The Hundred-Page Machine Learning Book
- Downloads：6105
- Type：Epub+TxT+PDF+Mobi
- Create Date：2021-08-20 06:55:16
- Update Date：2025-09-06
- Status：finish
- Author：Andriy Burkov
- ISBN：199957950X
- Environment：PC/Android/iPhone/iPad/Kindle
- Download
Summary
WARNING！ To avoid buying counterfeit on Amazon， click on "See All Buying Options" and choose "Amazon。com" and not a third-party seller。
Concise and to the point — the book can be read during a week。 During that week， you will learn almost everything modern machine learning has to offer。 The author and other practitioners have spent years learning these concepts。
Companion wiki — the book has a continuously updated wiki that extends some book chapters with additional information: Q&A， code snippets， further reading， tools， and other relevant resources。
Flexible price and formats — choose from a variety of formats and price options: Kindle， hardcover， paperback， EPUB， PDF。 If you buy an EPUB or a PDF， you decide the price you pay！
Read first， buy later — download book chapters for free， read them and share with your friends and colleagues。 Only if you liked the book or found it useful in your work， study or business， then buy it。
Concise and to the point — the book can be read during a week。 During that week， you will learn almost everything modern machine learning has to offer。 The author and other practitioners have spent years learning these concepts。
Companion wiki — the book has a continuously updated wiki that extends some book chapters with additional information: Q&A， code snippets， further reading， tools， and other relevant resources。
Flexible price and formats — choose from a variety of formats and price options: Kindle， hardcover， paperback， EPUB， PDF。 If you buy an EPUB or a PDF， you decide the price you pay！
Read first， buy later — download book chapters for free， read them and share with your friends and colleagues。 Only if you liked the book or found it useful in your work， study or business， then buy it。
Reviews
Muhammed Buyukkinaci
，
A summary of ML topics。 I started to read it to refresh my knowledge for Machine Learning。 I benefited from the book。 I also think to summarize what I learned from the book in a GitHub repository。However， some parts like RNN's aren't described well and also some topics in the last chapter aren't described in a detailed way。 A summary of ML topics。 I started to read it to refresh my knowledge for Machine Learning。 I benefited from the book。 I also think to summarize what I learned from the book in a GitHub repository。However， some parts like RNN's aren't described well and also some topics in the last chapter aren't described in a detailed way。 。。。more
Alireza Aghamohammadi
，
کتاب برای افرادی که وقت و زمان خواندن مراجع اصلی یادگیری ماشین را که معمولا بیش از هزار صفحه است را ندارند بسیار مناسب است و اکیدا توصیه می‌شود。الگوریتم‌های یادگیری ماشین （مانند ماشین‌های بردار پشتیبان، جنگل تصادفی، رگرسیون و 。。。） به همراه شبکه‌های عصبی （به صورت مقدماتی） و مبانی ریاضی پشت هر کدام توضیح داده می‌شود。 هر مبحث در سه تا چهار صفحه آموزش داده می‌شود。در واقع کتاب سعی می‌کند از تمامی حواشی دوری کند و چکیده و ضروریات هر الگوریتم را توضیح دهد و به نظرم کاملا موفق بوده است。
Justin
，
Great introduction to the main ML algos
Ibrahim Sharaf ElDen
，
The simplest and most concise ML book that I've ever read （so far， haha）！ I really love the tech-blogposts writing and explanation style that Burkov has adopted for this book， while the usual ML book is very academic and math-focused by nature， on the other side of the spectrum， this book focuses more on intuition， provides details but not too deep to overwhelm the reader， math is simple and used whenever it's necessary only。However， I'm not saying this should be your textbook for teaching yours The simplest and most concise ML book that I've ever read （so far， haha）！ I really love the tech-blogposts writing and explanation style that Burkov has adopted for this book， while the usual ML book is very academic and math-focused by nature， on the other side of the spectrum， this book focuses more on intuition， provides details but not too deep to overwhelm the reader， math is simple and used whenever it's necessary only。However， I'm not saying this should be your textbook for teaching yourself ML， and I believe this isn't the segment that the author was targeting when he wrote the book， in my opinion， the most suitable audience for this book are: 1。 Newbies who are looking for an ML introductory book， think of it as a bunch of carefully curated Medium posts， but it's way better and more streamlined。2。 Experienced ML professionals who are looking for a quick brush up on some concepts， maybe for an interview or a new project。Also kudos to the author for distributing this book as a "Read first， buy later"。 。。。more
Cristián S
，
It is a beautifully designed book， with a lot of topics covered， in more than a hundred pages。 It is a nice book if you want to get model ideas for new projects， usually focusing in novel models。 Anyway， as it covers too many topics， none of them is covered in detail enough to really understand the intuition of the models， and at the same time there are no concrete real examples。 I enjoyed how they explain some points that look difficult in other books。 Sometimes I missed better connections betw It is a beautifully designed book， with a lot of topics covered， in more than a hundred pages。 It is a nice book if you want to get model ideas for new projects， usually focusing in novel models。 Anyway， as it covers too many topics， none of them is covered in detail enough to really understand the intuition of the models， and at the same time there are no concrete real examples。 I enjoyed how they explain some points that look difficult in other books。 Sometimes I missed better connections between the different topics covered by the book。 After reading the book， I feel it is more like a nice book to read and to remember facts that you may forget after some time working on the field， but I am not sure if someone getting into the filed would understand why each thing mentioned in the book is important。 。。。more
Rui
，
Boa introdução a Machine Learning
Abul Abdulkarim
，
Not what they say but what those who paid for it say。 Please don't waste your money on this book。 Not what they say but what those who paid for it say。 Please don't waste your money on this book。 。。。more
Brendan
，
I applaud the gumption， but I don't think the concept is possible。 Burkov starts this book with promise， but quickly falls into simply summarizing the concepts。 He vacillates between giving too much of an introduction and not enough。 The most glaring fault is the succinct introduction of concepts filled with jargon like the following。"An autoencoder is a feed-forward neural network with an encoder-decoder architecture。"Sure， this is fine if you understand the encoder-decoder architecture， but wh I applaud the gumption， but I don't think the concept is possible。 Burkov starts this book with promise， but quickly falls into simply summarizing the concepts。 He vacillates between giving too much of an introduction and not enough。 The most glaring fault is the succinct introduction of concepts filled with jargon like the following。"An autoencoder is a feed-forward neural network with an encoder-decoder architecture。"Sure， this is fine if you understand the encoder-decoder architecture， but when you wash over the concepts so quickly， I doubt the true newcomers fully understand these concepts when phrased this way。 Because of this， I'm not sure who this book is written for。 If you have an understanding of ML and want a reference， this book is far too light on details。 If you have no understanding of ML， this book is far too heavy on concepts and implicitly supposes too much knowledge。 I certainly couldn't give this to my boss to understand， he wouldn't get past the first 10 pages。 For me？ I'm not sure I got anything out of this。 The concepts I knew were not bolstered conceptually here。 There were no great metaphors or mathematical insights。 The concepts I was unfamiliar with still seem gray and foggy in my mind with this book offering little to hold on to for support。Unfortunately， Burkov gave himself an impossible task and proved the task to be， for the moment， still impossible。 。。。more
Nikolay
，
This review has been hidden because it contains spoilers。 To view it， click here。 Not clear whom this is for。 It skims through engineering and production topics like: populations drift; data engineering; serving。 If this is for Software Engineers， then cmon， at least can use types in your Python or show how to test or integrate this things。 Book talks about what you already know。 Does not talk about what you likely don't know like real-world Bayesian models， calculus， GPUs， statistics etc。 Not a single real example from an industry or academia。 Belittling attitude towards rea Not clear whom this is for。 It skims through engineering and production topics like: populations drift; data engineering; serving。 If this is for Software Engineers， then cmon， at least can use types in your Python or show how to test or integrate this things。 Book talks about what you already know。 Does not talk about what you likely don't know like real-world Bayesian models， calculus， GPUs， statistics etc。 Not a single real example from an industry or academia。 Belittling attitude towards reader。 。。。more
Bugzmanov
，
It's pretty good refresher of core ML concepts。 It's a same-ol same-ol stuff that can be easily found elsewhere。 But packaged in concise and easy digestible form。 Highly recommended。 It's pretty good refresher of core ML concepts。 It's a same-ol same-ol stuff that can be easily found elsewhere。 But packaged in concise and easy digestible form。 Highly recommended。 。。。more
Heather Fryling
，
As a beginner， this book was an ideal starting point， giving me an overview of the field that was mathematical without being overly detailed。
Robert Nasuti
，
Moments of brilliance muddled by math This book had moments of brilliance， but other moments where it got bogged down in minutiae。 The structure was sometimes odd - the author would immediately dive into difficult to follow math at the start of a chapter; then in some summary a few chapters later would give a clear and succinct definition of the algorithm that would be using that earlier math。 It would leave me wishing I’d had the summary before the math。 Overall though the content was good。 The Moments of brilliance muddled by math This book had moments of brilliance， but other moments where it got bogged down in minutiae。 The structure was sometimes odd - the author would immediately dive into difficult to follow math at the start of a chapter; then in some summary a few chapters later would give a clear and succinct definition of the algorithm that would be using that earlier math。 It would leave me wishing I’d had the summary before the math。 Overall though the content was good。 The section on transfer learning in particular stands out to me。 Overall I feel I have a much better understanding of machine learning in its various forms than I did before reading。 。。。more
Cindy
，
If you want to condense machine learning into 100 pages （or more precisely， 136） without losing rigor， you're going to end up with a bunch of math equations because machine learning is essentially math applied to data。 This book is so mathematically dense。 It's symbolically complex and verbally concise。 I really wouldn't recommend this to someone just starting out with machine learning。 It could be a good refresher for someone who has studied machine learning at a graduate level。 Maybe if you've If you want to condense machine learning into 100 pages （or more precisely， 136） without losing rigor， you're going to end up with a bunch of math equations because machine learning is essentially math applied to data。 This book is so mathematically dense。 It's symbolically complex and verbally concise。 I really wouldn't recommend this to someone just starting out with machine learning。 It could be a good refresher for someone who has studied machine learning at a graduate level。 Maybe if you've been working with machine learning for a while and you've forgotten what exactly certain models do mathematically， this could help。 I agree with the author : "Practitioners with experience can use this book as a collection of directions for further self-improvement"。 The information within seems pretty up-to-date in terms of mentioning validation sets， and even genetic algorithms （mentioned briefly） and LSTMs。 Some of the explanations are not sufficient in themselves， and you're going to have to look the topic up online if you're not familiar with it （especially starting on page 65 with deep learning and backpropagation， although the book does include QR codes that you can scan for further elaboration）。 What I really enjoyed was that the author talked about certain statistical assumptions that are made about data in machine learning。 They seem obvious when stated， but they're not necessarily common sense。 For instance， it's usually assumed that your training data is randomly and independently selected from a particular distribution， and a machine learning model trained on the data is supposed to work on unseen future data because we assume that the future data is coming from the same distribution。 I also liked that the author provided multiple ways to solve particular problems （like an imbalanced dataset）。 Solid book。 I recommend it as a reference， but not necessarily as a one-stop shop for teaching yourself machine learning。 。。。more
Winn Koster
，
This book is an exceptional introduction to machine learning techniques for someone who already has a foundation in linear algebra。 It's deliberately limited in scope to get you started， and the author is very thoughtful with this -- if you want to dive into a topic with more detail， links to online examples are provided， as well as notes and recommendations for further reading and more advanced topics。I have now read this cover to cover once， but I expect that I'll pick it up to review certain This book is an exceptional introduction to machine learning techniques for someone who already has a foundation in linear algebra。 It's deliberately limited in scope to get you started， and the author is very thoughtful with this -- if you want to dive into a topic with more detail， links to online examples are provided， as well as notes and recommendations for further reading and more advanced topics。I have now read this cover to cover once， but I expect that I'll pick it up to review certain topics many times going forward。 。。。more
Ferhat Culfaz
，
Nice and simple overview of all the key topics。
Precious
，
Supplementary reading for a graduate class I was allowed to sit-in hehehe （Won’t be rating stuff I read for academic purposes）
LeoQuiroa
，
When I was at school， I used to write a really brief summary about the topic I wanted to learn and read it multiple times。 When I start to read this book， I had a throwback of those memories。 It feels like a very precise and concise summary of ML。 I really recommend this book for an advanced audience as a quick reminder。 On the other hand， for a beginner audience， oh boy！ you will find a dense book。
Syed Nouman Hasany
，
This book is not easy to review。 Some portions have been written exceptionally well （the one on unsupervised learning， for example）， while some portions are almost unreadable （the one on deep learning being the prime candidate）。 What I can safely say is that no one should ever recommend this book to someone starting their Machine Learning journey - if this is the first book they read， it might as well be their last。 However， if you are aware of at least a handful of algorithms and a decent amoun This book is not easy to review。 Some portions have been written exceptionally well （the one on unsupervised learning， for example）， while some portions are almost unreadable （the one on deep learning being the prime candidate）。 What I can safely say is that no one should ever recommend this book to someone starting their Machine Learning journey - if this is the first book they read， it might as well be their last。 However， if you are aware of at least a handful of algorithms and a decent amount of jargon， it can be safely said that you will enjoy this book。 The author has literally tried to cram everything in these 150 pages which means that inevitably you *will* come across passages which might provide interesting insights。 。。。more
Vagif Aghayev
，
An overall good book to review what has already learned。 Really liked the explanation in chapter 5 "Basic practice"。 Finally understood some concepts well and their proper usage。 An overall good book to review what has already learned。 Really liked the explanation in chapter 5 "Basic practice"。 Finally understood some concepts well and their proper usage。 。。。more
Carolina Zheng
，
I guess this book is okay if you don't care about math and want to know what popular algorithms do。 The book is especially allergic to linear algebra - there's no attempt to explain how PCA works。The author finds it necessary to remind readers how to add vectors in the math review chapter while referring to crucial concepts like "convex functions" and "parametric models" without properly defining them。Especially bad were almost all attempts to treat statistics （or， on the other hand， the omissio I guess this book is okay if you don't care about math and want to know what popular algorithms do。 The book is especially allergic to linear algebra - there's no attempt to explain how PCA works。The author finds it necessary to remind readers how to add vectors in the math review chapter while referring to crucial concepts like "convex functions" and "parametric models" without properly defining them。Especially bad were almost all attempts to treat statistics （or， on the other hand， the omission of statistical assumptions that should have been explained）。 Even the word statistic itself was misused in the text （an expectation isn't a statistic）， and SVM is mistakenly referred to as a "statistical model。"And no mention of OLS's analytical solution。。。 I guess scientists were running gradient descent by hand before computers existed？ 。。。more
John Mantios
，
concise and well-explained
Emanuele Del Fava
，
This book provided a very good introduction to machine learning （ML）， favouring intuition to detailed explanation of the different algorithms and functions。 Even though the book was designed to be mostly theoretical （the author showed very few examples from Python， which left me with many doubts concerning the implementation of the various techniques， even the most basic ones）， it did a good job at introducing readers to the jargon of ML and to the large variety of techniques， providing them wit This book provided a very good introduction to machine learning （ML）， favouring intuition to detailed explanation of the different algorithms and functions。 Even though the book was designed to be mostly theoretical （the author showed very few examples from Python， which left me with many doubts concerning the implementation of the various techniques， even the most basic ones）， it did a good job at introducing readers to the jargon of ML and to the large variety of techniques， providing them with practical recommendations on which techniques work better for each type of problem and with suggestions on how to structure the resolution of possible practical problems。 Even though I would have personally loved to see more Python examples， at least for the most basic techniques， I highly recommend this introductory book on ML！ 。。。more
Aina
，
I love this book！ Somehow it’s both wide and deep， covering both fundamentals and details at the same time。 Some pages you need to digest one sentence at a time。 The explanations are all really practical。 This is a book to read over and over again （as not algorithms you are working with every day）。
Mayank
，
Concise and easy introductory text on commonly and some less commonly used ML techniques。
Paresh
，
A decent overview of the key topics in machine learning。 That said， I do not think this book is for beginners （as the author claims）， but rather for individuals who have already learnt machine learning and want a document to refer back to the key concepts。 If you are starting out I would recommend the Elements of Statistical Learning or Andrew Ng’s course on Coursera for machine learning。
Dino Filipović
，
Book is very good intro into Machine Learning from academic perspective。
Data
，
This book swallows up the heavyweight mathematics textbooks and spits out a slim product no thicker than the width of my smartphone。 From page one all the way to page 136， Andriy Burkov， the author， does not waste a single word in distilling the most practical concepts in machine learning。 You read that right。 It is MORE than 100 pages！ Sounds like the book has some bias。 Get it？ At a minimum， prospective readers should be comfortable with Calculus， Statistics， Probability， vectors and matrices， This book swallows up the heavyweight mathematics textbooks and spits out a slim product no thicker than the width of my smartphone。 From page one all the way to page 136， Andriy Burkov， the author， does not waste a single word in distilling the most practical concepts in machine learning。 You read that right。 It is MORE than 100 pages！ Sounds like the book has some bias。 Get it？ At a minimum， prospective readers should be comfortable with Calculus， Statistics， Probability， vectors and matrices， as well as， familiar with data science concepts。 As for data scientists， the majority of your work is likely focusing on a handful of ML models。 While you might skim parts of the book， I think it is still a useful reference because of the breadth of material。 I provide a more in depth summary and commentary on the book at the following webpage:https://thedatageneralist。com/book-re。。。 。。。more
qronisaurous D
，
Shortly said， this book is the type of book that will save you a Google search。 If you have a particular problem type that you know could be or SHOULD be solved with ML; this book will definitely point in the right direction as to what "type" you should be utilizing。 Within this book you won't figure out how to solve your problem but you'll figure out how to figure out how to solve your problem。 I can see myself coming back to this book for more juicy insight。 Shortly said， this book is the type of book that will save you a Google search。 If you have a particular problem type that you know could be or SHOULD be solved with ML; this book will definitely point in the right direction as to what "type" you should be utilizing。 Within this book you won't figure out how to solve your problem but you'll figure out how to figure out how to solve your problem。 I can see myself coming back to this book for more juicy insight。 。。。more
Susmit Islam
，
Not too much in it for beginners， I'd say。 The book is short， at about 150 pages long。 But it covers a lot of the theory behind the most commonly used machine learning algorithms， and discusses a bit about their implementations as well。 It will serve as a good refresher if you've had a decent intro to these topics before at least at a theoretical or practical level。Topics covered include supervised learning algorithms like linear regression， logistic regression， support vector machines， decision Not too much in it for beginners， I'd say。 The book is short， at about 150 pages long。 But it covers a lot of the theory behind the most commonly used machine learning algorithms， and discusses a bit about their implementations as well。 It will serve as a good refresher if you've had a decent intro to these topics before at least at a theoretical or practical level。Topics covered include supervised learning algorithms like linear regression， logistic regression， support vector machines， decision trees， implementation through gradient descent， practical tips like normalisation， standardisation， one-hot encoding， hyperparameter tuning， cross-validation， preventing overfitting by regularisation of models， assessing model fit through confusion matrices， ROC curves， neural networks， convolutional and recurrent neural networks， kernel regression， ensemble learning algorithms such as random forests， gradient boosting， one-shot learning， transfer learning。 Among the unsupervised learning algorithms - k-means clustering， DBSCAN， HDBSCAN， kernel density estimation， a hint of principal component analysis and UMAP。 Other than these， ranking algorithms and recommendation algorithms were briefly touched on。Overall， the book would stand around somewhere between "okay" and "great" for me。 。。。more
Ashok Krishna
，