Artificial Intelligence: A Modern Approach (2nd Edition) (Prentice Hall Series in Artificial Intelligence)

Recommended for people looking for a good, but not that mathematical, summary of the field.

As a student with a very strong background in technical fields I am no stranger to heavy studying, reference, and in some cases even total reliance on textbooks. I have encountered many kinds of textbooks, some which get the job done, some which do the same painfully, and unfortunately a select few that were simply inscrutable and probably inhibited my learning more than anything else.

This textbook however, is definitely a cut above all the rest. It's very likely that it's the best textbook I've ever used for any subject, and in my opinion, contains an ideal combination of things:

1. The authors take pains to insert a small "exordium" before every major topic, explaining the topic's history, importance, relevance, and perhaps most uniquely, a text "roadmap" of what the authors are going to explain. The last factor is most refreshing to me, because it helps to concretely focus my attention on the overall organizational structure that the authors have decided to employ, giving each chapter (and the book in general) a much more cohesive and readable feel than is normal for a heavily technical textbook. It also helps to pique my own interest (and therefore extend my attention span) about the overall evolution of AI.

2. Explanations of concepts, whether old, new or concepts too advanced to be discussed at length, are the best I've ever had from a text-based source. I don't find myself re-reading technical explanations very often, and if I do, it's usually only to remember what certain algebraic notations denote in mathematical expressions.

3. The authors have decided to insert a token amount of their own wit and private jokes, whether it's the occasional reference to their own personal experiences in a humorous manner, or a wry quip about a certain topic. I personally find this extremely useful for holding my attention. It makes this textbook seem less like a textbook; in other words, it's much less dry than it could otherwise be. I even think that most of the jokes that the authors make seem quite sincere and genuine, and therefore actually funny, unlike some of the poor attempts I've seen in many others.

4. The examples utilized for explanations are relatively clear and almost instantaneous to absorb, especially when it involves a picture or graphical representation. The one complaint I have about this is that figures are often not on the same page as the text that is describing it. Editing could probably have fixed most occurrences of this situation, but in reality this does not do anything to lessen or tarnish the learning experience. So it's an extremely minor complaint, and has no bearing on the quality of the book.

If it isn't clear by now, this textbook is simply amazing. It's made the learning process much more pleasureable than I imagine it could have been. Currently I am also studying "Introduction to Automata Theory, Languages and Computation" and in comparison, that textbook falls under my last category of "inscrutable". I find myself wanting to tear my hair out and give up on the subject simply because the reading is utterly boring, and the explanations cryptic at best.

I never took a course in AI, but I've been reading and rereading this book, with pleasure, since the mid-nineties. This book is deep (as well as broad), tells a coherent story, and is very well-written and amusing. It is much more than a textbook or an encyclopedia; it's two of the smartest people around sharing years of study and reflection on some of the hardest and most interesting questions around.

It is not something to grok in a semester or two, and it should not be your only information source on any of the topics included. But if you are interested in AI or any related field, you ought to have it.

It is a physically unwieldy book. The next edition ought to be in several volumes, in soft covers, and perhaps printed on bible paper, so that I might read it comfortably in bed.

I'm currently teaching AI. Since it's the standard textbook for AI courses, I decided to use Russel&Norvig's book, and I am really disappointed.

The book is too superficial, trying to cover too much, and their notation and explanations are not always clear. For example, try to understand the Viterbi algorithm for HMMs. It's perfectly clear if you read an introductory article, but this book gives a very confusing idea of how it works. In several other parts of the book the same thing happens.
More often than not I have given other texts to my students.

I do not think using "one big book" is the right approach for teaching AI, because "AI" is too large. If you are teaching undergrad students in a "BS in AI" then you should use specific and in-depth books for each course: knowledge representation, vision, uncertainty, etc.
But if you are (as I am) teaching a short AI course in a Computer Science context, then I think you should probably pick very few subjects and treat them *in depth* -- otherwise your students will have no benefit in taking your course (whatever you tell them in that short time, they could learn by other means).

I enjoyed this book as a student taking an AI class. However, it was too heavy to carry it to the class. I did like book website and Google code page.

On the negative part I'd say the layout of the examples/pseudo code was ...rather inconvenient. LISP style made it a little bit awkward for a person who never saw LISP before. Some examples about evil king and his brother, and such were a little bit off... I'd rather get some real life examples. Problems at the end of chapters did not encourage going and doing it on your own.

I am not sure I'd be able to use this book as a self-study guide, but in the class it did make sense.