Generative Adversarial Networks: recent developments
It is an incremental review paper summarizing existing methods for researchers in machine learning.
This paper provides an overview of recent developments in Generative Adversarial Networks (GANs), focusing on their ability to learn latent space representations for generative modeling, but it does not present new results or concrete numbers.
In traditional generative modeling, good data representation is very often a base for a good machine learning model. It can be linked to good representations encoding more explanatory factors that are hidden in the original data. With the invention of Generative Adversarial Networks (GANs), a subclass of generative models that are able to learn representations in an unsupervised and semi-supervised fashion, we are now able to adversarially learn good mappings from a simple prior distribution to a target data distribution. This paper presents an overview of recent developments in GANs with a focus on learning latent space representations.