Sponsored by
[ Events ]

Activity Search
Sort out
NCTS Differential Geometry Seminar
16:00 - 17:00, December 19, 2017 (Tuesday)
Room 440, Astronomy-Mathematics Building, NTU
(台灣大學天文數學館 440室)
From Unsupervised Learning to Spectral Embedding Theory
Hau-Tieng Wu (Duke University)


Unsupervised learning is the step stone of machine learning (or artificial intelligence if you like) to the next generation. Several efforts have been made in past decades from both the algorithmic and theoretical viewpoints. We will first discuss a widely applied unsupervised learning algorithm, diffusion map. Then we provide our current theoretical understanding of diffusion map under the differential geometry framework, particularly the spectral embedding theory. If time permits, a comparison with other algorithms, like locally linear embedding or ISOMAP, or some variations, like vector diffusion map and connection Laplacian over the principal bundle structure, will be discussed.


back to list  
 (C) 2018 National Center for Theoretical Sciences