Latent variable models from independent components to VAEs and flows

Speaker: Ole Winther, University of Copenhagen & Technical University of Denmark (DTU).

Abstract: The keynote will cover latent variable models from independent component analysis to variational autoencoders and flows. Properties, relationships and use cases are discussed. Generative modeling of images and analysis of single cell RNA data are used as running motivational applications.

Presented at IEEE International Workshop on Machine Learning for Signal Processing, Tuesday, September 22, 2020.