20 Deep Generative Models

20.1 Boltzmann Machines

20.2 Restricted Boltzmann Machines

20.2.1 Conditional Distributions

20.2.2 Training Restricted Boltzmann Machines

20.3 Deep Belief Networks

20.4 Deep Boltzmann Machines

20.4.1 Interesting Properties

20.4.2 DBM Mean Field Inference

20.4.3 DBM Parameter Learning

20.4.4 Layer-Wise Pretraining

20.4.5 Jointly Training Deep Boltzmann Machines

centered deep Boltzmann machine

multi-prediction deep Boltzmann machine

20.5 Boltzmann Machines for Real-Valueed Data

20.5.1 Gaussian-Bernoulli RBMs

20.5.2 Undirected Models of Conditional Covariance

Mean and Covariance RBM

Mean Product of Student t-distributions ???

Spike and Slab RBM ???

20.6 Convolutional Boltzmann Machines

20.7 Boltzmann Machines for Structured or Sequential Outputs

20.8 Other Boltzmann Machines

20.9 Back-Propagation throughRandom Operations

20.9.1 Back-Propagating through Discrete Stochastic Operations

20.10 Directed Generative Nets

20.10.1 Sigmoid Belief Nets

20.10.2 Differentiable Generator Nets

inverse transform sampling ???

20.10.3 Variational Autoencoders

http://fiveeyes.github.io/learning/2017/08/25/Variational-Inference.html

https://github.com/FiveEyes/ml-notebook/blob/master/vae/vae.ipynb

deep recurrent attention write(DRAW)

20.10.4 Generative Adversarial Networks

DCGAN

conditional GAN

20.10.5 Generative Moment Matching Networks

20.10.6 Convolutional Generative Networks

20.10.7 Auto-Regressive Networks

20.10.8 Linear Auto-Regressive Networks

20.10.9 Neural Auto-Regressive Networks

20.10.10 NADE

20.11 Drawomg Samples from Autoencoders

20.11.1 Markov Chain Associated with any Denoising Autoencoder

20.11.2 Clamping and Conditional Smapling

20.12 Generative Stochastic Networks

20.12.1 Discriminant GSNs

20.13 Other Generation Schemes

20.14 Evaluating Generative Models

20.15 Conclusion