What do you think?
Rate this book
Adaptive Computation and Machine Learning
Foundations of Machine Learning
A new edition of a graduate-level machine learning textbook that focuses on the analysis and theory of algorithms.
This book is a general introduction to machine learning that can serve as a textbook for graduate students and a reference for researchers. It covers fundamental modern topics in machine learning while providing the theoretical basis and conceptual tools needed for the discussion and justification of algorithms. It also describes several key aspects of the application of these algorithms. The authors aim to present novel theoretical tools and concepts while giving concise proofs even for relatively advanced topics.
Foundations of Machine Learning is unique in its focus on the analysis and theory of algorithms. The first four chapters lay the theoretical foundation for what follows; subsequent chapters are mostly self-contained. Topics covered include the Probably Approximately Correct (PAC) learning framework; generalization bounds based on Rademacher complexity and VC-dimension; Support Vector Machines (SVMs); kernel methods; boosting; on-line learning; multi-class classification; ranking; regression; algorithmic stability; dimensionality reduction; learning automata and languages; and reinforcement learning. Each chapter ends with a set of exercises. Appendixes provide additional material including concise probability review.
This second edition offers three new chapters, on model selection, maximum entropy models, and conditional entropy models. New material in the appendixes includes a major section on Fenchel duality, expanded coverage of concentration inequalities, and an entirely new entry on information theory. More than half of the exercises are new to this edition.
This book is a general introduction to machine learning that can serve as a textbook for graduate students and a reference for researchers. It covers fundamental modern topics in machine learning while providing the theoretical basis and conceptual tools needed for the discussion and justification of algorithms. It also describes several key aspects of the application of these algorithms. The authors aim to present novel theoretical tools and concepts while giving concise proofs even for relatively advanced topics.
Foundations of Machine Learning is unique in its focus on the analysis and theory of algorithms. The first four chapters lay the theoretical foundation for what follows; subsequent chapters are mostly self-contained. Topics covered include the Probably Approximately Correct (PAC) learning framework; generalization bounds based on Rademacher complexity and VC-dimension; Support Vector Machines (SVMs); kernel methods; boosting; on-line learning; multi-class classification; ranking; regression; algorithmic stability; dimensionality reduction; learning automata and languages; and reinforcement learning. Each chapter ends with a set of exercises. Appendixes provide additional material including concise probability review.
This second edition offers three new chapters, on model selection, maximum entropy models, and conditional entropy models. New material in the appendixes includes a major section on Fenchel duality, expanded coverage of concentration inequalities, and an entirely new entry on information theory. More than half of the exercises are new to this edition.
480 pages, Hardcover
Published September 1, 2012
About the author
Mehryar Mohri
3 books1 followerMehryar Mohri is Professor of Computer Science at New York University's Courant Institute of Mathematical Sciences and a Research Consultant at Google Research.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 4 of 4 reviews
March 26, 2023
کتاب خوبیه به شرطی که کمی ماشین لرنینگ سرتون بشه. اگر قراره از صفر شروع کنید و دنبال کتابی برای یادگیری می‌گردید، این براتون سخته.
پیشنهاد می‌کنم با کتاب understanding machine learning شای بن‌دیوید آغاز کنید و همزمان با خواندنش ویدئوهای تدریس خود نویسنده در یوتیوب رو هم ببینید.
این کتاب برای آغاز یادگیری اصلا مناسب نیست. به انگلیسیِ سخت توضیح داده. 😜😁
وقتی اون رو کامل کردید و گوشی دستتون اومد، بیاید سراغ این کتاب.
ویدئوهای جادی در مکتب‌خونه رو هم در کنارش ببینید.
پیشنهاد می‌کنم با کتاب understanding machine learning شای بن‌دیوید آغاز کنید و همزمان با خواندنش ویدئوهای تدریس خود نویسنده در یوتیوب رو هم ببینید.
این کتاب برای آغاز یادگیری اصلا مناسب نیست. به انگلیسیِ سخت توضیح داده. 😜😁
وقتی اون رو کامل کردید و گوشی دستتون اومد، بیاید سراغ این کتاب.
ویدئوهای جادی در مکتب‌خونه رو هم در کنارش ببینید.
October 28, 2017
I did not like the texture of the paper of the hardcover version. Reading Mohri was overall very difficult and painful. While the concepts were explained well, the paper stock was too glossy/thick for this book to be a real page-turner.
-1 for explaining Rademacher Complexity before VC dimensions, and not motivating VC dimensions with "No-Free-Lunch" Theorem. I had to read Shai Shalev-Shwartz's book to understand VC dimensions.
-1 for having "feels bad" paper stock. Shai Shalev-Shwartz's book not only motivates Rademacher Complexity well, but also has GREAT paper stock.
Minus two stars overall.
-1 for explaining Rademacher Complexity before VC dimensions, and not motivating VC dimensions with "No-Free-Lunch" Theorem. I had to read Shai Shalev-Shwartz's book to understand VC dimensions.
-1 for having "feels bad" paper stock. Shai Shalev-Shwartz's book not only motivates Rademacher Complexity well, but also has GREAT paper stock.
Minus two stars overall.
March 9, 2017
On balance, this is a clear, thorough and comprehensive introduction to the foundations of machine learning. It is an excellent textbook.
Structurally, the book is clear, beginning with PAC and other research into learnability, proceeding to SVM, kernels and thence on to other, more complex topics: multiclass, Bayesian statistics, Markov models.
Ultimately though, this book is only a textbook. It is a reference and not an instructor. The proofs are clearly presented and easily consulted, but, like most textbooks, this work is a supplement to a lecture series, not a replacement.
Structurally, the book is clear, beginning with PAC and other research into learnability, proceeding to SVM, kernels and thence on to other, more complex topics: multiclass, Bayesian statistics, Markov models.
Ultimately though, this book is only a textbook. It is a reference and not an instructor. The proofs are clearly presented and easily consulted, but, like most textbooks, this work is a supplement to a lecture series, not a replacement.
Read
April 22, 2015Location: GG6 IRC
Accession no: DL027012
Accession no: DL027012
Displaying 1 - 4 of 4 reviews