Showing stat.MLShow all
2 papers · 1 filter
stat.ML2020
Variational Autoencoder with Learned Latent Structure
Marissa C. Connor, Gregory H. Canal, Christopher J. Rozell
The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this…
stat.ML2019
Representing Closed Transformation Paths in Encoded Network Latent Space
Marissa Connor, Christopher Rozell
Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are d…