Introduction

In the previous chapter, we discussed clustering algorithms and how they can be helpful to find underlying meaning in large volumes of data. This chapter investigates the use of different feature sets (or spaces) in our unsupervised learning algorithms, and we will start with a discussion regarding dimensionality reduction, specifically, Principal Component Analysis (PCA). We will then extend our understanding of the benefits of the different feature spaces through an exploration of two independently powerful machine learning architectures in neural network-based autoencoders. Neural networks certainly have a well-deserved reputation for being powerful models in supervised learning problems. Furthermore, through the use of an autoencoder stage, neural networks have been shown to be sufficiently flexible for their application to unsupervised learning problems. Finally, we will build on our neural network implementation and dimensionality reduction as we cover t-distributed...