Poster
in
Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL)

Isometric Gaussian Process Latent Variable Model

Martin Jørgensen · Søren Hauberg

Abstract:

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.

Chat is not available.