MicroNAS: Zero-Shot Neural Architecture Search for MCUs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910299618017280 |
|---|---|
| author | Qiao, Ye Xu, Haocheng Zhang, Yifan Huang, Sitao |
| author_facet | Qiao, Ye Xu, Haocheng Zhang, Yifan Huang, Sitao |
| contents | Neural Architecture Search (NAS) effectively discovers new Convolutional Neural Network (CNN) architectures, particularly for accuracy optimization. However, prior approaches often require resource-intensive training on super networks or extensive architecture evaluations, limiting practical applications. To address these challenges, we propose MicroNAS, a hardware-aware zero-shot NAS framework designed for microcontroller units (MCUs) in edge computing. MicroNAS considers target hardware optimality during the search, utilizing specialized performance indicators to identify optimal neural architectures without high computational costs. Compared to previous works, MicroNAS achieves up to 1104x improvement in search efficiency and discovers models with over 3.23x faster MCU inference while maintaining similar accuracy |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08996 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MicroNAS: Zero-Shot Neural Architecture Search for MCUs Qiao, Ye Xu, Haocheng Zhang, Yifan Huang, Sitao Machine Learning Artificial Intelligence Neural Architecture Search (NAS) effectively discovers new Convolutional Neural Network (CNN) architectures, particularly for accuracy optimization. However, prior approaches often require resource-intensive training on super networks or extensive architecture evaluations, limiting practical applications. To address these challenges, we propose MicroNAS, a hardware-aware zero-shot NAS framework designed for microcontroller units (MCUs) in edge computing. MicroNAS considers target hardware optimality during the search, utilizing specialized performance indicators to identify optimal neural architectures without high computational costs. Compared to previous works, MicroNAS achieves up to 1104x improvement in search efficiency and discovers models with over 3.23x faster MCU inference while maintaining similar accuracy |
| title | MicroNAS: Zero-Shot Neural Architecture Search for MCUs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.08996 |