Abstract

Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

Keywords

Computer scienceCategorizationArtificial intelligenceArchitectureVariety (cybernetics)Machine learningField (mathematics)Process (computing)Artificial neural networkMachine translationDeep learningGeography

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
preprint
Citations
1399
Access
Closed

External Links

Social Impact

Altmetric

Social media, news, blog, policy document mentions

Citation Metrics

1399
OpenAlex

Cite This

Thomas Elsken, Jan Hendrik Metzen, Frank Hutter (2018). Neural Architecture Search: A Survey. arXiv (Cornell University) . https://doi.org/10.48550/arxiv.1808.05377

Identifiers

DOI
10.48550/arxiv.1808.05377