What do you think?
Rate this book
Adaptive Computation and Machine Learning
Introduction to Machine Learning
A substantially revised fourth edition of a comprehensive textbook, including new coverage of recent advances in deep learning and neural networks.
The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Machine learning underlies such exciting new technologies as self-driving cars, speech recognition, and translation applications. This substantially revised fourth edition of a comprehensive, widely used machine learning textbook offers new coverage of recent advances in the field in both theory and practice, including developments in deep learning and neural networks.
The book covers a broad array of topics not usually included in introductory machine learning texts, including supervised learning, Bayesian decision theory, parametric methods, semiparametric methods, nonparametric methods, multivariate analysis, hidden Markov models, reinforcement learning, kernel machines, graphical models, Bayesian estimation, and statistical testing. The fourth edition offers a new chapter on deep learning that discusses training, regularizing, and structuring deep neural networks such as convolutional and generative adversarial networks; new material in the chapter on reinforcement learning that covers the use of deep networks, the policy gradient methods, and deep reinforcement learning; new material in the chapter on multilayer perceptrons on autoencoders and the word2vec network; and discussion of a popular method of dimensionality reduction, t-SNE. New appendixes offer background material on linear algebra and optimization. End-of-chapter exercises help readers to apply concepts learned. Introduction to Machine Learning can be used in courses for advanced undergraduate and graduate students and as a reference for professionals.
The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Machine learning underlies such exciting new technologies as self-driving cars, speech recognition, and translation applications. This substantially revised fourth edition of a comprehensive, widely used machine learning textbook offers new coverage of recent advances in the field in both theory and practice, including developments in deep learning and neural networks.
The book covers a broad array of topics not usually included in introductory machine learning texts, including supervised learning, Bayesian decision theory, parametric methods, semiparametric methods, nonparametric methods, multivariate analysis, hidden Markov models, reinforcement learning, kernel machines, graphical models, Bayesian estimation, and statistical testing. The fourth edition offers a new chapter on deep learning that discusses training, regularizing, and structuring deep neural networks such as convolutional and generative adversarial networks; new material in the chapter on reinforcement learning that covers the use of deep networks, the policy gradient methods, and deep reinforcement learning; new material in the chapter on multilayer perceptrons on autoencoders and the word2vec network; and discussion of a popular method of dimensionality reduction, t-SNE. New appendixes offer background material on linear algebra and optimization. End-of-chapter exercises help readers to apply concepts learned. Introduction to Machine Learning can be used in courses for advanced undergraduate and graduate students and as a reference for professionals.
712 pages, Hardcover
First published October 1, 2004
85 people are currently reading
645 people want to read
About the author
Ethem Alpaydin
7 books15 followersEthem ALPAYDIN received his BSc from Department of Computer Engineering of Bogazici University in 1987 and the degree of Docteur es Sciences from Ecole Polytechnique Fédérale de Lausanne in 1990. He did his postdoctoral work at the International Computer Science Institute, Berkeley in 1991 and afterwards was appointed Assistant Professor at the Department of Computer Engineering of Bogazici University. He was appointed Associate Professor in 1996 and Professor in 2002 in the same department.
As visiting researcher, he worked at Department of Brain and Cognitive Sciences, MIT in 1994, International Computer Science Institute, Berkeley in 1997, IDIAP, Switzerland in 1998, and TU Delft in 2014.
He was Fulbright Senior Scholar in 1997/1998 and received the Research Excellence Award from the Bogazici University Foundation in 1998 (junior faculty) and 2008 (senior faculty), the Young Scientist Award from the Turkish Academy of Sciences in 2001 and the Scientific Encouragement Award from the Turkish Scientific and Technical Research Council in 2002.
His book Introduction to Machine Learning was published by The MIT Press in October 2004; its German edition was published by Oldenbourg Verlag in May 2008, and Chinese edition was published by Huazhang Press in June 2009. Introduction to Machine Learning, second edition was published by The MIT Press in February 2010; its Turkish edition was published by Bogazici University Press in April 2011 and Chinese edition was published by Huazhang Press in June 2014. Introduction to Machine Learning, third edition was published by The MIT Press in August 2014.
He was an Editorial Board Member of The Computer Journal (Oxford University Press) in 2008-2014. He is a Member of The Science Academy, Turkey, Senior Member of the IEEE, and an Editorial Board Member of Pattern Recognition (Elsevier).
As visiting researcher, he worked at Department of Brain and Cognitive Sciences, MIT in 1994, International Computer Science Institute, Berkeley in 1997, IDIAP, Switzerland in 1998, and TU Delft in 2014.
He was Fulbright Senior Scholar in 1997/1998 and received the Research Excellence Award from the Bogazici University Foundation in 1998 (junior faculty) and 2008 (senior faculty), the Young Scientist Award from the Turkish Academy of Sciences in 2001 and the Scientific Encouragement Award from the Turkish Scientific and Technical Research Council in 2002.
His book Introduction to Machine Learning was published by The MIT Press in October 2004; its German edition was published by Oldenbourg Verlag in May 2008, and Chinese edition was published by Huazhang Press in June 2009. Introduction to Machine Learning, second edition was published by The MIT Press in February 2010; its Turkish edition was published by Bogazici University Press in April 2011 and Chinese edition was published by Huazhang Press in June 2014. Introduction to Machine Learning, third edition was published by The MIT Press in August 2014.
He was an Editorial Board Member of The Computer Journal (Oxford University Press) in 2008-2014. He is a Member of The Science Academy, Turkey, Senior Member of the IEEE, and an Editorial Board Member of Pattern Recognition (Elsevier).
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 18 of 18 reviews
to-read-in-part
December 13, 2018For a general introduction to machine learning, we recommend (Alpaydin, 2004).
Natural Language Processing with Python Pág.256
Natural Language Processing with Python Pág.256
December 1, 2019
This is a great book with horrible notations... The notation (i.e. formulas, equations, variable names and math) is so strange that, you struggle with the concepts you know... let alone complicated concepts that you don't...
Descriptions and the text is excellent though...
Descriptions and the text is excellent though...
Want to read
October 14, 2014Easy and straightforward read so far (page 230). However I have a rounded programming background and have already taken numerous graduate courses in math including optimization, probability and measure theory. So it is a good statement of the types of problem we like to solve, with intuitive examples, and the character of the solutions that classes of techniques will yield. In this sense, it can be a quick read and good overview - and enough discussion surrounding the derivations so that they are fairly easy to follow.
December 18, 2017
A quick intro/overview of machine learning . . . kind of dull/predictable in chapters 1-3 but perks up when it gets to Neural Networks (chap. 4), clustering (chap. 5), and reinforcement (chap. 6).
December 27, 2020
The title of this book is slightly misleading; it's perhaps not the first book anyone will find interesting who is just learning the techniques, basics and behind the scenes implementations of ML.
Sadly, this is such a rapidly expanding field that much of the book deals with a number equations for techniques no longer used. It's not the author's fault by any means, as putting ones arms around the entirety of the state of the art in AI is a technology that changes daily - perhaps even hourly, so any book on the subject is out of date once printed. For traditional programmers, AI (or in this case ML) gives us a way out of certain problems which boxed us in before. With the advent of convolutional neural networks appearing to generate the majority of AI research right now (December, 2020), the information contained herein is still pertinent. This book also explains a number of concepts which are still in wide use today (softmax activation, sigmoidal regression, etc.).
However, this is a heavy read; meaning, don't read this like a novel and expect to come out of the experience training Tensorflow to find and collect cat pictures online for you. This subject is too complex and thus reading this book alone is too wide of a gap between theory (which is this book) and actual implementation (which is not in this book).
Highly technical materiel will never be in the realm of NYT or Amazon best-selling books. Thus, I give credit where credit is highly due: Ethem Alpaydin knows his stuff and wrote this a few years back when much of the modern NN frameworks hadn't even been written yet. The author knew this wasn't going to break sales records at the local Barnes & Noble yet he clearly spent a lot of time in writing this book for others seeking more information on this topic anyway.
For programmers or those who have to implement a neural net, this could give you a great place to start, though personally I'd enjoy a less heavy introduction focusing on the concepts without the calculus. But the author does a superb job in walking the reader through the regression troubleshooting phase (e.g. how to correctly identify over-fitting). Additionally, some concepts are introduced, such as how to divide a test and validation data set, which isn't something normally learned as a developer. A data scientist on the other hand reading this book will also find some interesting background to the decisions as to why one model is superior to another for a specific task.
It's definitely not a Dummies Publishing book.. The reader should expect to break a mental sweat by the third or fourth page. I read deeply technical books all the time, and for other weirdo's like me, this one is well written and built as both a readable book as well as a reference guide.
That said, there are less aggressive ways of learning this topic than head first into the derivatives which make up the neuron weights for a given, trainable model. But, if you would like the under the hood view (as I often do), if you are willing to go deep this book does bring to mind topics which are glossed over in other AI/ML/CNN/ANN texts. For this reason, it's not a wasted read at all. While it was written less than a decade ago, it does go deeper than most in this category on some best practices in tuning a theoretical deployment with great examples and excellent pseudo-code break outs within the narrative.
Sadly, this is such a rapidly expanding field that much of the book deals with a number equations for techniques no longer used. It's not the author's fault by any means, as putting ones arms around the entirety of the state of the art in AI is a technology that changes daily - perhaps even hourly, so any book on the subject is out of date once printed. For traditional programmers, AI (or in this case ML) gives us a way out of certain problems which boxed us in before. With the advent of convolutional neural networks appearing to generate the majority of AI research right now (December, 2020), the information contained herein is still pertinent. This book also explains a number of concepts which are still in wide use today (softmax activation, sigmoidal regression, etc.).
However, this is a heavy read; meaning, don't read this like a novel and expect to come out of the experience training Tensorflow to find and collect cat pictures online for you. This subject is too complex and thus reading this book alone is too wide of a gap between theory (which is this book) and actual implementation (which is not in this book).
Highly technical materiel will never be in the realm of NYT or Amazon best-selling books. Thus, I give credit where credit is highly due: Ethem Alpaydin knows his stuff and wrote this a few years back when much of the modern NN frameworks hadn't even been written yet. The author knew this wasn't going to break sales records at the local Barnes & Noble yet he clearly spent a lot of time in writing this book for others seeking more information on this topic anyway.
For programmers or those who have to implement a neural net, this could give you a great place to start, though personally I'd enjoy a less heavy introduction focusing on the concepts without the calculus. But the author does a superb job in walking the reader through the regression troubleshooting phase (e.g. how to correctly identify over-fitting). Additionally, some concepts are introduced, such as how to divide a test and validation data set, which isn't something normally learned as a developer. A data scientist on the other hand reading this book will also find some interesting background to the decisions as to why one model is superior to another for a specific task.
It's definitely not a Dummies Publishing book.. The reader should expect to break a mental sweat by the third or fourth page. I read deeply technical books all the time, and for other weirdo's like me, this one is well written and built as both a readable book as well as a reference guide.
That said, there are less aggressive ways of learning this topic than head first into the derivatives which make up the neuron weights for a given, trainable model. But, if you would like the under the hood view (as I often do), if you are willing to go deep this book does bring to mind topics which are glossed over in other AI/ML/CNN/ANN texts. For this reason, it's not a wasted read at all. While it was written less than a decade ago, it does go deeper than most in this category on some best practices in tuning a theoretical deployment with great examples and excellent pseudo-code break outs within the narrative.
February 8, 2024
This is a dense book with almost as much math as text. This book makes most sense when you are already familiar with the basic concepts, as for most of them an intuitive introduction is not provided and most topics are explained math-first (and only).
The notation that Alpaydin uses is strange and not aligned with most other text books on ML. Why use "r" for a truth label when the whole world has settled on "y"? This makes some concepts even harder to grasp.
This book is probably very complete and very correct, but I wouldn't recommend it to people starting out with ML. Although it is posed as an introduction, I think it is more of an intermediate book.
The notation that Alpaydin uses is strange and not aligned with most other text books on ML. Why use "r" for a truth label when the whole world has settled on "y"? This makes some concepts even harder to grasp.
This book is probably very complete and very correct, but I wouldn't recommend it to people starting out with ML. Although it is posed as an introduction, I think it is more of an intermediate book.
August 6, 2021
Written in an unnecessarily complicated and sometimes bad English showing that the writer is not a native speaker of English. Easy notions we explained in a complicated way. Different nominations were used to name known mathematical and technical concepts. Poor non illustrative examples. Not a good investment.
December 1, 2020
The study of machine learning in data science. The book is very technical but that is what you need to learn the subject.
Read
January 7, 2022Some symbol overloading. Nice introduction to SVD.
September 12, 2024
Excellent book for getting up and running with the mathematical and logical foundations of Machine Learning
July 3, 2023
A very good book to learn the whole theory world of machine learning (will refer to it for beginners)
July 29, 2014
Very decent introductory book. It gives a very broad overview of the different algorithms and methodologies available in the ML field. Each chapter reads almost independently. It is similar to the Mitchell book but more recent and slightly more math intensive.
July 30, 2012
Simple language.Easily Understandable.
June 20, 2014
Little bit hard to get through, but otherwise quite good as an introductory book. You will want to look up stuff after reading this before applying it though.
October 13, 2016
Very good for starting.
Read
January 7, 2021In supreme philosophy,
an auguring of advanced algorithms(ain’t AGI).
an auguring of advanced algorithms(ain’t AGI).
Read
November 3, 2016terrible, little new information
April 30, 2017
Good introduction to the subject; however, I was expecting a book that was more "popular science." This book is very dry and straightforward. I only read about a third of the book.
Displaying 1 - 18 of 18 reviews