Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture introduces deep generative models, starting with a recap on mixture of multinoullis and latent Dirichlet allocation. It then delves into variational autoencoders and generative adversarial networks, discussing their architectures, training procedures, and weaknesses. The lecture concludes with a look at deep convolutional GANs and practical applications of autoencoders as generative models.