The best books if you want to become a machine learning engineer

Why this book?

There are three types of machine learning books — books written for people who want to become machine learning engineers, books written for people who want to become machine learning researchers, and books written for business executives. Reading a book written for researchers or executives can be a frustrating experience if you are a software engineer, social scientist, or mechanical engineer who wants to learn machine learning and get an ML job in the industry.

If you are a coder who wants to become an ML engineer, you have got to learn machine learning concepts, but you want to learn them in a practical way. You need a book that leads with intuition and shows you implementations with code. It has to do this without getting sidetracked into ML theory, getting mired in statistical concepts, or being so superficial that you don’t understand why the code works. Aurélien gracefully threads this needle — that’s what makes his book so good.

This is a very clearly written book. The author uses a simple framework (scikit-learn) to explain the basics, and then moves to TensorFlow for more realistic examples. Throughout, the book is immensely pragmatic. I strongly recommend this as your first ML book.

• Buy this book at:
• Bookshop.org
• Amazon

When you buy a book we may earn a small commission.

Why this book?

General-purpose machine learning is not why machine learning is so popular. Instead, ML is popular because a branch of ML, called deep learning, has proven to be incredibly powerful at handling unstructured data — images, video, natural language text, audio/speech, etc.

Francois Chollet is the author of Keras, the leading software framework for deep learning. As with Aurelien’s book, Francois’ book is clearly written, immensely pragmatic, and will give you the necessary intuition and show you how to implement deep learning models in code.

• Buy this book at:
• Bookshop.org
• Amazon

When you buy a book we may earn a small commission.

Why this book?

This recommendation is a bit of a cheat — I’m not recommending this exact book, but one of the books in the series that this book is part of.

Once you have the first two books under your belt, you’ll know how to solve ML problems. But you will keep reinventing the wheel. What you need next is a book on common “ML tricks” — best practices and common techniques when doing ML in production.

The problem is that these tricks are specific to the type of data that you will be processing. If you are going to be processing images or time series, read the corresponding books in the same series instead.

• Buy this book at:
• Bookshop.org
• Amazon

When you buy a book we may earn a small commission.

Why this book?

The difference between an ML beginner and an ML expert is that the ML expert doesn’t try to build something that they can simply reuse. But the expert also has the judgment to recognize scenarios where it is worth building something — this is usually because the current, generic, state-of-the-art (SoTA) models won’t be good enough.

Jeremy shows you what the state of the art (SoTA) looks like across a wide variety of ML fields, and how to use SoTA models to get what you need. If the first three books will make you a good ML engineer, this book will help you inch your way towards knowing what ML researchers know.

• Buy this book at:
• Bookshop.org
• Amazon

When you buy a book we may earn a small commission.

Why this book?

Even if you have the practical knowledge, it's sometimes necessary to understand the mathematical and theoretical concepts that underlie the machine learning approaches you are using. This book is a great introduction to the world of ML theory.

• Buy this book at:
• Bookshop.org
• Amazon

When you buy a book we may earn a small commission.