ML Anthology

NeuralArTS: Structuring Neural Architecture Search with Type Theory (Student Abstract)

Robert Wu, Nayan Saxena, Rohan Jain
AAAI 2022 pp. 13085-13086
doi:10.1609/AAAI.V36I11.21679 /aaai/2022/wu2022aaai-neuralarts/

Abstract

Neural Architecture Search (NAS) algorithms automate the task of finding optimal deep learning architectures given an initial search space of possible operations. Developing these search spaces is usually a manual affair with pre-optimized search spaces being more efficient, rather than searching from scratch. In this paper we present a new framework called Neural Architecture Type System (NeuralArTS) that categorizes the infinite set of network operations in a structured type system. We further demonstrate how NeuralArTS can be applied to convolutional layers and propose several future directions.

PDF AAAI Semantic Scholar

Cite

Text

Wu et al. "NeuralArTS: Structuring Neural Architecture Search with Type Theory (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21679

Markdown

[Wu et al. "NeuralArTS: Structuring Neural Architecture Search with Type Theory (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/wu2022aaai-neuralarts/) doi:10.1609/AAAI.V36I11.21679

BibTeX

@inproceedings{wu2022aaai-neuralarts,
  title     = {{NeuralArTS: Structuring Neural Architecture Search with Type Theory (Student Abstract)}},
  author    = {Wu, Robert and Saxena, Nayan and Jain, Rohan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {13085-13086},
  doi       = {10.1609/AAAI.V36I11.21679},
  url       = {https://mlanthology.org/aaai/2022/wu2022aaai-neuralarts/}
}