互信息论文笔记

https://github.com/topics/mutual-information

https://arxiv.org/abs/1801.04062 MINE: Mutual Information Neural Estimation

Isolating Sources of Disentanglement in Variational Autoencoders

https://arxiv.org/pdf/1802.04942.pdf

https://github.com/rtqichen/beta-tcvae

又被多传感器数据的论文引用

第一条 hierarchical disentangled representations 也使用互信息

cpc 也引用 MINE；

cpc：

多传感器数据融合和预测编码和互信息

https://arxiv.org/abs/1801.04062 MINE: Mutual Information Neural Estimation

逼近任意精度。

vae相关：

Isolating Sources of Disentanglement in Variational Autoencoders

是beta vae的改进，效果图片很多

https://github.com/rtqichen/beta-tcvae

https://github.com/miyosuda/disentangled_vae

Replicating "Understanding disentangling in β-VAE"

Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data

https://github.com/wnhsu/FactorizedHierarchicalVAE

paper 阅读：