GOLD-NAS: Gradual, One-Level, Differentiable

Cited by: 0|Bibtex|Views30|Links

Abstract:

There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and enlarge the search space to contain more than $10^{160}$ candidates. In the new space, most existing di...More

Code:

Data:

Your rating :
0

 

Tags
Comments