794 citations · 2.7k across the 93 of their papers we have counts for
Showing 2017 · stat.MLShow all
2 papers · 2 filters
stat.ML2017★ 794 cited
Data Augmentation Generative Adversarial Networks
Antreas Antoniou, Amos Storkey, Harrison Edwards
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviate…
stat.ML2017★ 95 cited
Moonshine: Distilling with Cheap Convolutions
Elliot J. Crowley, Gavin Gray, Amos Storkey
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is lit…