Appendix A. Mathematical foundations
You can’t do machine learning without math. In particular, linear algebra and calculus are essential. The goal of this appendix is to provide enough mathematical background to help you understand the code samples in the book. We don’t have nearly enough space to cover these massive topics thoroughly; if you want to understand these subjects better, we provide some suggestions for further reading.
If you’re already familiar with advanced machine-learning techniques, you can safely skip this appendix altogether.
Further reading
In this book, we have room to cover only a few mathematical basics. If you’re interested in learning more about the mathematical foundations of machine learning, here are some suggestions:
- For a thorough treatment of linear algebra, we suggest Sheldon Axler’s Linear Algebra Done Right (Springer, 2015).
- For a complete and practical guide to calculus, including vector calculus, we like James Stewart’s Calculus: Early Transcendentals (Cengage Learning, 2015).
- If you’re serious about understanding the mathematical theory of how and why calculus works, it’s hard to beat Walter Rudin’s classic Principles of Mathematical Analysis (McGraw Hill, 1976).
Linear algebra provides tools for handling arrays of data known as vectors, matrices, and tensors. You can represent all of these objects in Python with NumPy’s array type.