From Autoencoder to Beta-VAE

<!-- Autocoders are a family of neural network models aiming to learn compressed latent variables of high-dimensional data. Starting from the basic autocoder model, this post reviews several variations, including denoising, sparse, and contractive autoencoders, and then Variational Autoencoder (VAE) and its modification beta-VAE. --> <p><span class="update">[Updated on 2019-07-18: add a section on <a href="#vq-vae-and-vq-vae-2">VQ-VAE & VQ-VAE-2</a>.]</span> <br/> <span class="update">[Updat