In this chapter, we introduced some of the fundamental themes of deep learning. It consists of a set of methods that allow a machine learning system to obtain a hierarchical representation of data, on multiple levels. This is achieved by combining simple units, each of which transforms the representation at its own level, starting from the input level, in a representation at a higher level, slightly more abstract.
In recent years, these techniques have provided results never seen before in many applications, such as image recognition and speech recognition. One of the main reasons for the spread of these techniques has been the development of GPU architectures, which considerably reduced the training time of DNNs. There are different DNN architectures, each of which has been developed for a specific problem. We'll talk more about those architectures in later chapters, showing examples of applications created with the TensorFlow framework.
The chapter ended with a brief overview of the implemented deep learning frameworks.
In the next chapter, we begin our journey into deep learning, introducing the TensorFlow software library. We will describe its main features and look at how to install it and set up a first working session.
