BriefGPT.xyz
Apr, 2018
利用线性自编码器从主子空间提取主成分
From Principal Subspaces to Principal Components with Linear Autoencoders
HTML
PDF
Elad Plaut
TL;DR
本文介绍了使用一种单隐层全连接自编码器进行特征提取可以有效地恢复主成分分析(PCA)的加载向量, 且训练权重与PCA加载向量存在差异, 从而优化特征提取的性能。
Abstract
The
autoencoder
is an effective
unsupervised learning
model which is widely used in
deep learning
. It is well known that an
→