2 papers
cs.LG2021
Atlas Based Representation and Metric Learning on Manifolds
Eric O. Korman
We explore the use of a topological manifold, represented as a collection of charts, as the target space of neural network based representation learning tasks. This is achieved by…
stat.ML2018
Autoencoding topology
Eric O. Korman
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoen…