0%

Manifold Leaning

Manifold Learning

What's Manifold Learning? Manifold Learning is merely using the geometric properties of the data in high dimensions to implement the following things:

  • Clustering: Find groups of similar points. Given , build a function . Two "close" points should be in the same cluster.
  • Dimensionality Reduction: Project points in a lower dimensional space while preserving structure. Given in , build a function , where . "Closeness" should be preserved.
  • Semi-Supervised, Supervised: Given labelled and unlabeled points, build a labeling function. Given , build . Two "close" points should have the same label.

Manifold Learning assumes that the observed data lie on a low-dimensional manifold embedded in a higher-diemnsional space. This is known as manifold assumption.

References

[1] https://towardsdatascience.com/manifold-learning-the-theory-behind-it-c34299748fec

[2] @phdthesis{melas2020mathematical, title={The Mathematical Foundations of Manifold Learning}, author={Melas-Kyriazi, Luke}, year={2020}, school={Harvard University Cambridge, Massachusetts} }