As conclusion of this book, it is time to broaden the view. The rapid growth of deep learning research, including within the field of computational mechanics, has resulted in an extensive and diverse body of literature. To help researchers identify key concepts and promising methodologies within this field, this chapter provides an overview of deep learning in computational mechanics. Five main categories are identified and explored: simulation substitution, simulation enhancement, discretizations as neural networks, generative approaches, and deep reinforcement learning. This chapter focuses on presenting the methods used in deep learning in computational mechanics rather than their specific applications in computational mechanics, thereby enabling researchers to explore this field more effectively. The discussed concepts are explained as simple as possible. This renders the content accessible to both beginners who worked through the previous chapters, as well as experts. This makes it possible to gain an overview of the current state-of-the-art and thereby obtain ideas for future research directions.