Metraipolis › archive › dc_29362bd3f472

PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units — arXiv:2603.15106

Source
arXiv (en)
Original
https://arxiv.org/abs/2603.15106
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:14.696Z
SHA-256 of the archived text
34d76c9bffc9d747e70db447ee1f24209408512330c3aa9220aae9d97c777cef
Stable URL of this page
https://metraipolis.com/documento/dc_29362bd3f472

How to cite

PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units — arXiv:2603.15106 — arXiv (en), https://arxiv.org/abs/2603.15106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29362bd3f472 (Metraipolis archive dc_29362bd3f472, sha256 34d76c9bffc9d747e70db447ee1f24209408512330c3aa9220aae9d97c777cef)
BibTeX
@misc{dc29362bd3f472,
  title = {PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units — arXiv:2603.15106},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2603.15106},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29362bd3f472; sha256 34d76c9bffc9d747e70db447ee1f24209408512330c3aa9220aae9d97c777cef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2603.15106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge manual effort, one can use neural architecture search (NAS). However, many existing NAS methods are resource-intensive and time-consuming because they require the training of many different DNNs from scratch. Furthermore, they do not take the resource constraints of the target system into account. To address these shortcomings, we propose PrototypeNAS, a zero-shot NAS method to accelerate and automate the selection, compression, and specialization of DNNs to different target microcontroller units (MCUs). We propose a novel three-step search method that decouples DNN design and specialization from DNN training for a given target platform. First, we present a novel search space that not only cuts out smaller DNNs from a single large architecture, but instead combines the structural optimization of multiple architecture types, as well as optimization of their pruning and quantization configurations. Second, we explore the use of an ensemble of zero-shot proxies during optimization instead of a single one. Third, we propose the use of Hypervolume subset selection to distill DNN architectures from the Pareto front of the multi-objective optimization that represent the most meaningful tradeoffs between accuracy and FLOPs. We evaluate the effectiveness of PrototypeNAS on 12 different datasets in three different tasks: image classification, time series classification, and object detection. Our results demonstrate that PrototypeNAS is able to identify DNN models within minutes that are small enough to be deployed on off-the-shelf MCUs and still achieve accuracies comparable to the performance of large DNN models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2603.15106 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:59:48.440Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).