BriefGPT.xyz
Dec, 2014
使用嵌套 Dropout 学习紧凑的卷积神经网络
Learning Compact Convolutional Neural Networks with Nested Dropout
HTML
PDF
Chelsea Finn, Lisa Anne Hendricks, Trevor Darrell
TL;DR
研究探讨了Nested Dropout在通过反向传播训练的卷积神经网络中的应用，以确定与所需精度和所需任务和数据复杂度相对应的最佳表示大小。
Abstract
Recently,
nested dropout
has been shown as a method for ordering representation units in
autoencoders
by their information content, without diminishing reconstruction cost. However, it has only been applied to tr
→