Data preparation takes a great deal of time for complex datasets, as we saw in the previous chapter. However, time spent on data preparation is time well invested... this I can guarantee! In the same way, investing time in understanding the basic theory of learning from data is super important for any person that wants to join the field of deep learning. Understanding the fundamentals of learning theory will pay off whenever you read new algorithms or evaluate your own models. It will also make your life much easier when you get to the later chapters in this book.
More specifically, this chapter introduces the most elementary concepts around the theory of deep learning, including measuring performance on regression and classification as well as the identification of overfitting. It also offers some warnings about the sensibility of—and the need to optimize...