NeuralArTS: Structuring Neural Architecture Search with Type Theory

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 fr...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-11
Main Authors: Wu, Robert, Saxena, Nayan, Jain, Rohan
Format: Article
Language:English
Subjects:
Algorithms
Machine learning
Searching
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422