Performing nonlinear dimension reduction with Local Linear Embedding
Locally linear embedding (LLE) is an extension of PCA, which reduces data that lies on a manifold embedded in a high dimensional space into a low dimensional space. In contrast to ISOMAP, which is a global approach for nonlinear dimension reduction, LLE is a local approach that employs a linear combination of the k-nearest neighbor to preserve local properties of data. In this recipe, we will give a short introduction of how to use LLE on an s-curve data.
In this recipe, we will use digit data from
lle_scurve_data within the
lle package as our input source.
How to do it...
Perform the following steps to perform nonlinear dimension reduction with LLE:
- First, you need ...