Research >> Manifold learning

 

Manifold learning
Given unorganized points drawn from an unknown manifold,
can you reconstruct the manifold? This problem is of interest
theoretically, and also has potential applications in machine learning.
We propose a method which constructs a simplicial manifold; the method
is designed to work for abitrary dimension and codimension. Unlike the
Isomap and LLE family of algorithms, the proposed technique does not depend
on the manifold having the topology of a ball.

 

Faculty: Daniel Freedman

 

 

Publications:

D. Freedman. Efficient simplicial reconstructions of manifolds from their samples. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(10):1349 -1357, 2002. [ pdf ] [ bib ]

 

Home | People | Research | Publications | Contact | News/Events | Download | Links