no code implementations • 11 Jun 2020 • Robert Sicks, Ralf Korn, Stefanie Schwaar
Although variational autoencoders (VAE) are successfully used to obtain meaningful low-dimensional representations for high-dimensional data, the characterization of critical points of the loss function for general observation models is not fully understood.
no code implementations • 26 Mar 2020 • Robert Sicks, Ralf Korn, Stefanie Schwaar
We consider a variational autoencoder (VAE) for binary data.