Timezone: »

 
Isometric Gaussian Process Latent Variable Model
Martin Jørgensen · Søren Hauberg

Fri Dec 11 08:30 AM -- 09:30 AM (PST) @
in Differential Geometry meets Deep Learning (DiffGeo4DL) »

We propose a fully generative unsupervised model where the latent variable respects both the distances and the topology of the modeled data. The model leverages the Riemannian geometry of the generated manifold to endow the latent space with a well-defined stochastic distance measure, which is modeled as Nakagami distributions. These stochastic distances are sought to be as similar as possible to observed distances along a neighborhood graph through a censoring process. The model is inferred by variational inference. We demonstrate how the new model can encode invariances in the learned manifolds.

Author Information

Martin Jørgensen (Technical University of Denmark)
Søren Hauberg (Technical University of Denmark)

More from the Same Authors