 |
|
Title: Information Theory, Inference & Learning Algorithms
ISBN: 0521642981
Author:
David J. C. MacKay
Publicate Date: 2002-06-15
Publish: 2002-06-15
List Price: $64.00
Average Customer Rating: 4.5
Format: Hardcover
 |
|
|
|
|
Amazon Lowest New Price: $45.00
Amazon Lowest Used Price: $42.46
Amazon Merchant Price: $51.20
|
|
|
|
|
|
|
|
|
|
|
| Customer Review: |
|
1: A Bayesian View: Excellent Topics, Exposition and Coverage
I am reviewing David MacKay's `Information Theory, Inference, and Learning Algorithms, but I haven't yet read completely. It will be years before I finish it, since it contains the material for several advanced undergraduate or graduate courses. However, it is already on my list of favorite texts and references. It is a book I will keep going back to time after time, but don't take my word for it. According to the back cover, Bob McEliece, the author of a 1977 classic on information theory recommends you buy two copies, one for the office and one for home. There are topics in this book I am aching to find the time to read, work through and learn.
It can be used as a text book, reference book or to fill in gaps in your knowledge of Information Theory and related material. MacKay outlines several courses for which it can be used including: his Cambridge Course on Information Theory, Pattern Recognition and Neural Networks, a Short Course on Information Theory, and a Course on Bayesian Inference and Machine Learning. As a reference it covers topics not easily accessible in books including: a variety of modern codes (hash codes, low density parity check codes, digital fountain codes, and many others), Bayesian inference techniques (maximum likelihood, LaPlace's method, variational methods and Monte Carlo methods). It has interesting applications such as information theory applied to genes and evolution and to machine learning.
It is well written, with good problems, some help to understand the theory, and others help to apply the theory. Many are worked as examples, and some are especially recommended. He works to keep your attention and interest, and knows how to do it. For example chapter titles include `Why Have Sex' and `Crosswords and Codebreaking'. His web site ( http://www.inference.phy.cam.ac.uk/mackay/ ) is a wondrous collection of resource material including code supporting a variety of topics in the book. The book is available online to browse, either through Google books, or via a link from his web site, but you need to have it in hand, and spend time with it to truly appreciate it.
|
2: pretty much indispensible
This is an unqualified classic, to shelve with the likes of 'Structure and Interpretation of Computer Programs', 'Concrete Mathematics' and 'Mathematical Methods of Classical Mechanics'. If you are involved with, or interested in, high-end data analytics, then you _need_ this.
However 'high-end data analytics' does not even begin to do the book justice, so let me try again.
This is a magnificient compendium of fascinating stuff presented in a coherent information-theoretic framework. It covers everything from how digital television data compression and CD error correction work to a detailed commentary on neural networks, and discussion of principled AI methods such as clustering, Gaussian processes and probabilistic graphical models, together with Monte-Carlo techniques and a bunch of statistical physics. It even throws in a complete course in Bayesian statistics. It reads like a really good 'popular' 'science' book (I often wonder where the scare quotes should be) that doesn't bother to try to be popular.
In fact I bought this originally as bedside reading, for pleasure. It was only later that I actually used it for anything.
|
3: Outstanding book, especially for statisticians
I find it interesting that most of the people reviewing this book seem to be reviewing it as they would any other information theory textbook. Such a review, whether positive or critical, could not hope to give a complete picture of what this text actually is. There are many books on information theory, but what makes this book unique (and in my opinion what makes it so outstanding) is the way it integrates information theory with statistical inference. The book covers topics including coding theory, Bayesian inference, and neural networks, but it treats them all as different pieces of a unified puzzle, focusing more on the connections between these areas, and the philosophical implications of these connections, and less on delving into depth in one area or another.
This is a learning text, clearly meant to be read and understood. The presentation of topics is greatly expanded and includes much discussion, and although the book is dense, it is rarely concise. The exercises are absolutely essential to understanding the text. Although the author has made some effort to make certain chapters or topics independent, I think that this is one book for which it is best to more or less work straight through. For this reason and others, this book does not make a very good reference: occasionally nonstandard notation or terminology is used.
The biggest strength of this text, in my opinion, is on a philosophical level. It is my opinion, and in my opinion it is a great shame, that the vast majority of statistical theory and practice is highly arbitrary. This book will provide some tools to (at least in some cases) anchor your thinking to something less arbitrary. It's ironic that much of this is done within the Bayesian paradigm, something often viewed (and criticized) as being more arbitrary, not less so. But MacKay's way of thinking is highly compelling. This is a book that will not just teach you subjects and techniques, but will shape the way you think. It is one of the rare books that is able to teach how, why, and when certain techniques are applicable. It prepares one to "think outside the box".
I would recommend this book to anyone studying any of the topics covered by this book, including information theory, coding theory, statistical inference, or neural networks. This book is especially indispensable to a statistician, as there is no other book that I have found that covers information theory with an eye towards its application in statistical inference so well. This book is outstanding for self-study; it would also make a good textbook for a course, provided the course followed the development of the textbook very closely.
|
4: Great wish it had more n option inverse problems
This is fantastic book. Really takes an intuitive approach to the material. The explanation of occam's razor is worth the price of the whole book. Highly recommended.
|
5: Great Book As Far As It Goes
I have used this to get a good background in the topics covered, especially inference theory, and in general I found it to be great book which fills a market gap. The only sins I see are sins of omission. I personally would have enjoyed seeing a more task driven organization. I seem to need these methods periodically but I never seem to need the same method twice. Also, many of the techniques are heavily iterative, i.e., monte carlo, neural networks, etc. This is fine but much of what I do is in the context of simulations where 100,000 step iterative methods don't work so well because of resource constraints. Historically, that has been the problem with many of these methods. They are useful for relatively small domains but don't necessarily work that well for "real" problems. That is probably why more task oriented books are not available. Of course the author is following the outline of the current research into the subject manner which in turn is largely determined by "interesting" and "doable" problems. The real progess in this field will come when the problems are formulated more by what is needed in the nontraditional domains of application. A good example of a useful compression (and identification in some cases) technique that is not covered is Principal Component Analysis. Technically, it is in none of the technique domains covered in this book, but it would have been nice to see some of the methods in the book compared with PCA. The author does make the statement at one point that image recognition is an interesting problem for which the method being discussed at the time is used. Nevertheless, this is a great overview of the subject manner and is very entertaining. That in the long run probably explains the problem: it is a textbook.
|
|
|
|
|
