- Hardcover: 410 pages
- Publisher: Cambridge University Press; 1 edition (May 19, 2014)
- Language: English
- ISBN-10: 1107057132
- ISBN-13: 978-1107057135
- Product Dimensions: 7 x 1.1 x 10 inches
- Shipping Weight: 1.8 pounds (View shipping rates and policies)
- Average Customer Review: 18 customer reviews
- Amazon Best Sellers Rank: #119,369 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Understanding Machine Learning: From Theory to Algorithms 1st Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
"This elegant book covers both rigorous theory and practical methods of machine learning. This makes it a rather unique resource, ideal for all those who want to understand how to find structure in data."
Bernhard Schölkopf, Max Planck Institute for Intelligent Systems
"This is a timely text on the mathematical foundations of machine learning, providing a treatment that is both deep and broad, not only rigorous but also with intuition and insight. It presents a wide range of classic, fundamental algorithmic and analysis techniques as well as cutting-edge research directions. This is a great book for anyone interested in the mathematical and computational underpinnings of this important and fascinating field."
Avrim Blum, Carnegie Mellon University
"This text gives a clear and broadly accessible view of the most important ideas in the area of full information decision problems. Written by two key contributors to the theoretical foundations in this area, it covers the range from theoretical foundations to algorithms, at a level appropriate for an advanced undergraduate course."
Peter L. Bartlett, University of California, Berkeley
Machine learning makes use of computer programs to discover meaningful patters in complex data. It is one of the fastest growing areas of computer science, with far-reaching applications. This book explains the principles behind the automated learning approach and the considerations underlying its usage. The authors explain the "hows" and "whys" of the most important machine-learning algorithms, as well as their inherent strengths and weaknesses, making the field accessible to students and practitioners in computer science, statistics, and engineering.
Author interviews, book reviews, editors picks, and more. Read it now
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
I'm enjoying the book. It reads like a textbook that one might find at a university, and has exercises and notes for the order you'd go through it while teaching a class. I find it well-written and for the most part, easy to digest--a bit heavy on the math for what I was looking for, but you can skim over it for the ideas.
Each chapter is rather short (15-20 pages), yet is well written to convey the topic in detail, making the book comfortable to read.
Moreover, the connection among consecutive chapters is strong, giving an excellent coarse-to-fine introduction on sophisticated theories.
Over the past few years, I have read several machine learning books, and this is the one solidly based on "statistical learning theory".
Compared to other books that give only brief description to this aspect, this book does a good job not only on providing the basic proofs, but also on extending the theories to well-known practical algorithms, supporting the success of these algorithms and showing how theories can be used to design or analyze practical algorithms. For whom eager to know more about learning theory, this is a must-read book.
This is probably not the first introductory book in ML (the readers with strong mathematical background can disregard this reservation, they indeed can use this as !), for the beginners who want to learn the basic concepts of the ML and to understand the motivation behind the mathematical concepts I would recommend something like "Learning from Data" by Yaser Abu-Mostafa et al. http://www.amazon.com/Learning-Data-Yaser-S-Abu-Mostafa/dp/1600490069/ref=sr_1_1?s=books&ie=UTF8&qid=1416599862&sr=1-1&keywords=learning+from+data complemented by the e-chapters in the online forum http://book.caltech.edu/bookforum/ and, probably, by online course (see http://edx.org ).
But for those who have already got some basic ideas about the concepts of ML and the motivation for the theoretical justification of the algorithms, this is definitely should be the next book to read: it provides the rigorous proofs and presents the concepts and algorithms in clear mathematical language. There is no need to be scared though: the presentation of the stuff is excellent, the chapters are short enough in order to enable the reader to advance in reasonable steps (the book is derived from the lectures presented by both of the authors), there are excellent exercises. The theory is indeed well connected to practical algorithms and real applications as promised by the subtitle :)
What I especially like about this book is that it gives a good theoretical background, before jumping into the algorithms.
When getting to the algorithms the author show how to use the theoretical tools to analyze them, which is great !
Also, the theoretical part was enough for me to further read and understand more recent theoretical ML research papers.
That is a great feeling ! I wholeheartedly recommend this great book for graduates.
by introducing students to formal broad conceptual frameworks for understanding, comparing, analyzing,
and designing large classes of popular machine learning algorithms. These frameworks are explicitly presented
as mathematical theorems but the authors are careful about explaining the underlying assumptions of key theorems and
interpreting the conclusions of such theorems. Richard M. Golden.