Neural Architecture Search

University of Freiburg · Robert Bosch (Germany)

Indexed incrossref

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.

Citation impact

708
total citations
FWCI
75.21
Percentile
100%
References
79
Citations per year

Authors

3

Topics & keywords

Keywords
  • Computer science
  • Categorization
  • Artificial intelligence
  • Architecture
  • Process (computing)
  • Artificial neural network
  • Variety (cybernetics)
  • Machine learning
No related works found for this paper.

Funding