452 citations · 1.2k across the 5 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 393 cited
SMASH: One-Shot Model Architecture Search through HyperNetworks
Andrew Brock, Theodore Lim, J. M. Ritchie +1
Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning…
stat.ML2017★ 75 cited
FreezeOut: Accelerate Training by Progressively Freezing Layers
Andrew Brock, Theodore Lim, J. M. Ritchie +1
The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set…