Machine learning: Lab: faces

Faces and dimension reduction #

The Labeled Faces in the Wild data set contains images of generally well-known individuals. We will explore its images and focus on two objectives:

  • learn how to use the singular value decomposition to create a low-dimensional representation of a data set, and

  • compare the clusters formed when features are created via a linear projection versus a neural network embedding.

from Artificial Intelligence Review

This lab follows a companion notebook.