Rating: 
Summary: The most comprehensive book on AI
Review: Artificial Intelligence: A modern approach is definitely the most comprehensive book on AI I have come across. The latest edition covers everything from KR & Machine Learning to Robotics and Statistical learning, and has new chapters on Constraint Satisfaction Problems and Planning.
Artificial Intelligence has diverse branches and it's hard to see the correlations between them. This book manages to take a very innovative "agent" approach and tries to show some parallels between very disparate methods.
In my opinion, each branch of AI has made great progress by itself but more work needs to be done in trying to combine the different approaches together and create more comprehensive systems. The book does a very good job by making all these different approaches accessible in one volume.
This book also covers each topic in depth as well. Interested readers can always look at the exhaustive list of references for further reading. I have seen a variety of people use this book: from professors who have been in the fields for many years, to my friends in humanities who are just curious to know what AI really is. I highly recommend this book to anyone interested in AI.
Rating: 
Summary: A good introduction to a cutting-edge field
Review: Here is a fine primer for one of the most promising subdivisions of computer science. In it you will find all the conceptual foundations for the field, including most of what has been attained to date. This is a great book for learning the theory of AI, but if you actually want to program an artificial intelligence, it might actually discourage you. There is no actual code in this textbook, and for a very good reason. This is that, other than for simple games, high level code for AI programs gets HUGE. This is definitely NOT something you want to start out with if you aren't familiar with the fundamentals of computer science. If you don't have the ability to interpret pseudocode, you might not learn a whole lot. The material is very interesting, in my opinion, but not very practical. The authors describe all sorts of AI guidelines and components but don't really tell you how to actually DO any of it. It's probably just as well, as programming a good AI is extremely difficult (trust me on this one, I tried it). However, if you want to get into the field, this is as good a place as any to start. It's definitely going to be a hot area of computer science in the next few years, and this text does a good job of conveying the core concepts.
Rating:
Summary: A comprehensive and extensive book but ...
Review: i got this book from my local bookstore. This book covers most topics in AI. It is more comprehensive than most AI book i have read. However i dislike the writing style employed in this book. The author needs to refine his writing style and review the contents to include more interesting examples and some humor. It is not wise to have long paragraphs in thick books. The author should also include pratical examples of AI applications and some AI codes instead of general theories. Still a great book !
Rating:
Summary: Still the best learning algorithm for learning AI
Review: The first edition of this book was exceptional, and this one respects its fine quality, and in some parts exceeds it greatly. The field of artificial intelligence has advanced considerably since the first edition, and many of these very exciting developments are reflected in the book. Anyone, regardless of their level of background or expertise in artificial intelligence will benefit greatly from its perusal. Some of the better parts in the book:
1. The Website that is linked to the book, containing source code in LISP, PYTHON, and JAVA for the algorithms in the book. 2. The opening discussion on the history of artificial intelligence. The authors emphasize that the enhanced use of the scientific method is responsible for the rapid advances in AI in the last decade. 3. The historical summaries at the end of each chapter, which are fascinating reading by themselves and discuss ancillary developments not included in the main text.
4. The use of the "pointer hand" to emphasize important concepts. This should be helpful in the use of the book in a classroom setting. 5. The chapter on probabilistic language processing. The authors discuss an interesting example dealing with segmentation, namely that of finding the word boundaries in a sample text with no spaces. The Viterbi algorithm is used to do the word segmentation. The discussion on information retrieval in this chapter is also very interesting, and very important since the rise of the Internet and the consequent need for efficient search engines. 6. The discussion on the future developments in AI, given in the last chapter of the book. The authors discuss briefly a few of the more recent research topics, such as hierarchical reinforcment learning, anytime algorithms, and decision-theoretic metareasoning. Although short, the chapter motivates further reading on these topics, and references are given.
7. The discussion on "satisficing-making" decisions and its use in reducing the complexity of rational decisions. Although short, the discussion is helpful for those readers (like myself) who are not familiar with the concept of "satisficing". 8. The discussion of genetic algorithms, the authors pointing out their use widespread use in optimization problems, but observing, correctly, that more research needs to be done on genetic algorithms in order to determine when their use is optimal. The authors also discuss briefly the connection of quadratic dynamical systems with the performance of genetic algorithms. They also mention and interesting attempt by the researchers in genetic algorithms to justify population-based search in terms of Bayesian learning. References are given for both of these developments. 9. The discussion on constraint satisfaction problems is especially well-written, and this is good considering their enormous importance in enterprise and industrial applications in the last decade. Constraint logic programming is also discussed briefly.
10. The discussion on planning and acting in the real world is fascinating, especially the role of unexpected events or serendipity, which all successful planning must take cognizance of. 11. Applications of Bayesian networks have skyrocketed in recent years, and this justifies the authors thorough presentation of probabilistic reasoning and statistical learning in the book. Some of the disappointments in the book:
1. The discussion on support vector machines is too short, given the importance of this new learning paradigm. Support vector machines can be pretty deep from a mathematical standpoint so this might be the reason the authors chose not to give the details.
2. For those interested in automatic theorem proving, the discussion on this topic might be too short, considering what has been accomplished since the first edition, especially in the proof of the Ramsey conjecture.
3. Only a brief overview of inductive logic programming is given. Through the use of the language Progol, inductive logic programming has made some headway recently, especially in the field of bioinformatics.
4. No discussion at all of abductive reasoning, which has become very important in applications recently, such as event correlation in telecommunication networks. 5. The chapter on "Philosophical Foundations" should have been omitted entirely, given the pragmatic but still rigorous approach the authors take in the book. The title assumes that the field of artificial intelligence is in need of some sort of philosophical underpinning or justification, which it does not. Further, the attempted refutation of philosophical arguments against AI is a misappropriation of time. Instead, efforts should be concentrated on building better thinking machines and developing more sophisticated algorithms in AI. The presence of thinking machines actually working in the field performing useful tasks will serve as a concrete counterexample against any "impossibility proofs" of the philosophers. In the last paragraph of the book, the authors ask the reader to consider whether AI will succeed in its goals. I disagree with them somewhat when they say that AI has not yet had a major impact. It has. The problem is that many researchers are too modest to acknowledge their achievements, and many times are too easily convinced that what they have done does not in any way approach what could be called intelligent. As the authors remark, much work remains to be done. But much work has been done. One can say with confidence the future of AI will be very exciting and full of surprises, and witnessing this future will be a deep privelege.
Rating: 
Summary: Encyclopedic
Review: While R&N's coverage of topics in Artificial Intelligence is no doubt encyclopedic, several problems exist with the book: 1) The textbook is awfully traditional and only mentions in passing newer trends in AI. For example, case-based reasoning (or the "Yale view of AI") is mentioned, but not covered. Because AI is a new and rapidly changing field, and because AI paradigms are usually based on a small set of ontological assumptions, I believe it would not be too difficult for students to understand new paradigms. Obviously this should be a high pedagogical priority. 2) The textbook is rather condescending, with the authors strongly imposing their viewpoints. In other words, the authors are a little too dogmatic and that is reflected in the text. For example, they sometimes go about ranking paradigms. 3) The textbook is sometimes rather ambiguous when explicating certain paradigms, and the end-of-chapter problems are very, very ambiguous. One of the justifications for unclear questions is to get people thinking, but when the theoretical explications are already ambiguous it defeats the whole purpose. 4) The philosophical sections in R&N are rather naive and superficial. In spite of its obvious shortcomings, R&N has been tremendously useful to me, and I recommend it as a reference. The good news, I've heard, is that a new edition of R&N is coming out next year where these problems are eliminated.
Rating: 
Summary: Survey type of book, shallow but good for reference
Review: In ONE world: 'self-filler' This book is not really an introduction to Computational Intelligence, for an introductory type of book read David E. Goldberg's Genetic Algorithms Book, it is exceptional in terms of readability, concepts presented and depths it gradually delves into. That is the father of all genetic algorithm/EC/AI books, in my humble opinion. I know most of the stuff in Engelbrecht's book now, not because I've read it from his book, but because I've learnt it from other sources, do yourself a favor, read more descriptive aind insightful material about AI and CI. the chapters on NN and SOM, GA, EC are very shallow, he just summarizes ideas you can get from reading free sources like, AI webpages, presents a bunch of formulas, and to understand what they mean, you have to refer to the glossary and appendices. Furthermore he is inconsistent in his symbols, the terms represented by his symbols change through-out the book, sometimes even in consecutive chapters. Stuff he never addresses: Taboo Search, Simulated Annealing aren't even mentioned in the book. Travelling salesman problems, snake in the box, hybrid systems, neuro fuzzy system, adaptive genetic fuzzy systems are all never mentioned. There are no examples of the uses of the material he covers, kind of takes the flavor away from what you're reading. It is bland, fonts are awful, and pictures are drawn with Microcrap's paintbrush. This book will never give you an insight into CI paradigms, if you already know that stuff and want a quick revision, or want a reference for the formulas, get this book, or else it's just a shelf-filler. If you want to learn about AI/CI ideas go to www.mathworld.com (it's matlab's webpage), you'll learn a lot more in an easier way.
Also search the web, it contains almost all the information you need about latest CI research, go to www.citeseer.com and read research papers.
Rating:
Summary: The most comprehensive book on AI
Review: Artificial Intelligence: A modern approach is definitely the most comprehensive book on AI I have come across. The latest edition covers everything from KR & Machine Learning to Robotics and Statistical learning, and has new chapters on Constraint Satisfaction Problems and Planning.
Artificial Intelligence has diverse branches and it's hard to see the correlations between them. This book manages to take a very innovative "agent" approach and tries to show some parallels between very disparate methods.
In my opinion, each branch of AI has made great progress by itself but more work needs to be done in trying to combine the different approaches together and create more comprehensive systems. The book does a very good job by making all these different approaches accessible in one volume.
This book also covers each topic in depth as well. Interested readers can always look at the exhaustive list of references for further reading. I have seen a variety of people use this book: from professors who have been in the fields for many years, to my friends in humanities who are just curious to know what AI really is. I highly recommend this book to anyone interested in AI.
Rating:
Summary: good book
Review: in hindsight this was a good book...i used it a lot because i couldn't understand my prof very well...i got an A
Rating:
Summary: A Pleasant four-week walk through the field
Review: This is my first book in the field of AI and I really enjoyed reading it in a three-week vacation (four weeks would have been a little more relaxed and appropriate). I am not a computer scientist but could follow most of the book easily (Well I do have a strong mathematical background.). The book is not very formal, but still based on sound arguments. It has a tremendously wide range of subjects incorporated: both within AI and between disciplines as differently as Philosophy and Operations Research. Nearly every one of them is dealt with at an excellent level. Only the physics parts in the perception and robot chapters are a little mediocre in presentation quality. Anyhow they are pretty much at the end of the book. Also I liked very much the extensive historical overviews. The book contains lots of reading recommendations to explore further fields. I would have liked solutions to selected problems. The books print is laid out fine and with a lot of care. A two-column layout might be for the width of the book more appropriate. I read the international edition (2nd), which is paperback. This book is very heavy and it took quite a bit of ability to hold it reasonably comfortly over the many reading hours required.
Rating:
Summary: Still the best modern AI book available.
Review: I had finished reading this book 3 months ago. My comments are :-
- It covers most of modern AI topics.
- It is quite easy to understand in some topics. Also quite hard in some topics.
- It is well-explained, but will be great if they used a more understandable way. This book is suitable for a CS-student, or anyone who interesting in AI (But require some CS background).
| 
