Macro neural architecture search revisited

Hanzhang Hu
Hanzhang Hu
John Langford
John Langford
Rich Caruana
Rich Caruana
Eric Horvitz
Eric Horvitz

2nd Workshop on Meta-Learning at NeurIPS, 2018.

Cited by: 1|Bibtex|Views6

Abstract:

Neural architecture search (NAS) has recently shown promising results for automatically finding cost-efficient and accurate predictors. However, most recent work exclusively study the small search space of repeatable network modules (cells), instead of the more general overall network (macro), partially because the models found by macro-s...More

Code:

Data:

Your rating :
0

 

Tags
Comments