generative models - Restricted Boltzmann Machines vs GAN. Generation and Generalization Methods for Energy-Based Models. EBM

generative models - Restricted Boltzmann Machines vs GAN - Cross Validated:

Source:

https://stats.stackexchange.com/questions/338328/restricted-boltzmann-machines-vs-gan

"RBM is sort of a layer 

whereas GAN is an architecture. 

GANs are composed of two parts for which you can use different networks - convolutional (CNN), fully connected etc., 

.... whereas RBMs define joint probability on one layer of visible and hidden units." 

"GANs are known to be hard to train. That said, they are more general (since you can plug in anything you like as encoder and decoder) 

so this comparison doesn't make much sense (it's sort of like comparing linear regression to neural networks for regression)."

--------

Implicit Generation and Generalization Methods for Energy-Based Models. EBM:

https://openai.com/blog/energy-based-models/

https://s3-us-west-2.amazonaws.com/openai-assets/energy-based-models/ebm_final.pdf