Aidan N. Gomez, Ivan Zhang, Kevin Swersky, Yarin Gal, Geoffrey E. Hinton
TL;DR使用有针对性的dropout进行神经网络的训练，可以使网络更容易剪枝并且保持稀疏性。
Abstract
neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away connections or hidden units. But standard training