Introduction to Non-Linear Dimension Reduction Techniques

Summary of the project:

• Usual dimension reduction techniques are linear in nature
• This project was about introducing few novel approaches in literature for non-linear dimension reduction
• Brief discussion on Dimension reduction, Kernel PCA, Multidimensional Scaling (MDS), Locally Linear Embedding (LLE), t-SNE, Diffusion Map.
• Basic comparison of these methods on a non-linear data

You can find the slides for the presentation of this project here .