A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm
RProp：一种快速反向传播学习的直接自适应方法.
ADADELTA: An Adaptive Learning Rate Method
Adadelta：一种自适应学习率方法.
Don’t Decay the Learning Rate, Increase the Batch Size
通过增加批量大小代替学习率衰减.
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
InfoVAE：平衡变分自编码器的学习和推断过程.
Understanding disentangling in β-VAE
使用信息瓶颈解释β-VAE的解耦表示能力.
β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
β-VAE：学习变分自编码器隐空间的解耦表示.