EtinyNet: Extremely Tiny Network for TinyML

Kunran Xu, Yishi Li, Huawei Zhang, Rui Lai, Lin Gu

AAAI 2022 pp. 4628-4636

doi:10.1609/AAAI.V36I4.20387 /aaai/2022/xu2022aaai-etinynet/

Abstract

There are many AI applications in high-income countries because their implementation depends on expensive GPU cards (~2000$) and reliable power supply (~200W). To deploy AI in resource-poor settings on cheaper (~20$) and low-power devices (

PDF AAAI Semantic Scholar

Cite

Text

Xu et al. "EtinyNet: Extremely Tiny Network for TinyML." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I4.20387

Markdown

[Xu et al. "EtinyNet: Extremely Tiny Network for TinyML." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/xu2022aaai-etinynet/) doi:10.1609/AAAI.V36I4.20387

BibTeX

@inproceedings{xu2022aaai-etinynet,
  title     = {{EtinyNet: Extremely Tiny Network for TinyML}},
  author    = {Xu, Kunran and Li, Yishi and Zhang, Huawei and Lai, Rui and Gu, Lin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {4628-4636},
  doi       = {10.1609/AAAI.V36I4.20387},
  url       = {https://mlanthology.org/aaai/2022/xu2022aaai-etinynet/}
}