逐层降低以训练非常深的神经网络

Nov, 2015

Gradual DropIn of Layers to Train Very Deep Neural Networks

Leslie N. Smith, Emily M. Hand, Timothy Doster

TL;DR通过DropIn层动态增加神经网络的深度，提供训练过程中的正则化，并在多个实验中证明了其有效性。

Abstract

We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a t