P art 1 of this book gives you a first high-level understanding of what probabilistic deep learning (DL) is about and which types of tasks you can tackle with it. You’ll learn about different neural network architectures for regression (that you can use to predict a number), and about classification (that you can use to predict a class). You’ll get practical experiences in setting up DL models, learn how to tune these, and learn how to control the training procedure. If you don’t already have substantial experience with DL, you should work through part 1 in full before moving on to the probabilistic DL models in part 2.