Title: Laplacian Eigenmaps
Speaker: Ke Wang, Rutgers University
Date: Wednesday, April 21, 2010 12:10pm
Location: Graduate Student Lounge, 7th Floor, Hill Center, Rutgers University, Busch Campus, Piscataway, NJ
Laplacian eigenmaps is a geometrically motivated algorithm in performing nonlinear dimensionality reduction. In this talk, I will describe this algorithm, explain the idea behind and show how the graph Laplacian is playing a role here and in other algorithms.