- Hardcover: 1152 pages
- Publisher: Pearson; 3 edition (December 11, 2009)
- Language: English
- ISBN-10: 0136042597
- ISBN-13: 978-0136042594
- Product Dimensions: 8.1 x 1.7 x 10.1 inches
- Shipping Weight: 4.8 pounds (View shipping rates and policies)
- Average Customer Review: 189 customer reviews
- Amazon Best Sellers Rank: #38,334 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Artificial Intelligence: A Modern Approach (3rd Edition) 3rd Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
From the Back Cover
The long-anticipated revision of this #1 selling book offers the most comprehensive, state of the art introduction to the theory and practice of artificial intelligence for modern applications.Intelligent Agents. Solving Problems by Searching. Informed Search Methods. Game Playing. Agents that Reason Logically. First-order Logic. Building a Knowledge Base. Inference in First-Order Logic. Logical Reasoning Systems. Practical Planning. Planning and Acting. Uncertainty. Probabilistic Reasoning Systems. Making Simple Decisions. Making Complex Decisions. Learning from Observations. Learning with Neural Networks. Reinforcement Learning. Knowledge in Learning. Agents that Communicate. Practical Communication in English. Perception. Robotics.For computer professionals, linguists, and cognitive scientists interested in artificial intelligence.
About the Author
Stuart Russell was born in 1962 in Portsmouth, England. He received his B.A. with first-class honours in physics from Oxford University in 1982, and his Ph.D. in computer science from Stanford in 1986. He then joined the faculty of the University of California at Berkeley, where he is a professor of computer science, director of the Center for Intelligent Systems, and holder of the Smith–Zadeh Chair in Engineering. In 1990, he received the Presidential Young Investigator Award of the National Science Foundation, and in 1995 he was cowinner of the Computers and Thought Award. He was a 1996 Miller Professor of the University of California and was appointed to a Chancellor’s Professorship in 2000. In 1998, he gave the Forsythe Memorial Lectures at Stanford University. He is a Fellow and former Executive Council member of the American Association for Artificial Intelligence. He has published over 100 papers on a wide range of topics in artificial intelligence. His other books include The Use of Knowledge in Analogy and Induction and (with Eric Wefald) Do the Right Thing: Studies in Limited Rationality.
Peter Norvig is currently Director of Research at Google, Inc., and was the director responsible for the core Web search algorithms from 2002 to 2005. He is a Fellow of the American Association for Artificial Intelligence and the Association for Computing Machinery. Previously, he was head of the Computational Sciences Division at NASA Ames Research Center, where he oversaw NASA’s research and development in artificial intelligence and robotics, and chief scientist at Junglee, where he helped develop one of the first Internet information extraction services. He received a B.S. in applied mathematics from Brown University and a Ph.D. in computer science from the University of California at Berkeley. He received the Distinguished Alumni and Engineering Innovation awards from Berkeley and the Exceptional Achievement Medal from NASA. He has been a professor at the University of Southern California and a research faculty member at Berkeley. His other books are Paradigms of AI Programming: Case Studies in Common Lisp and Verbmobil: A Translation System for Faceto-Face Dialog and Intelligent Help Systems for UNIX.
Browse award-winning titles. See more
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
The biggest difference is the absence of the last two chapters. The U.S. edition includes: Chapter 26, "Philosophical Foundations", which covers arguments over consciousness in machines and the possibility of robot uprisings; and Chapter 27, "AI: The Present and Future", which *briefly* describes some things AI researchers need to work on before we can build a "general-purpose intelligent agent" (a.k.a. one single AI that will be good enough at a lot of different tasks). These two chapters are interesting, but I wouldn't call them core material, so I'm not surprised they got left out.
Other than that, the differences are astonishingly minor. The chapters are unnumbered, and some of them swapped places for no reason, but all the content from chapters 1 through 25 is here, plus the two appendixes. The ONLY edits to the text are removals of cross-chapter references. The U.S. version will say something like, "When we discussed whatzits in Chapter 4, we mentioned that they come in two flavors, X and Y", while the same line in this book will say, "Whatzits come in two flavors, X and Y". Again, those are the ONLY edits. All the other sentences are the same. The equations are the same. The diagrams are the same. The exercises at the end of each chapter are the same.
In short, if you can do without those last two chapters, buy this version and save your money.
This book was made by multiple authors. Fortunately, the book's definitions and summaries are generally coherent. It has a through coverage on the history of AI, the definitions (those that are controversial have been noted as such), and provides psuedocode of many algorithms. Similar to other textbooks on this topic, it does not provide run-throughs of those algorithms.
The organizations of the book can be improved. I have some problems with the way they organized the material on the second part of the book (II: Problem Solving). Chapter 3 is named "Solving Problems by Searching", but I didn't realize all they did was on classical searches in Chapter 3 until I read Chapter 4. They could have explained why uniform-cost search is uninformed search even though it has a cost function better than they did in the textbook. A better naming scheme for those chapters would be "Ch3: Global Search ", "Ch4: Local Search/... (I would suggest breaking Chapter 4 and put it into different places.)".
I bought the Kindle version, and it had many formatting problems. Most of them are minor (such as missing a "space" between two words, images appearing in different locations, image sizes too small, etc.) However, I had caught one specific error in the second part of the book (somewhere between chapter 3-5) where the fact is exactly the opposite than the one written (forgot to add the negation?) I should have marked and noted it so I can write down which error it was in the review but I was too lazy...
But it's a good purchase overall!
Ill update this again once the class is over and I'm farther in the book.
The reason why this book got 4 instead of 5 stars was for two reasons: (1) the statistical knowledge that one needed to know in order to understand a concept was not adequately covered in the book; and (2) it is pretty much impossible to skip around the book (you're forced to learn chapter by chapter, otherwise you'll get lost in the later ones, so in terms of learning methods, it's not really flexible).
If you want to learn about artificial neural networks and reinforcement learning, the Mitchell text is pretty decent as well. Wikipedia also helps.