Customer Reviews

Machine Learning (Mcgraw-Hill International Edit)

5 star:		(14)
4 star:		(2)
3 star:		(4)
2 star:		(1)
1 star:		(0)

 

 

Have you ever bought something that warns "assembly required" only to find out that the instructions are missing? That's a pretty accurate analogy to how Mitchell's book left me feeling. With an empty smile, he hands you a bag of techniques and tells you to go to town. Sure, there are hints about when you might apply particular algorithms, but they are abstract and occasionally hidden in the text. It's as if you've been handed a wrench and told that it can turn things. Huzzah.

When describing a field of knowledge, it's important to communicate the "Big Picture." Mitchell does a poor job of this. That is to say that he doesn't do this at all. The lack of a pervasive thread is all the more odd and disconcerting given that his dissertation gave an amazingly coherent description of the process of inductive learning. I suppose I feel a bit taken because there's nothing so tangible or real to hold the disjoint chapters together. So, without any real historical or philosophical context, we're left with something reminiscent of a first-year calculus book. Here's how to differentiate, here's how to integrate, now go figure out what you're supposed to do with those things.

Nevertheless, anyone needing a reference guide (think of a shop manual) to machine learning techniques (that isn't quite up to date) would do well to buy this book. Anyone wanting to understand the field of machine learning should probably check out a bit of the competition. I think you'll find that some folks' kung fu is stronger.

It's pretty well done, it covers theory and core areas but - maybe it was more the state of the field when it was written - I found it unsatisfyingly un-synthesized, unconnected, and short of detail (but this is subjective). I found the 2nd edition of Russell and Norvig to be a better introduction where it covers the same topic, which it does for everything I can think of, except VC dimension.

The book sorely needs an update, it was written in 1997 and the field has moved fast. A comparison with Mitchell's current course (materials generously available online) shows that about 1/4 of the topics taught have arisen since the book was published; Boosting, Support Vector Machines and Hidden Markov Models to name the best-known. The book also does not cover statistical or data mining methods.

Despite the subjective complaint about lack of depth it does give the theoretical roots and many fundamental techniques decently and readably. For many purposes though it may have been superceded by R&N 2nd ed.

This textbook is useful too much for students that need to learn about learning algorithms. In this textbook explains the key theory and algorithms to solve various problems. For student who plan to make a research in machine learning, this textbooks can give basic knowledge and background of the research.

This book serves as an excellent introduction to machine learning. The material covers a broad range of the important concepts and methods used in machine learning today. The text is well-written and well-organized, and I find myself frequently using it as a reference.

When I came to the field of machine learning, the book provides me a clear, easy-understanding picture to the field so that I believe any of you can get into the field by use of the book. If you are looking for your first book to this field, don't waste your time, it is. Even through my life in the research, I depended on it most of the time. It's too great.

This book is a good introduction to the field, but I think the notation can be quite cumbersome at times. I've seen the concepts presented elsewhere in less confusing form, but it's a good general source as it includes a considerable amount of information from relatively current research. The examples are typically very easy to understand, though they aren't always complicated enough to make the notation easy to understand.

Excellent book , state-of-the-art, nice presentation and covering lots of topics in a friendly manner. highly recommended !

I am a graduate student at a major research university. I am currently taking my fifth AI/Machine Learning graduate course. This is the one book everyone grabs for when they need a reference. I had to mark the spine of my book with tape so I could find it more easily on my colleagues shelves.

Other books are either not as accessible or too niche-specific. This is the only book out there that covers all of the major machine learning techniques (with the possible exception of support vector machines) and covers them in a manner that can be well understood.

Every discipline has one book that must be on your shelf. If you are planning on doing serious research in Machine Learning - this is the one book.

I got this book from the university's library, because I wanted a nice book that can show me different methods for machine learning, so I can learn the buzzwords, and understand their meaning, at least in principle. It was important to me that the book won't go too much in depth into any subject, and more importantly, that the book won't use unfamiliar terminology, unless explained before.

This book is indeed a nice overview of the field at the time it was written, although a lot happened in Machine Learning since, the book remains a good source for learning what can be done and how.

Reading the book is quite easy (I'm a graduate student in computer science), and quickly I got what I was asking for.

This book is not a magic pill for any problem. This is not a cookbook. So the compliments are in place as long as you know what you're looking for.

These days I attend a seminar where the students are asked, each student in turn to present one chapter from this book (and some other books). Surely, once the seminar is over, we (the students) will know enough to be able to chat about Machine Learning, and more importantly, we will know where to look for deeper texts if we wanted to.

I agree with some of the previous reviews which criticize the book for its lack of depth, but I believe this to be an asset rather than a liability given its target audience (seniors and beginning grad. students). The average college senior typically knows very little about subjects like neural networks, genetic algorithms, or Baysian networks, and this book goes a long way in demystifying these subjects in a very clear, concise, and understandable way. Moreover, the first-year grad. student who is interested in possibly doing research in this field needs more of an overview than to dive deeply into
one of the many branches which themselves have had entire books written about them. This is one of the few if only books where one will find diverse areas of learning (e.g. analytical, reinforcment, Bayesian, neural-network, genetic-algorithmic) all within the same cover.

But more than just an encyclopedic introduction, the author makes a number of connections between the different paradigms. For example, he explains that associated with each paradigm is the notion of an inductive-learning bias, i.e. the underlying assumptions that lend validity to a given learning approach. These end-of-chapter discussions on bias seem very interesting and unique to this book.

Finally, I used this book for part of the reading material for an intro. AI class, and received much positive feedback from the students, although some did find the presentation a bit too abstract for their undergraduate tastes