about this book
This book dives into the design of ML algorithms from scratch. Throughout the book, you will develop mathematical intuition for classic and modern ML algorithms and learn the fundamentals of Bayesian inference and deep learning as well as data structures and algorithmic paradigms in ML.
Understanding ML algorithms from scratch will help you choose the right algorithm for the task, explain the results, troubleshoot advanced problems, extend algorithms to new applications, and improve the performance of existing algorithms.
What makes this book stand out from the crowd is its from-scratch analysis that discusses how and why ML algorithms work in significant depth, a carefully selected set of algorithms that I found most useful and impactful in my experience as a PhD student in machine learning, fully worked out derivations and implementations of ML algorithms explained in the text, as well as some other topics less commonly found in other ML texts.
After reading this book, you’ll have a solid mathematical intuition for classic and modern ML algorithms in the areas of supervised and unsupervised learning, and will have gained experience in the domains of core ML, natural language processing, computer vision, optimization, computational biology, and finance.
Who should read this book
This book was written for anyone interested in exploring machine learning algorithms in depth. It may prove invaluable to many different types of readers, including the following: