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

Robert Wu, Nayan Saxena, Rohan Jain

[AAAI-22] Student Abstract and Poster Program - FINALIST

Keywords
Poster Session 6 @ Blue 4, Poster Session 10 @ Blue 4, Poster Session 6, Poster Session 10

Download Paper
Enter the Virtual Venue
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.

Introduction Video

Sessions where this paper appears

  • Poster Session 6

    Blue 4

  • Poster Session 10

    Blue 4