Adam: A Method for Stochastic Optimization
Adam：自适应矩估计.
On the importance of initialization and momentum in deep learning
Nesterov Momentum：一种动量梯度更新方法.
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.