In the preceding chapter, we looked at some widely-used dimensionality reduction techniques, which enable a data scientist to get greater insight into the nature of datasets.
The next few chapters will focus on some more sophisticated techniques, drawing from the area of deep learning. This chapter is dedicated to building an understanding of how to apply the Restricted Boltzmann Machine (RBM) and manage the deep learning architecture one can create by chaining RBMs—the deep belief network (DBN). DBNs are trainable to effectively solve complex problems in text, image, and sound recognition. They are used by leading companies for object recognition, intelligent image search, and robotic spatial recognition.
The first thing that we're going to do is get a solid grounding in the algorithm underlying DBN; unlike clustering or PCA, this code isn't widely-known by data scientists and we're going to review it in some depth to build...