CREATOR: gd-jpeg v1.0 (using IJG JPEG v62), quality = 75

Introduction to Machine Learning, third edition

The MIT Press

September 2014:  ISBN: 978-0-262-028189

The book can be ordered through The MIT Press, Amazon (CA, CN, DE, FR, IN, JP, UK, US), Pandora (TR).

PHI Learning Pvt Ltd (formerly Prentice-Hall of India) published an English language reprint in 2015 (for distribution in India, Bangladesh, Burma, Nepal, Sri Lanka, Bhutan and Pakistan only).

Table of Contents


Lecture Slides:

(For instructors to use in their courses; please keep the first page and footer if you edit the slides)


  1. Introduction (pdf, pptx)
  2. Supervised Learning (pdf, pptx)
  3. Bayesian Decision Theory (pdf, pptx)
  4. Parametric Methods (pdf, pptx)
  5. Multivariate Methods (pdf, pptx)
  6. Dimensionality Reduction (pdf, pptx)
  7. Clustering (pdf, pptx)
  8. Nonparametric Methods (pdf, pptx)
  9. Decision Trees (pdf, pptx)
  10. Linear Discrimination (pdf, pptx)
  11. Multilayer Perceptrons (pdf, pptx)
  12. Local Models (pdf, pptx)
  13. Kernel Machines (pdf, pptx)
  14. Graphical Models (pdf, pptx)
  15. Hidden Markov Models (pdf, pptx)
  16. Bayesian Estimation (pdf, pptx)
  17. Combining Multiple Learners (pdf, pptx)
  18. Reinforcement Learning (pdf, pptx)
  19. Design and Analysis of Machine Learning Experiments (pdf, pptx)


Instructor Resources: Select the links below "Resources" on the left hand side of the book's MIT Press web page


The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. Subjects include supervised learning; Bayesian decision theory; parametric, semi-parametric, and nonparametric methods; multivariate analysis; hidden Markov models; reinforcement learning; kernel machines; graphical models; Bayesian estimation; and statistical testing.

Machine learning is rapidly becoming a skill that computer science students must master before graduation. The third edition of Introduction to Machine Learning reflects this shift, with added support for beginners, including selected solutions for exercises and additional example data sets (with code available online). Other substantial changes include discussions of outlier detection; ranking algorithms for perceptrons and support vector machines; matrix decomposition and spectral methods; distance estimation; new kernel algorithms; deep learning in multilayered perceptrons; and the nonparametric approach to Bayesian methods. All learning algorithms are explained so that students can easily move from the equations in the book to a computer program. The book can be used by both advanced undergraduates and graduate students. It will also be of interest to professionals who are concerned with the application of machine learning methods.

Introduction to Machine Learning can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods.


“Ethem Alpaydin’s Introduction to Machine Learning provides a nice blending of the topical coverage of machine learning (à la Tom Mitchell) with formal probabilistic foundations (à la Christopher Bishop). This newly updated version now introduces some of the most recent and important topics in machine learning (e.g., spectral methods, deep learning, and learning to rank) to students and researchers of this critically important and expanding field.”
John W. Sheppard, Professor of Computer Science, Montana State University

“I have used Introduction to Machine Learning for several years in my graduate Machine Learning course. The book provides an ideal balance of theory and practice, and with this third edition, extends coverage to many new state-of-the-art algorithms. I look forward to using this edition in my next Machine Learning course.”
Larry Holder, Professor of Electrical Engineering and Computer Science, Washington State University

“This volume is both a complete and accessible introduction to the machine learning world. This is a ‘Swiss Army knife’ book for this rapidly evolving subject. Although intended as an introduction, it will be useful not only for students but for any professional looking for a comprehensive book in this field. Newcomers will find clearly explained concepts and experts will find a source for new references and ideas.”
Hilario Gómez-Moreno, IEEE Senior Member, University of Alcalá, Spain


I would like to thank those who found these and took the time to send them.

·      Miguel Carreira-Perpinan has a list of corrections.

·      (p. 62): In the eighth line under the table, it should read ".... or equivalently if P(C_2|x)>4/5. (Basak Tugce Eskili)

·      (p. 135): In equation (6.29) and the paragraph that follows, u_i should be v_i and v_i should be w_i. (Bas Terwijn))

·      (p. 152): In the second (unnumbered) equation, it should read x^s -- s should be a superscript, not a subscript. (Haotian Zhang)

·      (p. 169): In the second equation of E-step, there is an extra ) before ]. (Haotian Zhang)

·      (p. 169): On line 16, just above "where", at the very end, \phi should not have superscript l. Three lines below, the third line from the bottom, \pi should have superscript l. (Lisa Hellerstein)

·      (p. 170): On lines 8 and 9, at the very end, \phi should not have superscript l. (Lisa Hellerstein)

·      (p. 191): In the solution of Exercise 4, while defining Q', p_ij should not have superscript l.

·      (p. 262): In the second line from the bottom of the page, 'u' (the 'u' on the right-hand side of the inequality) should be 'v'. (Fernando Andre Alarcon Delgado)

·      (p. 355): In the paragraph just below Eq. 13.10, “sections” is misspelled as “sectiona.” (Phil Ringsmuth)

·      (p. 370): In Eq. 13.47, $x^t$ should be deleted. (Xiaosong Zhang)

·      (p. 398): The last line should read \int p(r'|x',w) ( P(X,r|w)p(w)/P(X,r) ) dw (Ali Tabatabai)

·      (p. 447): In the first line of the second paragraph, "some" is misspelled as “sone.” (Jeffrey Robinson)

·      (p. 523): In Eq. 18.9, in the last term “+1” should be subscript, to read  “st+1” (Tao Zheng)

Created on Sep 3, 2014 by E. Alpaydin (my_last_name AT boun DOT edu DOT tr)