The fundamental mathematical tools needed to understand machine learning include linear algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability and statistics. These topics are traditionally taught in disparate courses, making it hard for data science or computer science students, or professionals, to efficiently learn the mathematics. This self contained textbook bridges the gap between mathematical and machine learning texts, introducing the mathematical concepts with a minimum of prerequisites. It uses these concepts to derive four central machine learning methods: linear regression, principal component analysis, Gaussian mixture models and support vector machines. For students and others with a mathematical background, these derivations provide a starting point to machine learning texts. For those learning the mathematics for the first time, the methods help build intuition and practical experience with applying mathematical concepts. Every chapter includes worked examples and exercises to test understanding. Programming tutorials are offered on the book’s web site.
-78%
Mathematics for Machine Learning
Original price was: $88,99.$19,95Current price is: $19,95.
✔️ File: PDF 16,30 MB • Pages: 417
Ilya A. Shlyakhter –
Excellent for reviewing concepts you’ve understood a while back but have since gotten rusty on. Just the right level of detail. If learning for the first time, other books that spend more time illustrating/motivating the concepts might be better — can’t say for sure as I’m not in that position. But for reviewing, it’s great. The book fulfills a definite need by bringing in one place the mathematics most relevant to ML, and going through it in a concise yet precise manner.
Estefano Palacios Topic –
The book is the missing piece between books like Artificial Intelligence: A Modern Approach and the mathematics you require to take such an undertaking. The authors do assume very little prior knowledge from the reader, but it t is recommended that you’ve had exposure to some of the mathematical topics prior to reading the book. But don’t let that stop you if you’re a beginner: you’ll have to make a few detours to grasp some terms and such. Having said that, a course on single variable calculus ought to be under your belt. That’s basically the only prerequisite.
The explanations are clear, and the book is designed to bring clarity and lucidity onto the topics, not send the student on an endless pit of proofs and rigor.
Pi –
I read the draft of the book which was available prior to the release. The book is difficult to read and less intuitive to an audience who wish to dig deeper. I would prefer to read books like Hastie and Bishop over this.
Srikanth Hanumanthappa –
Best book if you are looking to study math of machine learning! Author has given references where to do further studies. If you are beginner to calculus , linear algebra and probability n statistics this is not the book since book expect you at advanced mathematics level Or studied the basics of math concepts in your curriculum
Thomas Paine –
This is a subject where people say, “I understand the underlying math.” Factually incorrect. The underlying math IS what to understand. I love the topic and I want to expand my depth and breadth of knowledge–and I’m not disappointed.
Ihatepickles –
Just an unbelievable book. It may be a bit difficult to follow but complemented by a couple of online resources for when you’re stuck it’s awesome. Definitions are precise. Explanations are succinct.
It is not intended to be, but is a masterpiece that brings out the beauty of mathematics.
alcidessd –
Very good product and service 100% recommended.
SB Jones –
I recommend the book for its clear delineations of sections within chapters. It makes for a good reference for calculations that may not be on the tip of your tongue. I would lodge one major complaint, hence 4 stars, they should make the answers available for the questions at the end of the chapters. Without them, the quizzes are essentially a waste of space as you have no idea if your calculations are correct.
Mavichov(gh.liang) –
Even though I can get a free e-copy, I still like the paperback version because I flip through it occasionally. This book sketches a clear big picture of the knowledge tree for ML and provides necessary build blocks to help you build solid foundations in preparation for practical ML.
You have to be aware this paperback version doesn’t come with solutions. One of my reason to buy this is for the solutions. It turned out that only instructors can request solutions from the press company.
Peter Washington –
In college, I was bored out of my mind during Linear Algebra, Multivariable Calculus, and Statistics courses. I wish the concepts would be introduced in the way they are in this book. For example, partial differentiation and gradients are explained in terms of neural network weight optimization / gradient descent. This book is especially valuable if you know the basic intuition behind machine learning and neural networks, and also have a basic intuition behind the math, and want to combine this intuition with a formal mathematical understanding.
Tom –
like the book.. paperback is handy for reference
Ethan –
This book is great for combining all of the domains of math that form machine learning. If you are a beginner and haven’t had much college math training, I recommend reading the sections and supplementing with external resources such as Khan Academy and YouTube because the writing in this book is very formal. In my experience with this book, if I go to KA and work out whatever I am having trouble with and then return to this book, then I will understand the material and how it fits into the big picture.
Mark –
The format – definition, theorem, example – make this book very accessible to all STEM undergraduates. It is a good survey of introductory topics found in a linear algebra and multivariable calculus course. However, if you have already taken these courses or taken much more difficult math, this book is a disappointment – it references a lot of other texts when the math gets interesting – i.e. instead of covering the approximation of linear equations via Krylov methods, it just reference other texts if you are interested.
JRVV –
Fits my needs pretty well. A well-curated collection of the essential math for AI and ML. I purchased the physical copy, despite having the free PDF, because I enjoyed it a lot and plan to re-read it with more detailed note-taking and highlighting on the book itself. I did have to consult other sources just to clear up some parts but was expected in reading a math book. Highly recommended!
BlaST –
I bought this book expecting to be babied in Linear Algebra, Vector Calculus, Probability, etc… so I could fill in the mathematical gaps in my machine learning adventures.
THEY DO NOT BABY YOU.
The authors even say in the preface of this book that it is terse and they WEREN’T KIDDING.
They DO NOT explicitly explain the mathematical concepts they use in their examples and I have spent lots of time trying to decipher and search the internet for explanations to comprehend what’s in this book. I would rather buy a book just on Linear Algebra that babies me through everything than go through this.
This isn’t necessarily a fault of the book per se… they just assume you have solid mathematical fundamentals from High School/College. And I guess I don’t.
Smehta –
It’s a bit terse to read at times but worth persevering through. The book contains good detail of key mathematical concepts and their uses in machine learning
Tuan Tran –
This book is excellent for brushing up your mathematics knowledge required for ML. It is very concise while still providing enough details to help readers determine important parts. This is my go-to if I need to review some concepts or brush up on my knowledge in general.
I wouldn’t recommend this book if you have absolutely no prior math experience though as it can be hard to digest and sometimes they would skip parts here and there in proofs and examples. Especially for the probability section, the concepts will be very hard to grasp without prior knowledge
Galileu Kim –
A brilliant didactical work on the mathematical foundations of machine learning.
javier wilder carruitero buzzio –
This is an awesome book but you need some basic experience on linear algebra and calculus to put in context and make it easier going through the content.
Ayshen –
Great book who wants to understand the maths behind the ML models, but some parts are rocket science :). I would definitely recommend this book to people in academia or to whom who has enough time to dive deep into theoretical aspect of the ML.
Sodipo Gideon Olawale –
This book really provides the mathematical foundation of machine learning and also points the reader to relevant text and materials for full reference.
Anthony Garza –
Read this carefully, work the examples outlined in grey. This goes great with any math methods book like boas,potter, or riley
Zenifer Cheruveettil –
I could somewhat understand this book only because I’ve learned the topics from other sources. Book covers all of the topics required for machine learning, but is presented in a very dull way.
Biggest disappointment is that book claims to be suitable for “evening learners” and assumes only high school math from its readers, but isomorphism and Abelian groups are introduced out of the blue. I’m not sure whether there is any high school anywhere those topics are taught.
FPAGL –
Les bases mathématiques et analyse numériques de niveau Master1 (Bac+4).
Agréable à avoir en format papier.
+ accès au site web pour suivre les quelques coquilles.
Simple regret : impossible d’accéder aux corrections des nombreux exercices sans être un enseignant dans une faculté.
Javier Espinoza Traslaviña –
Great undergraduate mat material
Sterling Ramroach –
I have a PhD in ML and a CS background. My stats knowledge is lacking so I was hoping this book could help me get a better understanding of the core foundational concepts in ML.
In the first few chapters (Part 1 of the book) there is a lot of skimming over the math which makes it difficult for me to learn. I have to spend more time looking at other sources to fill in the blanks.
Part 2 is a lot easier to read. I enjoyed these chapters a lot more.
Than Hau Wan, Jennifer –
Book arrived in good condition
jahbar –
Good book
Guest –
The treatment of linear algebra is very interesting. After reading the book, I am able to connect many dots in this subject.
Michael –
Don’t get me wrong, this is a really good book. But this is a book that’s stuck somewhere between a Mathematics book and a Computer Science book.
Having studied the mathematics in ML during college, I’m already familiar with the topic discussed in the book. I’m mainly reading it as a refresher of linear algebra and calculus that I haven’t used in years.
It does a good job laying out necessary mathematical concepts, but it doesn’t do as good of a job at providing proofs/explanations to a lot of the properties and extensions. For example, the book gives a good algebraic definition of orthogonality in terms of vectors and subspaces (inner product of the vectors/subspaces in question equal 0). However, in the next section about function orthogonality, the book just says “functions can be seen as vectors” and provides a definition in terms of a definite integral. The book didn’t provide reasoning for such a jump from inner product to integral, nor did it provide explanations or intuitions for the upper and lower bounds of the integral. There are many more examples where the book doesn’t provide proofs/explanations and hurries on to introduce new concepts.
The first few chapters alone is definitely enough for you to understand the concepts of the later chapters, but you WILL need to read dedicated mathematics textbooks (like the ones they pointed out in the “further readings” sections at the end of each chapter) if you want to form a sound mathematical foundation.
On the other hand, it did a decent job introducing many important algorithms in ML and the mathematics behind them, but it also lacks many key ideas important to ML. One would expect a book focusing on the mathematical side would be fairly theoretical on the subject of learning, but it doesn’t cover fundamental theories in learning such as PAC learning, VC dimensions, No Free Lunch theorem, etc. I think the “Understanding Machine Learning: From Theory to Algorithms” book by Shai Shalev-Shwartz and Shai Ben-David is a much better read on those subjects.
Overall, it’s a good book to have, especially when you need to a quick refresher on the mathematics or needs some help understanding the mathematical intuitions behind popular ML algorithms. What the book is not, is a beginner-friendly machine learning textbook for those who don’t already know some linear algebra.
María del mar y Elena –
La entrega muy bien. El Producto estaba muy protegido y llegó intacto.
L. A. Duran –
This is an excellent intro to the mathematics behind machine learning. It doesn’t go so deep that you fall asleep but it also doesn’t gloss over some very important details.
Having said that, there is no reason to buy this book as it is free for download from GitHub.
DavidSpb –
This book delivers what one should reasonably expect. If you transition to ML, you need understanding of underlying math in order to work in this field at an advanced level. This book covers most of math you need – linear algebra, analytic geometry, vector calculus, multivariate calculus, probability, statistics, and optimization.
The book is around 350 pages, so I do not understand the reviewers complaining about the lack of rigor. It cannot possibly be rigorous, but it contains enough useful pointers in case you need to drill down on anything in particular. If you have decent college-level math background and did your share of proofs, all you need now is a nice refresher focused specifically around ML, and this book is perfect for that.
alireza –
This is it. I got pretty far with this book in my graduate studies. The covered math is all you need to have a solid foundation to read cutting-edge papers and develop advanced intelligent systems. There are also plenty of exercises to consolidate your knowledge. Well done to the authors.
Gabriella –
Le basi matematiche di questo libro non sono da super specialisti. Ma anche per chi è un ricercatore, questo libro offre un approccio diverso su molti temi standard, facendoti guardare a cose che conosci bene da un punto di vista inaspettato
Slacker –
Nachdem ich vor 25 Jahren Informatik studiert habe und dort bereits “Neuronale Netze” (feed-forward back-propagation) kennengelernt hatte, wollte ich, motiviert durch den Hype der aktuellen AI (insbesondere machine learning sowie deep learning) mehr darüber lesen.
Daher zunächst das “Standardwerk” (Titel “Deep Learning”) gekauft. Die dort enthaltene Mathematik ist, meines Erachtens, so stark ver-klausuliert und auch von der Notation her schwer zu lesen, dass ich dieses Buch hier “Mathematics for Machine Learning” gekauft habe: Ich muss sagen/schreiben: Das ist die BESTE Darstellung der verschiedenen mathematischen Themenbereiche (Vektoren, Matrizen, Lineare Algebra, Wahrscheinlichkeitsrechnung, u.s.w.), die ich als Praktiker der Informatik je gesehen habe.
Sehr gut verständlich (mit dem math. Grundwissen eines Informatikers), sehr tolle praxis-bezogene Beispiele zu den mathematischen Verfahren.
Darüber hinaus in einem hervorragenden Englisch geschrieben, das wirklich Freude macht, es zu lesen.
Ich denke, dass jeder, der sich intensiv mit Machine Learning auseinandersetzen möchte, hier sowohl ein Lehrwerk als auch ein Nachschlagewerk erhält.
Übungen mit Lösungen (auf github) runden dieses Buch ab. Ich bin begeistert!!!
Varun –
The authors assumed a certain degree of mathematical knowledge the reader’s part. I would recommend it to someone whose mathetical proficiency is lukewarm at best. You’d be better off taking online course and then using this as a reference instead of making this your go to resource.