Skip to content

Latest commit

 

History

History
37 lines (31 loc) · 1.21 KB

Elsken2019Neural.md

File metadata and controls

37 lines (31 loc) · 1.21 KB

Title

Neural Architecture Search: A Survey

Author

Thomas Elsken, Jan Hendrik Metzen, Frank Hutter

Key Words

  • Neural Architecture Search
  • AutoML
  • AutoDL
  • Search Space Design
  • Search Strategy
  • Performance Estimation Strategy

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 cate- gorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

Bib

@article{JMLR:v20:18-598, author = {Thomas Elsken and Jan Hendrik Metzen and Frank Hutter}, title = {Neural Architecture Search: A Survey}, journal = {Journal of Machine Learning Research}, year = {2019}, volume = {20}, number = {55}, pages = {1-21}, url = {http://jmlr.org/papers/v20/18-598.html} }