Manifold constrained finite Gaussian mixtures

Archambeau, Cédric;Verleysen, Michel
(2005) 8th International Work-Conference on Artificial Neural Networks (IWANN 2005) — Location: Barcelona (Spain) (8.June.2005)

Files

C24-ManifoldConstrainedFiniteGaussianMixtures.pdf
  • Restricted Access
  • Adobe PDF
  • 224.23 KB
Request a copy

Details

Authors
Abstract
In many practical applications, the data is organized along a manifold of lower dimension than the dimension of the embedding space. This additional information can be used when learning the model parameters of Gaussian mixtures. Based on a mismatch measure between the Euclidian and the geodesic distance, manifold constrained responsibilities are introduced. Experiments in density estimation show that manifold Gaussian mixtures outperform ordinary Gaussian mixtures.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Archambeau, C., & Verleysen, M. (2005). Manifold constrained finite Gaussian mixtures. Lecture Notes in Computer Science, 3512, 820-828. https://hdl.handle.net/2078.5/140508 (Original work published 2005)