Now more than ever, it is crucial to understand the core foundations of AI and machine learning.
True mastery of a subject means understanding its tenets from multiple, complementary angles.
Ideally, this means being able to explain what you know intuitively.
-
Being able to draw a picture of an idea plainly on a cocktail napkin.
-
Being able to recall key formulae that rigorously support or define an idea.
-
And finally, being able to apply a concept practically, in code.
This book aims to lead you towards this mastery of AI fundamentals by explaining every concept
intuitively first, visually second, mathematically third, and fourth in code. In that order. For every major concept.
Machine Learning Refined is used as a reference text in over 100 universities and colleges around the world, including:
What People Say
John G. Proakis
Professor Emeritus, Northeastern University
An excellent book that treats the fundamentals of machine learning from basic principles to practical implementation.
Osvaldo Simeone
Professor, King's College London
Machine Learning Refined builds on first principles and geometric intuition, while offering real-world examples, commented implementations in Python, and computational exercises. I expect this book to become a key resource for students and researchers.
Islem Rekik
Associate Professor, Imperial College London
A fantastic and easy way to launch yourself into the exciting world of machine learning … It was my inspiring guide in preparing my 'Machine Learning Blinks' on my BASIRA YouTube channel for both undergraduate and graduate levels.
Jitkomut Songsiri
Associate Professor, Chulalongkorn University
A great textbook for those who want to learn machine learning for the first time, with an emphasis on mathematical optimization.
Veronica Medrano
Reviewed MLR on Amazon
Machine Learning Geeks, get your hands on this! What I enjoy about it is its fluid description of the complex, theoretical side, explained in such a way that you can confidently go out and apply Machine Learning skills in the real world.
Julio Perez Olvera
Reviewed MLR on Goodreads
One of the best books on the topic, it has a solid theory content and also practical exercises using numpy and autograd. Would definitely recommend to anyone starting with ML.
David Duvenaud
Associate Professor, University of Toronto
This book is great for getting started in machine learning. It builds up the tools of the trade from first principles, provides lots of examples, and explains one thing at a time at a steady pace. The level of detail and runnable code show what's really going when we run a learning algorithm.
John Brittan
Vice President of Research & Development, PGS
A great book on mathematical optimization and a fine introduction to machine learning. The authors’ stated aim was to write a textbook for both first-time learners of the subject and more advanced practitioners. In this it would appear they have firmly succeeded.
Kimiaki Shirahama
Professor, Doshisha University
Every method is explained in a comprehensive, intuitive way, and mathematical understanding is aided and enhanced with many geometric illustrations and elegant Python implementations.
Helena Minaljevic
Professor, Berlin University of Applied Sciences
A comprehensive textbook on the fundamental concepts of machine learning … provid[ing] a very accessible introduction to the main ideas behind machine learning models.
Estefano Palacios
Reviewed MLR on Goodreads
There are hundreds of books on the topic of machine learning. They belong two sets: heavy on math or so lightweight that.machine learning seems like witchcraft. This books strikes a balance by teaching machine learning rigorously but from first principles.
Rama Ramakrishnan
Reviewed MLR on Amazon
Loved this book! Viewing all the usual ML algorithms using the unifying lens of optimization and gradient descent is very nice.
Why Read This Book?
Resources
In our GitHub page located here, you will find a range of resources that complement the 2nd edition of Machine Learning Refined, including: