Spectral embedding using Laplacian Eigenmaps
The laplacianEigenmapsDemo script demonstrates basic usage of the core laplacianEigenmaps function for several classic manifold learning examples.
This code was tested in MATLAB R2017b.
As the graph and conncomp functions were first introduced in R2015b, that is likely the oldest version of MATLAB in which this code will run.
The syntax for optional inputs to eigs changed in R2017b, hence that function call will likely need to be modified for use in earlier versions of MATLAB.
No dependencies outside of the MATLAB standard library are required.
-
Belkin, Mikhail, and Partha Niyogi. "Laplacian eigenmaps for dimensionality reduction and data representation." Neural Computation 15.6 (2003): 1373-1396. (Link)
-
Bengio, Yoshua, et al. "Learning eigenfunctions links spectral embedding and kernel PCA." Learning 16.10 (2006). (Link)
-
Ng, Andrew Y., Michael I. Jordan, and Yair Weiss. "On spectral clustering: Analysis and an algorithm." Advances in Neural Information Processing Systems (2002). (Link)
-
van der Maaten, Laurens, Eric Postma, and Jaap van den Herik. "Dimensionality reduction: a comparative review." Journal of Machine Learning Research 10 (2009): 66-71. (Link)
This project is licensed under the MIT License.