In this chapter, we explored two new unsupervised learning methods, PCA and SVD, for dimensionality reduction. We saw how to extract features for, and train, these models using facial image data. We visualized the results of the model in the form of Eigenfaces, saw how to apply the models to transform our original data into a reduced dimensionality representation, and investigated the close link between PCA and SVD.
In the next chapter, we will delve more deeply into techniques for text processing and analysis with Spark.
