卷积神经网络正则化的最大池化减少丢失方法

Dec, 2015

Max-Pooling Dropout for Regularization of Convolutional Neural Networks

Haibing Wu, Xiaodong Gu

TL;DR这篇论文研究了深度学习中dropout技术在pooling layer中的应用，提出了一种基于概率加权的pooling方法，称为probabilistic weighted pooling，并通过实验证明了它的优越性。

Abstract

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, →