Variational Autoencoders: an introduction to new applications and a new regularization approach.


In this presentation, we discuss the Variational AutoEncodeur (VAE): a latent variable model emerging from the machine learning community. To begin, we introduce the theoretical foundations of the model and its relationship with well-established statistical models. Then, we discuss how we used VAEs to solve two widely different problems. First, we tackled a classic statistical problem, survival analysis, and then a classic machine learning problems, image analysis and image generation. We conclude with a short discussion of our latest research project where we establish a new metric for the evaluation or regularization of latent variable models such a Gaussian Mixture Models and VAEs.

You can download the slides here.

The talk was recorded and is freely available as a lecture here.