Manifold learning and maximum likelihood estimation for hyperbolic network embedding.
Gregorio Alanis-LobatoPablo MierMiguel A. Andrade-NavarroPublished in: Appl. Netw. Sci. (2016)
Keyphrases
- manifold learning
- maximum likelihood estimation
- nonlinear dimensionality reduction
- laplacian eigenmaps
- manifold embedding
- low dimensional
- maximum likelihood
- em algorithm
- embedding space
- geodesic distance
- dimensionality reduction
- locality preserving projections
- discriminant embedding
- semi supervised
- high dimensional
- probability distribution
- expectation maximization
- parameter estimation
- latent space
- high dimensional data
- dimension reduction
- low dimensional manifolds
- sparse representation
- head pose estimation
- feature space
- probability density
- vector space
- locally linear embedding
- data mining
- unsupervised learning
- image classification
- nearest neighbor
- knn
- machine learning