The Hundred-Page Machine Learning Book (The Hundred-Page Books)

If you are serious about learning machine learning, The Hundred-Page Machine Learning Book by Andriy Burkov is the first book you should pick up. It’s nothing short of a triumph — clear, concise, brilliantly organized, and incredibly practical. In a little over a hundred pages, Burkov manages to explain complex concepts like supervised and unsupervised learning, model evaluation, neural networks, and even advanced topics like ensemble methods and dimensionality reduction. Every chapter is filled with wisdom distilled from years of real-world experience, written in a style that is both accessible to beginners and valuable for seasoned professionals. What impressed me the most is how efficient the book is: there’s not a single wasted word. Every paragraph adds real value. The balance between mathematical intuition, algorithmic depth, and practical advice is absolutely perfect. Plus, the references to additional resources (via QR codes and links) make this book a living gateway to even deeper learning. If you’ve ever been intimidated by machine learning, this book will completely change that. It makes the field feel exciting, achievable, and even fun. I cannot recommend it highly enough. 5/5 stars — This book belongs on the desk of every aspiring data scientist, engineer, or AI enthusiast!

I've gone through different books, papers and courses on ML and Artificial intelligence, and I've found that a majority of them are either overwhelmingly dense, or disappointingly shallow, with very few of them hitting any sort of sweet spot. This book is one of the few exceptions. Despite being short, it manages to cover a lot of ground without sacrificing a fair treatment of the basics. There's an exceptionally good balance between math and concepts in my opinion, and it's all explained in very simple terms, without ever feeling pretentious or cryptic. I think the author did an outstanding job distilling a great deal of useful information into 100-ish pages while avoiding making this a dense read. It's actually the only book I've been able to breeze through while still getting a lot of useful insights in the process. In fact, even though I already had some experience on the field when I read this book, I found that the way some concepts and topics are presented provided me with a new way of approaching them or thinking about them that further deepened my understanding of those topics, and allowed me to explore them in ways I had not done before. I wish this book existed when I started learning ML. It would have made a lot of thing clearer from the start. All in all; This book is a fantastic resource that serves as a perfect introduction to the topic for beginners, and a good "refresher" and a source of invaluable tips and insights for the more experienced ML practitioners.

Disclaimer: The author asked me to review this book, though I had already purchased my own copy. I promise to be 100% honest in how I feel about this book, both the good and the less so. Overview: This book does exactly what it states. It's a 100+ page book that gives you an overview of machine learning, the math behind most of the reviewed techniques so you can follow along with current research to an extent), and QR code links to further reading. The author also follows a 'read first, buy later' policy, which I respect. The book is very well organized, giving the reader an introduction and discussion on the mathematical notation used, a well written chapter that discusses several very common algorithms, talks about best practices (like feature engineering, breaking up the data into multiple sets, and tuning the model's hyperparameters), digs deeper into supervised learning, discusses unsupervised learning, and gives you a taste of a variety of other related topics. What I Like: This is a well rounded book, far more so than most books I've read on machine learning or artificial intelligence. After reading through this, I feel like I can competently discuss the subject, read one of the simpler machine learning research papers, and not be totally lost on the mathematics involved. The language used is concise and reads very well, showing very tight editing. What I Didn't Care For: I know that this is a general introduction and meant to be kept short. Like many other reviewers, however, I would have enjoyed a deeper look into everything that was in this book. What I Would Like To See: I know that the author is currently writing a data engineering book without the 100 page limitation. Personally, I would like to see him write a ML Math book (I'm weird like that) as well as an MLOps book. I expect the later to be what he writes next, if he chooses to continue writing. Overall, I got a LOT out of this book and look forward to more. I am giving a rating of 4.8 out of 5. If I include the wiki and further reading, I would bump it up to 4.9.

While this book is presented as a primer for Machine Learning enthusiast and practitioners ranging from beginner to expert, I would argue against diving headfirst into it if you have not done some pre-work first. To be fair, the book really is well put together and does a great job of explaining and connecting various ML concepts. However, to get the most out of this text I recommend the following build-up process before reading. First, read the “Machine Learning for Everyone” post on the vas3k blog to make sure this is a topic you are really are interested in, and to demystify yourself of that the idea that all of this ML stuff is synonymous with AI. Second, take a Python course at either codecademy or a similar online self-paced learning website. Then I recommend taking a Linear Algebra course at a site like Kahn academy, especially if it has been many years since your last math course. Lastly, I recommend taking a Data Science course at either General Assembly, Kaggle, or Data Camp to get the basics and generally terminology down. At this point you will likely be a bit overwhelmed and wondering how to form one coherent big picture of all of this stuff you just learned. It is at this point where the “The Hundred-Page Machine Learning Book” comes in perfectly. It resets all you have learned to this point into one coherent picture. Reading it at this point also will require less look up of the referenced topics, math, and libraries / tools. While the book is only 100 pages and reads fast, it is probably best to chunk it up into no more than a chapter a day and read it over two weeks. It has also has a long shelf life because you will find yourself referencing back to it from time-to-time.

In 2018 I was nominated for Data Scientist of the Year for Nashville, and became a finalist. Machine learning has been a big part of my career since 2005. I would like to say I don’t need a book like THPMLB, however, it is a fantastic resource. There is math in this book, and the reader will want to find a resource to become familiar with the notation, if they don’t already know it. I’ve always found the notation is the first filter for people getting into science of any type. However, the notation is more complex looking than it is once you know what the symbols mean. In the end, all math devolves down to a few basic operations and notation simply implies several assumptions about how to apply them. What makes the book excellent is the very plain-speaking method in which the lessons are taught. This isn’t someone trying to impress PhD’s in their field. This is someone looking to talk to you about machine learning. This straightforward approach will help you learn machine learning techniques. For someone like me, it offers a handy reference to techniques I’ve used but forgot the details to, or techniques I’ve wanted to explore. Its small size makes it easy to find what you are looking for, get a basic understanding, and launch you into further learning. Finally, this is a living product and there is a constantly updated wiki for this book. That alone is worth the small price you’d pay for this book. This book gets my highest recommendation.

WARNING: It's now possible to buy a counterfeit copy of Andriy's book! To avoid that, click on "See All Buying Options" button and choose *Amazon.com* as the seller. I'm a software engineer currently working for a big tech company. This is hands down the book you need to grok and master machine learning concepts. As a programmer, I have felt capable of utilizing the machine learning tools available, but have felt distant from understanding the many cited academic papers. I can confidently say, just a few chapters into this book, that this is the book I was missing! I have followed Andriy on LinkedIn for a long time now, and always appreciated his posts. When I saw he was publishing a book, I didn't think twice and ordered it. As expected, the book is clear, concise and does a thorough job explaining basic mathematical concepts, machine learning principles, and the most important fundamentals to understand the field. One note: I can tell this book will be useful for a long time. I have many tech related books that become obsolete a few years or even months after they are published. Andriy's approach delves into the core principles, while explaining how to understand further developments into the field. This is something I was missing and truly appreciate. I have a quirk of reading physical books alongside a text-to-speech interface on a digital device. Especially with text books, this is helpful, but not all textbooks are capable of being processed this way. Fortunately, when you purchase the physical book, Andriy sends you the digital edition as well. As a result, I have been able to breeze through the text in my ideal learning state. For those who have been working around the academic machine learning world, but are influenced by it - buy this book! For those who are familiar with machine learning concepts and have gone through all the blog posts and MOOCs you could get your hands on - buy this book!

Burkov's book is exactly what a practicing professional in the field of machine learning needs at hand: a concise ready reference that covers just enough of the core concepts to resolve everyday issues in the field, without a lot of filler or overly verbose backgrounder. In my work in ML algorithmics, I have reached over to this work and have quickly assured myself of my own understanding of the underpinnings necessary to deal with real day-to-day issues in the field. Brevity is the soul of wit, it has been said. In the case of Burkov's work, brevity is the soul of usability. When I need longer books, I reach to them, but not until I have given Burkov's summary its due consideration. There is no shortage of heavy doorstop tomes out there in the field -- The Hundred Page Machine Learning Book is more of a key to open the door than a doorstop, and this is exactly what I needed in my career. Even in such a succinct work, he has addressed what needs to be considered with sufficient depth to justify this book's place in its niche, and in doing so, he has done the profession a great service. Moreover, the QR codes supplied throughout and the author's supplementary materials, such as the companion wiki are sufficient for those who need or desire the full experience of filling out the excruciating details of this large and varied field. Even without these, however, the book is, in my considered opinion, a standalone masterwork.

I use it for the machine learning class I teach.

I am a materials engineer and this book helped me a lot to quickly understand the concepts of machine learning with a very basic knowledge. I am very grateful to have come across this book. While I was working on my Master's thesis on a topic related to computer vision, the book was very accessible thanks to its clear explanations and helped me to quickly get into my topic. It also proved to be directly applicable to my professional work. I would recommend this book to anyone who wants to learn more about machine learning and also to professionals in the field who want a reference book. Thank you Andriy for this great book!

Es uno de los mejores libros que he visto a nivel principiante. Es importante que el objetivo del libro no es que tengas horas experiencia práctica al terminar de leerlo, sino dar un "panorama general" del Machine Learning, cosa que el autor hace de forma magistral.

So succinct and doesn't skip the math on anything. An intro to ML but has something for everyone to learn. Great to keep on the shelf at home or work for reference

I'd say no one book or course is adequate for mastering Machine Learning, but this book is really helpful! It may not cover all aspects in great detail, but it does touch all the important points and with admirable clarity. The book is like a structured learning guide, based on which we can get a baseline understanding, and then go elsewhere to pick up more details as needed. I use it in conjunction with half a dozen other machine learning books and online courses. I love this book!

Volevo una buona ma veloce introduzione al mondo del Machine Learning, per cominciare ad applicarlo al mio lavoro quotidiano. Credo che questo libro sia perfetto per questo scopo. È veramente sintetico ma accurato. Vengono presentate principalmente le tecniche "classiche" di Machine Learning, quelle più importanti e utilizzate, insieme a una serie di "best practices" di riconosciuto successo. Gli algoritmi più moderni, che vengono sviluppati di anno in anno, non sono presenti, ma troverete una buona collezione di algoritmi fondamentali, che vi permetterà anche di comprendere gli sviluppi più recenti di questo settore. Scrivo questa relazione circa un anno dopo l'acquisto del libro. Sto utilizzando il Machine Learning abbastanza spesso nel mio lavoro (anche se non mi ritengo un professionista), e utilizzo ancora questo libro come riferimento, per rinfrescare una formula o un concetto.