# Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices

arXiv: https://arxiv.org/abs/2310.07217 · HTML: https://mlsanity.com/paper/2310.07217/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution](https://mlsanity.com/paper/1804.09081/) (2018)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Can weight sharing outperform random architecture search? An investigation with TuNAS](https://mlsanity.com/paper/2008.06120/) (2020)
- [DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs](https://mlsanity.com/paper/2008.07127/) (2020)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [Visual Wake Words Dataset](https://mlsanity.com/paper/1906.05721/) (2019)
- [Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2006.05822/) (2020)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search](https://mlsanity.com/paper/2102.11646/) (2021)
- [Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge](https://mlsanity.com/paper/2301.10281/) (2023)
- [UDC: Unified DNAS for Compressible TinyML Models](https://mlsanity.com/paper/2201.05842/) (2022)
- [Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks](https://mlsanity.com/paper/2206.00302/) (2022)

## Built on by (most cited first, 7 of 7)

- [Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons](https://mlsanity.com/paper/2510.01439/) (2025)
- [Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones](https://mlsanity.com/paper/2402.15273/) (2024)
- [Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time](https://mlsanity.com/paper/2409.18566/) (2024)
- [Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems](https://mlsanity.com/paper/2412.20201/) (2024)
- [UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification](https://mlsanity.com/paper/2606.14735/) (2026)
- [Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras](https://mlsanity.com/paper/2607.28293/) (2026)
- [Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study](https://mlsanity.com/paper/2609.30553/) (2026)

## Abstract (arXiv)

The rapid proliferation of computing domains relying on Internet of Things (IoT) devices has created a pressing need for efficient and accurate deep-learning (DL) models that can run on low-power devices. However, traditional DL models tend to be too complex and computationally intensive for typical IoT end-nodes. To address this challenge, Neural Architecture Search (NAS) has emerged as a popular design automation technique for co-optimizing the accuracy and complexity of deep neural networks. Nevertheless, existing NAS techniques require many iterations to produce a network that adheres to specific hardware constraints, such as the maximum memory available on the hardware or the maximum latency allowed by the target application. In this work, we propose a novel approach to incorporate multiple constraints into so-called Differentiable NAS optimization methods, which allows the generation, in a single shot, of a model that respects user-defined constraints on both memory and latency in a time comparable to a single standard training. The proposed approach is evaluated on five IoT-relevant benchmarks, including the MLPerf Tiny suite and Tiny ImageNet, demonstrating that, with a single search, it is possible to reduce memory and latency by 87.4% and 54.2%, respectively (as defined by our targets), while ensuring non-inferior accuracy on state-of-the-art hand-tuned deep neural networks for TinyML.