This book introduces how to build a successful machine learning project to solve business problems in practice. Unlike its successor (“The Hundred Page Machine Learning” book which is about machine learning science/research), this one focuses on engineering. It talks about every steps of creating ML project in details (as the following figure shows). The reader will be able to find out all the important details during the journey.
In the author’s own words, the target audience of this book is:
data analysts who lean towards a machine learning engineering role, machine learning engineers who want to bring more structure to their work, machine learning engineering students, as well as software architects who happen to deal with models provided by data analysts and machine learning engineers.
The book is great in outlining the steps during development, unveiling the pitfalls at each step, clarifying the most important problems/solutions, and demonstrating best practices. I also like the summary at the end of each chapter that helps me recap.
However, I feel the details covered in the book are sometimes too overwhelming for newbies to carry. It’s like reading a cookbook without actually cooking. I can only recall 40% of the most important points in the books after reading. It’s worth revisiting corresponding chapters when I really work on a project in future.
Book site: http://www.mlebook.com/
Amazon link: Machine Learning Engineering