You made it to the end of the book! What are you going to do now? Read more books! Machine learning, and in particular, deep learning, is a fast-moving field, so any reading list risks being outdated by the time you read it. However, the following list aims to show you the most relevant books that have a safety net of remaining relevant over the coming years.
Wes McKinney, Python for Data Analysis, http://wesmckinney.com/pages/book.html.
Wes is the original creator of pandas, a popular Python data-handling tool that we saw in Chapter 2, Applying Machine Learning to Structured Data. pandas is a core component of any data science workflow in Python and will remain so for the foreseeable future. Investing in sound knowledge of the tools he presents is definitely worth your time.
Marcos Lopez de Prado, Advances in Financial Machine Learning, https://www.wiley.com/en-us/Advances+in+Financial+Machine+Learning-p-9781119482086.
Marcos is an expert at applying machine learning in finance. His book is largely focused on the danger of overfitting and how careful researchers have to be when doing proper science. While focused more on high-frequency trading, Marcos writes very clearly and makes potential issues and solutions very understandable.
Trevor Hastie, Robert Tibshirani, and Jerome Friedman, Elements of Statistical Learning, https://web.stanford.edu/~hastie/ElemStatLearn/.
The "bible" of statistical machine learning, containing good explanations of all the important concepts of statistical learning. This book is best used as a lookup book whenever you need some in-depth information on one concept.
Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani, Introduction to Statistical Learning, https://www-bcf.usc.edu/~gareth/ISL/.
Introduction to Statistical Learning is a bit like a companion to Elements of Statistical Learning. Written by some of the same authors, it introduces the most important concepts in statistical learning in a rigorous manner. It's ideal if you are new to statistical learning.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, https://www.deeplearningbook.org/.
While this book is very praxis-oriented, Deep Learning is more focused on the theory behind deep learning. It covers a broad range of topics and derives practical applications from theoretical concepts.
Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, http://incompleteideas.net/book/the-book-2nd.html.
The standard work of reinforcement learning discusses all major algorithms in depth. The focus is less on flashy results and more on the reasoning behind and derivation of reinforcement learning algorithms.
Kevin P. Murphy, Machine Learning: a Probabilistic Perspective, https://www.cs.ubc.ca/~murphyk/MLbook/.
This book covers machine learning techniques from a probabilistic and much more Bayesian perspective. It's a very good guide if you want to think about machine learning differently.
Cameron Davidson-Pilon, Probabilistic Programming and Bayesian Methods for Hackers, http://camdavidsonpilon.github.io/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/.
This is probably the only probabilistic programming book that focuses on practical applications. Not only is it free and open source, it also gets frequent updates with new libraries and tools so that it always stays relevant.