)
- [Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks](https://mlsanity.com/paper/2407.01054/) (2024)
- [MicroNAS: Zero-Shot Neural Architecture Search for MCUs](https://mlsanity.com/paper/2401.08996/) (2024)
- [TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT](https://mlsanity.com/paper/2104.02233/) (2021)
- [BOMP-NAS: Bayesian Optimization Mixed Precision NAS](https://mlsanity.com/paper/2301.11810/) (2023)
- [UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers](https://mlsanity.com/paper/2402.09264/) (2024)
- [MONAS: Efficient Zero-Shot Neural Architecture Search for MCUs](https://mlsanity.com/paper/2408.15034/) (2024)
- [From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices](https://mlsanity.com/paper/2507.23536/) (2025)
- [Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering](https://mlsanity.com/paper/2204.14103/) (2022)
- [Tackling Neural Architecture Search With Quality Diversity Optimization](https://mlsanity.com/paper/2208.00204/) (2022)
- [Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution](https://mlsanity.com/paper/2211.17246/) (2022)
- [Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation](https://mlsanity.com/paper/2502.12690/) (2025)

## 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.