Matlab Toolbox for Dimensionality Reduction

降维方法包括：

1. Principal Component Analysis (PCA)

2. • Probabilistic PCA

3. • Factor Analysis (FA)

4. • Sammon mapping

5. • Linear Discriminant Analysis (LDA)

6. • Multidimensional scaling (MDS)

7. • Isomap

8. • Landmark Isomap

9. • Local Linear Embedding (LLE)

10. • Laplacian Eigenmaps

11. • Hessian LLE

12. • Local Tangent Space Alignment (LTSA)

13. • Conformal Eigenmaps (extension of LLE)

14. • Maximum Variance Unfolding (extension of LLE)

15. • Landmark MVU (LandmarkMVU)

16. • Fast Maximum Variance Unfolding (FastMVU)

17. • Kernel PCA

18. • Generalized Discriminant Analysis (GDA)

19. • Diffusion maps

20. • Neighborhood Preserving Embedding (NPE)

21. • Locality Preserving Projection (LPP)

22. • Linear Local Tangent Space Alignment (LLTSA)

23. • Stochastic Proximity Embedding (SPE)

24. • Multilayer autoencoders (training by RBM + backpropagation or by an evolutionary algorithm)

25. • Local Linear Coordination (LLC)

26. • Manifold charting

27. • Coordinated Factor Analysis (CFA)

28. • Gaussian Process Latent Variable Model (GPLVM)

29. • Stochastic Neighbor Embedding (SNE)

30. • Symmetric SNE (SymSNE)

31. • new: t-Distributed Stochastic Neighbor Embedding (t-SNE)

32. • new: Neighborhood Components Analysis (NCA)

33. • new: Maximally Collapsing Metric Learning (MCML)

    下载地址：http://homepage.tudelft.nl/19j49/Matlab_Toolbox_for_Dimensionality_Reduction.html