Manifold learning encompasses much of the disciplines of geometry, computation, and statistics,and has become an important research topic in data mining and statistical learning.The simplest description of manifold learning is that it is a class of algorithms for recoveringa low-dimensional manifold embedded in a high-dimensional ambient space.
The goal of this mini-course is to introduce severalfundamental algorithms in manifold learning: MDS (Multidimensional Scaling), LLE(Locally Linear Embedding), Laplacian Eigenmap, TDA(Topological Data Analysis). We will focus on the theoretical properties of them. The prerequisite of this mini-course is linear algebra.
Schedule
10:00-10:30IntroductionChih-Wei Chen 10:30-11:30MDSSeçkin Gunsen 11:30-13:00Lunch break 13:00-14:30LLELiren Lin 14:30-15:30Laplacian EigenmapChin-Hung Jephian Lin 15:30-15:45Break 15:45-17:15TDAYi-Sheng Wang
Location
Room 4009-1, 4F, College of Science, NSYSU, Kaohsiung