Contribute Media
A thank you to everyone who makes this possible: Read More

On Laplacian Eigenmaps for Dimensionality Reduction


The aim of this talk is to describe the non-linear dimensionality reduction algorithm based on spectral techniques introduced in \cite{BN2003}. This approach has its foundation on the spectral analysis of graph Laplacian. The motivation of the construction comes from the role of the continuous limit, the Laplace-Beltrami operator, in providing an optimal embedding for manifolds.


Improve this page