AKA Story

Variational Autoencoder

Goal Variational methods for inference of latent variables became popular in the last years. Here, we have a look at variational autoencoders from a slightly more mathematical point of view. Motivation Some deep generative models for vision tasks, such as style transfer or simply generating images similar to some given images, rely heavily on variational autoencoder frameworks. Only very recently latent variables have been introduced into the hierarchical recurrent encoder decoder framework to enhance the expressive power of the model when coming up with responses to utterances. Further variational autoencoder allow to perform unsupervised learning and are thus in general interesting to solving artificial intelligence. Ingredients variational inference, posterior distribution, latent variable, Bayes model, Kullback-Leibler divergence, objective function, lower bound […]