Research Area:  Machine Learning

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 errorprone 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:  

Author(s) Name:  Thomas Elsken, Jan Hendrik Metzen, Frank Hutter

Publisher name:  JMLR

DOI:  

Volume Information:  papes 1-21

Paper Link:   https://jmlr.org/papers/v20/18-598.html