The purpose of the Jupyter Notebook is to summarise theory and demonstrate the implementation of variational autoencoders, such that I should be able to use this as a VAE cheat sheet in a few months from now.
Note, download VAE.ipynb at [1] and run it on your Jupyter Notebook local host to ensure that the pictures are displayed properly. (If that did not work out just have a look at the PDF_version)
Steven Battilana 