Customer Reviews

An Introduction to Support Vector Machines and Other Kernel-based Learning Methods

5 star:		(5)
4 star:		(3)
3 star:		(0)
2 star:		(0)
1 star:		(1)

 

 

This is a first book introducing support vector learning, a very hot area in machine learning, data mining, and statistics. Aside from Burges (1998)'s tutorial article and Vapnik (1995)'s book, this book by two authors actively working in this field is a welcome addition which is likely to become a standard reference and a textbook among students and researchers who want to learn this important subject. Besides tutoring systematically on the standard theory such as large margin hyperplane, nonlinear kernel classifiers, and support vector regression, this book also deals with growing new areas in this field such as random processes. More interestingly, this book discusses a lot of applications which I consider very imoportant and healthy for the advance of this field, such as medical diagnosis, image analysis, and bioinformatics. In all, I strongly recommend this book for students, and young researchers who want to learn. I'm sure a lot of people will find this book a wise investment, since it provides a handy and timely review of a rapidly growing field.

This book introduces the concepts of kernel-based methods and focuses specifically on Support Vector Machines (SVM). It is hard to read and a good background in mathematic is clearly needed. The book has a strong emphasis on SVM starting from the very first line of text. Concepts are well explained, although equations are not clear. The notation doesn't facilitate the reading at all. The book covers linear as well as kernel learning. The kernel trick is well described. It is easy to understand ideas behind SVM while reading the corresponding chapter. Finally a small chapter on SVM applications is proposed. Unfortunately, it only contains typical SVM applications (i.e. standard problems).

I think this book is good if you:

* Have a strong mathematical background
* Work in the specific domain of SVM (or kernel-based methods in general)
* Want to write a research paper about SVM and need the correct notations

However, this book is NOT intended for people who:

* Don't like to read theorems, corollaries and remarks
* Are not interested in reading hundreds of proofs

This is my personal opinion as a computer scientist: this book is definitely written for mathematicians.

I used to believe that the thicker the book, the greater the chance that I'd be able to learn something from it. This book by Cristianini and Shawe-Taylor is the complete opposite.

The book is clear and concise in it's development of the theory of SVMs, and is thorough in going through all relevant background material. Particularly useful is the section optimisation which is usually missing from statistical and computer science backgrounds.

Beware that this book is not for the mathematically shy. If you want to learn about SVMs and don't mind getting your teeth stuck into some serious (applied) maths, then this book is for you.

We incorporated a Support Vector Machine Classifier in our analysis software product. Although other texts and articles provided friendlier background and an easier introduction, when the time came to actually code a classifier, this was the book that offered the level of detail required to build something that ran. The math is heavy, the prose is terse, but it goes deep under the covers of what actually constitutes a kernel transformation, what function families qualify as kernels, as well as deep component-by-component algorithms.

The biggest drawback of this book is that it does not meet the needs of the many non-mathematically inclined who are interested in SVM's. It uses the academic euphemism 'introduction' to mean 'brutally advanced, but if I called it that, no one would buy it'. One of the reviewers was expecting an actual introduction, and was disappointed.

Oh Puhleeeezzzzz... How is your vector math??? Remember your linear algebra well? Do you have a background in SVM's? Intuitively able to suck out of thin air the meaning of the Gamma co-efficient as applied to svm's?? You've read all the background papers and remember your formal logic???? No?? too bad..your out of luck..

This book is more aptly titled an Introduction to the Formalisms of SVM's. If your a software engineer trying to implement one of these, forget it.. Be nice if they put that quadratic algorthim psuedocode into something more readable than greek symbology..

If you are trying to build one of these engines, then this book is of absolutely no help, unless you have a background in machine learning and have read all the papers on SVM's. If you can decompose the math into code in your head, then you might find it entertaining... What I don't get is how all the rest of these reviewers can give such "glowing praise" for this book and have it be so completely worthless as an introduction... makes me think some of these are shills..

Bottom line is, if your trying to code a svm, this book will not help. If your trying to understand how to implement a svm, this book will not help. If you are trying to understand how an svm works, this book will not help. If you want to know the mathematical basis for SVM's and like that presentation.. this is the book for you..

I'm currently an undergraduate in computer science and math at a Cal State university, and I found this book to be both complete and accessible. In six weeks of independent study, I was able to implement an SVM and recreate the chessboard example from his book, and now I find myself reading research-level papers on more advanced kernels and datasets.

My only real criticism of the book is that the authors sometimes resort to wacky matrix notation to get mathematical expressions to fit inline, when they really should be centered and displayed in full.

I think the best addition would be a prologue entitled "How To Read This Book," because it seems that other reviewers are dissatisfied by the lack of hand-holding required for someone with none of the (prerequisite) comfort level with linear algebra notation and methods of proof. That being said, almost all of the proofs contained in the book are there for completeness alone. One does not need to reprove each proposition in order to understand how to implement an SVM or grasp the concepts behind kernel-based methods. For instance, the KKT conditions are essential as a measure of convergence in training an SVM, but the derivation is superfluous for an engineer.

As an analogy, just because a book on algorithms presents bubble sort doesn't make bubble sort important, but omitting bubble sort (or some other introductory sorting algorithm) would make an introductory volume incomplete. The authors here provide the same foundations for support vector machines, so that the reader can actually understand why it works. This book is self-contained, and it's much better for it.

In my search for a good book on SVMs, this one was by far superlative. I would recommend it to anyone in my position who is interested in mathematics and programming.

I just happened to read the reviews on the book on Support vector machines by Nello Cristianini and John Shawe-Taylor. Could not resist adding my own comments about the book. Excellent book. I plan to use the book for the course on "Fundamentals of computer aided engineering" that I teach at the Swiss Federal Institute of Technology, Lausanne (EPFL).

I wrote my review of this book on the ai forum.
You can see my write up there at the link below:

http://agsforum.agstechnet.com/index.php?topic=30.msg33;topicseen#msg33

I liked the book overall.

The book is just great. The appendix on algorithms could have more explanations. Also the application section is a short. It would have been more usuful to take one of these applicaitons and describe it in details. But all in all, the book is excellent.