BriefGPT.xyz
Dec, 2018
变分自编码器无意中寻找主成分分析方向
Variational Autoencoders Pursue PCA Directions (by Accident)
HTML
PDF
Michal Rolinek, Dominik Zietlow, Georg Martius
TL;DR
该论文研究了变分自编码器（VAE）在学习可解释的表示和生成建模方面的出色表现，提供了对其良好性能的解释，阐明了该架构中解码器的局部正交性，从而促进重构和正交性之间的平衡。
Abstract
The
variational autoencoder
(VAE) is a powerful architecture capable of
representation learning
and
generative modeling
. When it comes to
→