English

NeuralArTS: Structuring Neural Architecture Search with Type Theory

Machine Learning 2021-11-08 v3 Logic in Computer Science Programming Languages Machine Learning

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.

Keywords

Cite

@article{arxiv.2110.08710,
  title  = {NeuralArTS: Structuring Neural Architecture Search with Type Theory},
  author = {Robert Wu and Nayan Saxena and Rohan Jain},
  journal= {arXiv preprint arXiv:2110.08710},
  year   = {2021}
}

Comments

(Student Abstract) In Proceedings of the 36th AAAI Conference on Artificial Intelligence, Vancouver, BC,Canada, 2022

R2 v1 2026-06-24T06:56:55.734Z