e99 Online Shopping Mall

Geometry.Net - the online learning center Help  
Home  - Computer - Artificial Intelligence (Books)

  1-20 of 100 | Next 20

click price to see details     click image to enlarge     click link to go to the store

$87.49
1. Artificial Intelligence: A Modern
$54.10
2. Artificial Intelligence: A Modern
$10.13
3. Understanding Artificial Intelligence
$73.84
4. Paradigms of Artificial Intelligence
$58.41
5. Artificial Intelligence for Games,
$10.00
6. The Essence of Artificial Intelligence
$23.94
7. Artificial Intelligence (3rd Edition)
 
$69.61
8. PROLOG Programming for Artificial
$5.62
9. Introducing Artificial Intelligence
 
$6.25
10. Introduction to Artificial Intelligence:
$21.17
11. Artificial Intelligence Illuminated
 
12. An Artificial Intelligence Approach
$41.55
13. Artificial Intelligence: A Systems
$34.98
14. A.I. Artificial Intelligence:
$39.72
15. Bio-Inspired Artificial Intelligence:
$17.00
16. Affect and Artificial Intelligence
$55.99
17. Artificial Intelligence: Foundations
$18.85
18. Artificial Intelligence for Games
19. The Connection Machine (Artificial
$38.00
20. Artificial Intelligence: A Guide

1. Artificial Intelligence: A Modern Approach (3rd Edition)
by Stuart Russell, Peter Norvig
Hardcover: 1152 Pages (2009-12-11)
list price: US$132.00 -- used & new: US$87.49
(price subject to change: see help)
Asin: 0136042597
Average Customer Review: 4.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description

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.

... Read more

Customer Reviews (17)

4-0 out of 5 stars Apparently, it's *the* AI book.
As textbooks go, this one is well-organized and illustrated, and in addition to educating you with regards to artificial intelligence, provides a decent background in introductory algorithms and probability.

What?What's that?

He's on his way to city hall?

He's hacked all the security cameras?Who gave him the capabilities to interface with such systems?!

...I'm terribly sorry.I must attend to one of my more unruly projects.Good day.

4-0 out of 5 stars Good Book
I am currently using this book for an Artificial Intelligence (AI) course at Duke University. I purchased the book because it was required for the course, and have been pleased with it thus far.

The book is well written and very comprehensive. It does not go into great detail with the various topics in AI, but it does give a very thorough overview of methods being used. It appears to be very up-to-date with the subject matter. Also, it is not programming language specific, which was great for me because my java and C are a bit rusty.

It is a bit pricey, but no more than other well written text books. I would recommend this book to anyone looking to get into or to teach a course in AI.

5-0 out of 5 stars Exactly as expected
I bought this book and very promptly received it as expected.I have no complaints and look forward to learning the material.

4-0 out of 5 stars Well written
I am about halfway through this book for a class on Artificial Intelligence. One thing that really sticks out about this book is the writing style. I have much respect for authors who use plain English and don't sandbag the reader with needlessly complex language. All of the concepts are quite technical (in my opinion) yet I have no problems understanding the concepts because of the writing style. There is a certain clarity to it.

As for the overall merit, I'll withhold judgement and complete the review after I'm finished with the book.

5-0 out of 5 stars Finally, a text book that you can read
Text books are usually cryptic and boring, but this one's actually quite fun to read. It's so easy and fun that I'm actually excited when the professor assigns a new reading. In fact, I liked it so much that I looked up the author to find more of his books, and guess what? The author works at Google. Someone in Google making a user-friendly textbook? I'm in! ... Read more


2. Artificial Intelligence: A Modern Approach (2nd Edition)
by Stuart Russell, Peter Norvig
Hardcover: 1132 Pages (2002-12-30)
list price: US$132.00 -- used & new: US$54.10
(price subject to change: see help)
Asin: 0137903952
Average Customer Review: 4.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
The long-anticipated revision of this best-selling book offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence. 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 those interested in artificial intelligence.Amazon.com Review
Artificial Intelligence: A Modern Approach introducesbasic ideas in artificial intelligence from the perspective ofbuilding intelligent agents, which the authors define as"anything that can be viewed as perceiving its environmentthrough sensors and acting upon the environment througheffectors." This textbook is up-to-date and is organized usingthe latest principles of good textbook design. It includes historicalnotes at the end of every chapter, exercises, margin notes, abibliography, and a competent index. Artificial Intelligence: AModern Approach covers a wide array of material, includingfirst-order logic, game playing, knowledge representation, planning,and reinforcement learning. ... Read more

Customer Reviews (87)

3-0 out of 5 stars All theory but lacks concrete examples
The book explains well the theory behind many AI techniques, but you only reaches the pseudocode, so people that are new to programming must resort to Google to get some better examples and some down-to-earth approaches if you want to implement your AI

3-0 out of 5 stars I Confess, I Wikipedia did a better job explaining some of the concepts...
This was a decent book, but really, I felt the authors took a simple principle and DRAGGED it through the mud until it was no longer simple. A quick search online often found something that was much more consumable and concise.

3-0 out of 5 stars Could have been great, but ...
As some reviewers have said, this is probably the most comprehensive AI textbook on the market. The "pros" of the book have been covered pretty well by other reviewers, so I'll limit my review to some of the things that bug me about the book.

1. No answer key for any problems. This feature has been standard in textbooks for decades as a way for students to self-check their understanding of the material.

2. Examples are scant and sometimes stop in the middle. For example, in Chapter 13, the example of applying Bayes' Rule gives one approach and indicates that it will discuss an alternative approach, but then the text just goes off on another path and never completes the example.

3. Inconsistent and (sometimes) convoluted pseudocode for the algorithms. Pseudocode should be a fairly-close-to-English approximation of the algorithm, but this book seems to mix RTL, English, and any other notation. Though the appendix includes an attempt at explaining their rationale behind their own brand of pseudocode, it's incomplete at best. Also, the function names don't follow any convention I've ever seen (I have 30+ years experience in software), and aren't even consistent within the book.

4. Condescending language. This should never occur in a textbook. In far too many places, the authors tell us that "the sharp-eyed reader will have noticed" or similar phrases, which basically implies, "if you didn't get our explanation and find the hidden subtext, you are not sharp-eyed". All such language should have been edited out.


The authors came so close to writing a classic, but sadly missed the mark. I think that any professors who claim that their students "universally love this book" are deluding themselves. Still, if your professor is good at explicating the material, it's worth going through it once, then switching to other materials, maybe primary source materials in the subfield(s) that grab your interest.

5-0 out of 5 stars Nice introductory text on AI
I used this book for a graduate course in Artificial Intelligence. We covered about half of the book in class. The book is very comprehensive and I found that parts of the book have heavy notations including calculus (and I needed to review some of those concepts in order to follow completely). Overall I liked the book very much and I highly recommend to those who are looking for an introductory and broad view of AI.

1-0 out of 5 stars cheating
This seller is cheating on the item he is selling. The book he sold to me is an international edition and does not have the same cover as list above. Do not buy things from the seller. ... Read more


3. Understanding Artificial Intelligence (Science Made Accessible)
by Scientific American
Paperback: 160 Pages (2002-03-01)
list price: US$15.99 -- used & new: US$10.13
(price subject to change: see help)
Asin: 0446678759
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
UNDERSTANDING ARTIFICIAL INTELLIGENCE is one of the first four titles that launch an exciting new Pocket Science series, from the editors of America's leading popular science magazine, Scientific American.

Comprised of critically acclaimed essays by the world's leading experts on each topic in the series, these collections will become definitive texts on crucial issues of our technological times. The authoritative and prestigious reputation of Scientific American puts these books at the top of any science fan's list.

Called AI by followers and practitioners, the field of Artificial Intelligence is dedicated to the proposition that human brains are nothing more than machines, albeit extremely complicated ones, whose abilities will someday be duplicated-and surpassed-by computers.

This collection of essays discusses the wide spectrum of knowledge compiled on the pursuit of this elusive goal. It includes a fascinating overview of the subject by Douglas B. Lenat, the president of Cycorp, Inc., and a forward-thinking essay on "The Rise of Robots" by Hans Marvec, the principal research scientists at the robotics Institute at Carnegie Mellon University, which conservatively estimates that by 2050, robot brains based on computers will start rivaling human intelligence.

Other articles include "Here's Looking at You," which profiles a robot who learns about itself and its environment through trial and error, as well as a profile on Marvin L. Minsky, the mastermind behind Artificial Intelligence. The book-like the entire series-is targeted to intelligent readers who want to expand their understanding of complex scientific subjects and contains essays from top scientists working in the field. Like the magazine, the book encompasses a spectrum of innovation through expert-authored articles that demonstrate the convergence of science, technology, and the world economy, challenging readers with fresh, new ideas and empowering them to make smart, strategic decisions. ... Read more

Customer Reviews (2)

5-0 out of 5 stars Required reading for 21st century humans!
"Will robots inherit the Earth? Yes, but they will be our children."--Marvin L. Minsky

"Understanding Artificial Intelligence" is a great little book (139 pages, paperback). It's one of the wonderful "science made accessible" series by Scientific America's editors.

The book is a compilation of excellent essays by key thinkers in the field. Don't be scared off if you don't have a degree in computer science. All entries are well written and not so heavy as to lose most readers.

This book is a short read but it will stay with you for a long time. If you plan on being alive to see the next few decades, you need to know something about artificial intelligence. This book is a great place to start your education.

The editors write:

"Will a future proclamation be necessary to free artificial intelligence [from human bondage]? Should we allow this to happen? Should we fear out electronic offspring? Will ambulatory AI machines proceed down the Terminator's path . . . or down the benign road become helpful human assistants? Will artificial humans inherit the planet, as some scientists are now inclined to say, or will the melding of biology and bionics simply necessitate a new definition of human? We may not have all the answers yet, but the questions will become more important as each new invention leads toward true artificial awareness."

I highly recommend this book. It educates, yes, but more important, it inspires a sense of wonder and excitement about what tomorrow may bring.


--Guy P. Harrison, author of Race and Reality: What Everyone Should Know About Our Biological Diversity" and "50 Reasons People Give for Believing in a God" (a skeptical analysis of common justifications for religious belief)



The following is a column about robots and AI, published in the Cayman Observer on Sunday in April 2010. If you find it interesting, then you will love "Understanding Artificial Intelligence."


Will robots and AI rule tomorrow?

I am never alone. I share my Grand Cayman home with three humans, two dogs, one cat, and two robots. A few times per week my mechanical friends sweep the floors throughout my house. They navigate around chairs, scurry under tables, and annoy the cat. The more advanced model knows when it's had enough and returns to its docking station to nestle in for a recharge.

This is all very important to me because it means I don't have to sweep. While the robots work, I am free to engage in activities far more appropriate for a member of the most intelligent species on Earth--like watching TV.

Robots have plans that extend far beyond mere housework, however. Soon they will be everywhere. But there is the slight possibility of a downside--extinction of the human species. Yes, intelligent machines in the not-so-distant future may become so smart that they could threaten our existence. My cute little floor sweepers may turn out to be the great-great grandparents of real-life "terminators" that will kill us all one day.

Just like any other normal Cayman family, my children and I often discuss the impending robot apocalypse. My son reassures me that robots won't have any need to fight us because we will eventually be machines just like them. We will become robots, he believes. Given recent advances in prosthetic limbs, ear implants, brain implants, and so on, he may be on to something. Maybe we will merge with our technology so intimately and thoroughly that there will be no "us" and "them" to define battle lines. My daughter is not worried either. She is convinced that someone will be smart enough to remember to simply program the robots to be nice. Ah, don't you just love youthful optimism?

Still, I wonder. With computers on course to become freakishly powerful in about three or four decades, and with robotics development in high gear, will we be able to hang on to civilization's top rung? It seems likely that a game-changing new "species" is on the horizon and approaching fast, one that will be difficult if not impossible for us to control. Thanks in large part to unprecedented military investment in robotics, we are now stepping into a very different world--for better or worse. "In the blink of an eye," writes Peter Singer in his book, "Wired for War", "things that were just fodder for science fiction are creeping, crawling, flying, swimming and shooting on today's battlefields. And these machines are just the first generation of these new technologies, some of which may already be antiquated as you read these lines."

Hugo de Garis, an artificial intelligence researcher as well as my pleasant Face Book friend, may be engineering our collective doom. He is the author of the nightmare-inducing book, "The Artilect War," in which he admits feeling conflicted about his work. He believes it is highly probable that super-intelligent machines will brush us aside one day. Despite those fears, however, his research is so fascinating that he can't stop himself.

Unprecedented transformations are occurring right now. For example, did you know that in 2009 the United States Air Force trained more ground-based "pilots" to fly robot planes than it did traditional pilots for conventional planes? This year, the Air Force is projected to acquire more new robot planes than new conventional aircraft. This represents a monumental shift in the human-robot equation, yet the public mostly doesn't know or doesn't care. The various military robots that we know of are controlled and monitored closely by humans today, but what about tomorrow? Robot autonomy on the battlefield will be here soon, if it isn't already.

The military, rather than my floor-sweeping needs, is driving much of the cutting edge research. So much so that when the final histories of the wars in Iraq and Afghanistan are written one day it is possible that surprisingly little attention will be given to Bush, Saddam, the Taliban, oil, and terrorism. The greatest impact of these wars may well turn out to be robots.

I attended an exhibition of advanced and near-future technology called "NextFest" a few years ago in Chicago. I spoke with a representative from the company that makes one of the drones used by the US Air Force. I met a solider who wore a sleek prototype suit that, when fully developed, would make him stronger and even tighten automatically like a tourniquet to slow blood loss if he was wounded in battle. A Japanese woman demonstrated how strong she was thanks to the robotic "exoskeleton" she wore. I saw ASIMO, the famous Japanese robot, do its usual slow shuffling walk. Interested but not overwhelmed, I felt like I was watching the Australopithecus of robot evolution. But, of course, the robot equivalents of Homo erectus and Neanderthal are already being designed or built somewhere right now. There will be no four-million-year-wait for them. Don't blink.

I am not suggesting that anyone should panic or lose sleep over a possible robot takeover in the future. At the very least, however, you should be aware of what they are up to. The robots are not coming; they are here already. The invasion has begun. I know because an indifferent little robot on a mission just rolled by in front of me right here in my living room. It cares nothing about me; it just wants to sweep. That's what it does; that's who it is. I admire its dedication and focus. But I wonder, will the day come when its descendants demand more?

5-0 out of 5 stars Mind-Children and Smart Refrigerators
Understanding Artificial Intelligence is a collection of articles about artificial intelligence that have appeared in Scientific American over the past decade. Together they show AI as a fascinating and integrated field, rather than just a series of isolated projects. The authors, without exception, are using the human mind as an inspiration for creating superior technology. They are impatient with the idea that they are trying in any way to create 'articial humans'.

All the authors are well-known AI experts who have put in their time at the lab bench - or computer keyboard - and are talking from hands-on experience. Every piece meets Scientific American's standard of good, clear English without `talking down' to readers. The enthusiasm and pragmatism of these scientists comes through clearly.

At around 150 pages, this e-book was easy to read in one sitting, a perfect length for a domestic flight. ... Read more


4. Paradigms of Artificial Intelligence Programming: Case Studies in Common Lisp
by Peter Norvig
Paperback: 946 Pages (1991-10-15)
list price: US$98.95 -- used & new: US$73.84
(price subject to change: see help)
Asin: 1558601910
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description

Paradigms of AI Programming is the first text to teach advanced Common Lisp techniques in the context of building major AI systems. By reconstructing authentic, complex AI programs using state-of-the-art Common Lisp, the book teaches students and professionals how to build and debug robust practical programs, while demonstrating superior programming style and important AI concepts. The author strongly emphasizes the practical performance issues involved in writing real working programs of significant size.Chapters on troubleshooting and efficiency are included, along with a discussion of the fundamentals of object-oriented programming and a description of the main CLOS functions. This volume is an excellent text for a course on AI programming, a useful supplement for general AI courses and an indispensable reference for the professional programmer.

Amazon.com Review
This is an overview of classical artificial intelligence (AI) programming via actual implementation of landmark systems (case studies). For the student interested in AI, Paradigms of Artificial Intelligence Programming is an invaluable history lesson. Even the programmer who is relatively uninterested in AI will find value in the book's basic introduction to Lisp and case studies written in Lisp. But perhaps the book's best feature is its information on efficiency considerations in Lisp. Paradigms of Artificial Intelligence Programming is worth purchasing for these discussions alone, which provide a wealth of useful guidelines for optimizing your code. ... Read more

Customer Reviews (8)

5-0 out of 5 stars Amazing book about designing programs
Don't let the title of the book fool you: Yes, it presents all its code in Common Lisp and yes, the domain it discusses mostly is Artificial Intelligence, but PAIP (as it's affectionately called by fans) is a book about the general process of designing programs and implementing them. It's just a by-product that along the way you will learn Common Lisp (which is a very interesting language) and will get familiar with some very interesting problems in the fields of AI, code optimization, search, compilation and OOP/

Peter Norvig is a masterful programmer and writer. His code is excellently thought-out and designed, and shines with originality and clarity at every snippet you read. Every chapter has interesting insights and great code in it. Reading through this book from cover to cover is a behemoth task, but even starting small is great. Norvig even includes several exercises *with solutions* for each chapter, which really helps understanding the material.

In short, PAIP is one of the best books about programming and computer science I have ever read. It is highly recommended.

5-0 out of 5 stars One of the Best
"Paradigms of Artificial Intelligence Programming" is one of the best books of computer science that I have ever read.I put it up there in the pantheon with "Structure and Interpretation of Computer Programs".I have found more useful and mind expanding material in these case studies than I have in many other books on computer science. I highly recommend this book to anyone, even if they have never used Lisp.

5-0 out of 5 stars Norvig's Corollary to Greenspun's Tenth Law of Programming
This book has been called "The best book on programming ever written".I'd have to agree--it is certainly the best that I've ever read.

William Zinsser said, "The essence of writing is rewriting" and the same can be said for writing computer programs.Norvig's book presents this process--how the limitations of a program are overcome by revision and rewriting.What sets Norvig apart as a writer is that, amazingly enough, he can write about debugging (the most dreaded part of computer programming) and make it a fascinating read!

Lisp has been getting a higher profile lately because of essayists like Paul Graham and Philip Greenspun; in particular,Greenspun's Tenth Rule of Programming which states: "Any sufficiently complicated C or Fortran program contains an ad hoc, informally-specified, bug-ridden, slow implementation of half of Common Lisp." So, should this book be read as an exhortation to return to Lisp as the preferred programming language?

Paradoxically, I think not.One third of the way through the book, Norvig shows us how to implement Prolog in Lisp.From then on out, most of the AI techniques he presents either directly use Prolog instead of Lisp (such as his excellent discussion of natural language processing using Prolog) or use Prolog as a base to build on (such as his discussions on knowledge representation).

From this we can abstract what I'd like to call Norvig's Corollary to Greenspun's Tenth Law of Programming: "Any sufficiently complicated LISP program is going to contain a slow implementation of half of Prolog".I'm leaving out the "ad hoc", "bug-ridden" part of Greenspuns's law, because Norvig's programs are neither.But it is quite remarkable the degree to which, once having absorbed Prolog, Norvig uses Prolog as the basis for further development, rather than Lisp.

Is this a book about Prolog then?Again, no.What is the take-away message?It is this: as our world becomes more and more complex, and as the problems which programmers are facing become more and more complex, we have to program at a higher and higher level.

Norvig does not stop at just embedding Prolog in Lisp.He also shows us how to embed scheme as well.Excellent discussion on the mysterious call/cc function and on continuations.

In a capsule review, it is impossible to really give an overview of a 1,000 page book like this one. But the scope and heft of the volume really needs to be commented on: the programs presented in this book are like basis vectors, the totality of which nearly span the space of programming itself. In no way should this be considered "just an AI book" or "justa LISP book".This book transcends language, time, and subject matter.It is a programmer's book for the ages.

5-0 out of 5 stars An Excellent Reference on WHY to write good Lisp
This book is equally excellent regardless of whether you wish to regard it as:

a) A historical study of Artificial Intelligence, with USABLE examples of code, or

b) A book presenting techniques for programming in Common Lisp.

As a reference about Common Lisp, it is certainly lacking, but this is no great problem when both the Common Lisp HyperSpec and Steele's book are readily available in electronic form.It provides something more important: SIGNIFICANT examples, and significant discussions on WHY you would use various Lisp idioms, and, fairly often, discussions on HOW pieces of Common Lisp are likely to be implemented.Its discussion of an implementation of the LOOP macro, for instance, provides a very different point of view than the "references" to LOOP.(Contrast too with Graham's books, which largely deprecate the use of LOOP.)

From an AI perspective, it is also very good, providing WORKING SAMPLES for a whole lot of the historically significant AI problems, including Search, PLANNER, symbolic computation, and the likes.

It would be interesting to see parallel works from the following sorts of perspectives:

- The same sorts of AI problems solved using functional languages (e.g. - ML, Haskell), to allow contrasting the use of those more modern languages.Being more "purely functional" has merits; such languages commonly lack macros, which is something of a disadvantage.

- The use of CL to grapple with some other sorts of applications, notably random access to data [e.g. - databases] and rendition of output in HTML/SGML/XML [e.g. - web server].

4-0 out of 5 stars Not advanced, but good and vast
The strength of this book is its combination of breadth and completeness: there is working code (well beyond the toy stage) of a large number of different AI systems that cover a large subset of what is commonly considered AI.

The programming itself is rather basic, and very straightforward.In many places an advanced programmer would have avoided a global variable, unified code through the use of higher-order functions, had functions communicate through a shared local environment, created a lazy list, you name it.

The author avoids most of these more advanced approaches in order to present the ideas behind the approaches without being sidetracked into programming technique issues, and that is the correct choice for this book.Even as it is, there is already the duplicity of teaching Common Lisp and teaching AI programming.

That being said, the code in general is not bad at all, even though I wouldn't want my students to learn CL programming from it.The author has simply bent down to the level of, a good C programmer, and worked from there.His main intention being to teach AI programming approaches, he has spent much less time to raise the programming level of his audience.

Knowing the author's level of Lisp programming, I can't wait to see a book by his hand on how to use abstraction as an organising principle in programming. ... Read more


5. Artificial Intelligence for Games, Second Edition
by Ian Millington, John Funge
Hardcover: 896 Pages (2009-08-20)
list price: US$74.95 -- used & new: US$58.41
(price subject to change: see help)
Asin: 0123747317
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Creating robust artificial intelligence is one of the greatest challenges for game developers, yet the commercial success of a game is often dependent upon the quality of the AI. In this book, Ian Millington brings extensive professional experience to the problem of improving the quality of AI in games. He describes numerous examples from real games and explores the underlying ideas through detailed case studies. He goes further to introduce many techniques little used by developers today. The book's associated web site contains a library of C++ source code and demonstration programs, and a complete commercial source code library of AI algorithms and techniques.

"Artificial Intelligence for Games - 2nd edition" will be highly useful to academics teaching courses on game AI, in that it includes exercises with each chapter. It will also include new and expanded coverage of the following: AI-oriented gameplay; Behavior driven AI; Casual games (puzzle games).

* The first comprehensive, professional tutorial and reference to implement true AI in games written by an engineer with extensive industry experience.
* Walks through the entire development process from beginning to end.
* Includes examples from over 100 real games, 10 in-depth case studies, and web site with sample code. ... Read more

Customer Reviews (2)

5-0 out of 5 stars Excellent and approachable
The vast majority of software development books, whether it be for line-of-business app dev or game development, seem to have little to no information that can be found via a casual internet search.

This book is one of the few exceptions.There is a refreshing breadth and depth of game AI knowledge in this book that has been of tremendous help.Unlike the common "Gems" series of books, this book contains enough information on nearly every topic for the reader to build a 'ground up' implementation of their own.

My only complaints are that the pseudocode seems to be overly simplified and not as easily converted to a concrete implementation as I'd like, and that even for a book on game-specific AI implementations, the authors seem to enjoy a bit more of an academic/idealized approach to the design.That might be less bothersome to a professional game developer, but I'm at the hobbyist/indie level, and sometimes need a quick-and-dirty implementation before I begin to really understand what's going on.

Having said that, I was able to use the book to learn about and implement goal-oriented action planning, fast and flexible A* path finding (with additional info on modified funnel algorithm online), and several other critical components.

I would absolutely recommend this book.

5-0 out of 5 stars Detailed explanations of AI algorithms, their purpose and usage
Artificial Intelligence for Games by Ian Millington and John Funge covers lots of topics but is mainly designed to help the reader to master one element of game development which is artificial intelligence (AI). The book covers a wide range of techniques for game AI including detailed explanations of AI algorithms, their purpose and usage.

As I have learnt from this book, artificial intelligence is about making computers able to perform some thinking tasks that human and animals are capable of. This includes superhuman abilities in solving many arithmetic, sorting, searching and decision making problems. This book shows how it can be achieved revealing a range of techniques to the reader.

The book is split into five parts: introduction for AI in games, the substance of the AI (movement, pathfinding, decision making, tactical and strategic reasoning, learning), technologies and ways of implementation that enable the AI to do its job and finally designing game AI.

I think this book could be aimed at a wide range of readers but is most suitable for those looking for solid understanding of game AI and comprehensive reference to techniques used in top studios. The book helps to gain a deep and thorough view on modeling complex emotional states, triggers, and behaviors. To get the most from the book, you have to manage some time to read it and to understand its contents. If you need a quick AI solutions repository you should probably find another book related to a particular technology or computer language.

The book is associated with a website that contains a library of C++ source code covering the techniques found in the book. Hopefully the C++ code used in samples is relatively easy to read and includes many comments. There are also demonstration programs compiled as EXE files.

Besides many technical solutions to AI related issues I have also learnt from this book a few high-level things. For instance I have learnt that creating good AI is all about matching the right behaviors to the right algorithms and that often, a very simple technique used well can have better results then implementing complex the AI in the game.

This book is an open minder or a view broadener on many aspects related to the AI in games. It can also serve as a great example of good analysis, desing and prototyping examples of more or less complex algorithms which are about to use in specific projects. This is a very valuable title for any computer science professional dealing with Artificial Intelligence (for games). ... Read more


6. The Essence of Artificial Intelligence
by Alison Cawsey
Paperback: 200 Pages (1997-11-20)
list price: US$19.95 -- used & new: US$10.00
(price subject to change: see help)
Asin: 0135717795
Average Customer Review: 4.5 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
This is a practical, highly-accessible introduction to the state-of-the-art in artificial intelligence.This book demystifies artificial intelligence, making it concrete and transparent. It covers knowledge representation, inference, expert systems, natural language processing, machine learning, neural networks, agents, robots, and more. The book includes extensive self-test questions, case studies, figures, worked examples, sample algorithms and a complete glossary.For anyone interested in artificial intelligence; no prior background is required. ... Read more

Customer Reviews (5)

5-0 out of 5 stars A good overview and introduction to the field of AI
This book a a great starting point for studying Artificial Intelligence.For those with a Computer Science background, the book is a quick read that will show how theories such as data structures and search algorithms apply to the different areas of AI.For those without a background in computers, the book will take longer to read and for deeper understanding of some subjects other texts may need to be consulted.However, it is still one of the easiest-to-understand books on AI as most are extemely lengthy and detailed beyond the scope of what most beginners are able to understand.
The book is well written and explains complicated topics in plain English.Figures are used effectively to explain certain concepts.An extremely helpful feature is that every chapter is summarized and further references on that topic are given with a short description of the strength and weaknesses of each reference.
I would definitely recommend this book to those who want to learn about AI.Its a great starting point that can lead you in the right direction if you want to study a particular topic in further detail.

5-0 out of 5 stars Wonderfully simple and sweet
This is a wonderfully compact introduction to the basic concepts of Artifical Intelligence. You probably aren't going to be able to go and write your own AI after reading this but at least you'll have enough background to read a more detailed text and some of the scientific literature out there. If you've picked up other AI books and felt lost then start here, you won't regret it.

5-0 out of 5 stars Very readable introductory text
This is a very readable introductory text.Its coverage of topics is surprisingly good for such a slender volume.I especially liked the chapter on searching--the examples are very clear.

4-0 out of 5 stars A neat and concise summary
This book is a fine introductory text on AI. It covers all major subjects in the field and it is very clear and elaborates on the problems in a very direct and simple manner.If you are looking for an introductory text,then you found it by now.

4-0 out of 5 stars A neat and concise summary
This book is a fine introductory text on AI. It covers all major subjects in the field and it is very clear and elaborates on the problems in a very direct and simple manner.A very fine book as an introductory text. ... Read more


7. Artificial Intelligence (3rd Edition)
by Winston
Paperback: 750 Pages (1992-05-10)
list price: US$105.20 -- used & new: US$23.94
(price subject to change: see help)
Asin: 0201533774
Average Customer Review: 3.5 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
This is an eagerly awaited revision of the single bestselling introduction to Artificial Intelligence ever published. It retains the best features of the earlier works including superior readability, currency, and excellence in the selection of the examples.Amazon.com Review
This book is one of the oldest and most popular introductionsto artificial intelligence.An accomplished artificial intelligence(AI) scientist, Winston heads MIT's Artificial IntelligenceLaboratory, and his hands-on AI research experience lends authority towhat he writes. Winston provides detailed pseudo-code for most of thealgorithms discussed, so you will be able to implement and test thealgorithms immediately. The book contains exercises to test yourknowledge of the subject and helpful introductions and summaries toguide you through the material. ... Read more

Customer Reviews (10)

4-0 out of 5 stars Rethinking Fraud Aalysis
My business used this book to help us rethink our analysis of credit and prepaid card fraud. While the material itself has been around for some time, it helped us develop new methods of detecting potential fraud.

1-0 out of 5 stars Nauseating
In a phrase: as nauseating as the "artwork" which besmirches its cover.This book is definitely not worth the price.Donate the money instead to your city's homeless instead!You will learn as much about AI by doing so and will actually contribute something to the world.Of course, the cover makes a great prank at cocktail parties.Place it under someone's drink and it will look like the beverage has been spilled.

Winston's book is not only disorganized, but pretentious.He writes about the mind as if he has the authority of a philosopher of mind, when, in fact, he's just a programmer.Winston and his books will go down in history with the works of others, such as Doug Lenat, who made their fame primarily by doing something very easy before anyone else got around to doing it.

Real AI is yet to come.

1-0 out of 5 stars Can't get worse
This book is bad (period). It is very incoherent and ill-organized. The examples are vague and serve anything but support the material. Very theoritical with hardly any real life applications. Lacking in modern AI topics/game design.

1-0 out of 5 stars Miserable AI book - avoid at all costs
Winston's book is really terrible.I mean truly repellently, malignantly bad."Can it really be as bad as all that?" you wonder.Yes!!It's that bad!!For starters, the book is poorly organized.Topics that logically belong together are often several chapters apart.There is no overall structure to the book.It seems like a collection of topics in AI that were hastily assembled without concern for thematic organization or flow.For example, the forward and backward chaining algorithms are presented in a chapter (Ch. 7) on rule-based systems, but are not even mentioned in the chapter (Ch. 13) on logic!Perceptron training is presented AFTER backpropagation!Contrast this with the much better book by Russell and Norvig, which uses the theme of intelligent agents as a continuing motivation throughout, and which groups related topics into logically arranged chapters.

The examples in Winston are atrocious.The main example in the backpropagation chapter is some kind of classification network with a bizarre topography.This example is so trivial and weird that it totally fails to illustrate the strengths of backpropagation.The explanations of generalization and overfitting in backprop training are awful.

The only chapter of this book that is not an unmitigated pedagogical disaster is the chapter on genetic algorithms, although better introductions exist (e.g. Melanie Mitchell).

A further annoyance is the placement of all the exercises at the end of the book instead of the end of the chapters to which they correspond.

Avoid this book.It is truly horrible, and vastly superior books on AI are readily available at comparable prices.

5-0 out of 5 stars Very useful and well written; an industry perspective:
Suppose you are, like me, a software engineer who never actually studied CS beyond junior level undergraduate 'data structures'... and now you have to work on something involving complicated pattern matching... this is howto do it: buy this book and Sipser's on the Theory of Computation.Afterdigesting them (which is easy if you're as good with logical mathematics asthe typical software engineer), you should be able to read currentliterature in either field, and will have a deep, fundamental understandingof how to best solve whatever problem you're working on.That's whatworked for me, anyway.An excellent book, as is Sipser's. ... Read more


8. PROLOG Programming for Artificial Intelligence (International Computer Science Series)
by Ivan Bratko
 Paperback: 736 Pages (2011-04-12)
list price: US$69.61 -- used & new: US$69.61
(price subject to change: see help)
Asin: 0321417461
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
The third edition of this guide to Prolog and Artificial Intelligence has been updated to include key developments in the field. Divided into two parts, the first part of the book introduces the programming language Prolog, while the second part teaches Artificial Intelligence using Prolog as a tool for the implementation of AI techniques. ... Read more

Customer Reviews (9)

5-0 out of 5 stars especially good for A.I.
A new edition will be out soon, in 2010.This is an excellent book on Prolog *and* on AI.

For example, chapter 19 is an introduction to inductive learning in first-order logic, an advanced topic rarely found in introductory books.The example program HYPER is a very powerful learner as compared to other "propositional" machine learning methods such as decision trees, neural networks, or support vector machines.I have ported HYPER to Lisp and am still exploring it.

Prolog is not a very popular language nowadays, but basic knowledge of it is still essential to learning logic-based AI.

5-0 out of 5 stars Why is this the the best textbook on prolog?
Although this text is always mentioned in the same breath as other introductory textbooks on prolog, I don't think I've ever seen it described as "the best."
The book which usually takes the palm in such comparisons is"Art of Prolog."While "Art of Prolog" is an outstanding book, I think that now, in 2006, it has been eclipsed by the 3rd edition Bratko's book.Why?

Simply this: Bratko's textbook is (as far as I'm aware) the _only_ textbook on prolog which treats the language as a living, developing language!Other textbooks are great for their time, but they are unfortunately stuck in their time.Its as if nothing has happend to the prolog language since February 16, 1987.But this isn't true at all!

The biggest case in point: constraint logic programming!Bratko's text is the only introductory prolog textbook to even acknowledge the existance of CLP.And Bratko gives very lucid descriptions of it, along with very helpful examples and challenging exercises.

Another case in point: inductive logic programming!An entire new branch of machine learning theory has risen, based on logic programming, and NONE of the other introductory prolog textbooks cover it?Come on guys!

I would love to see a 4th edition of this book, because since this one has been published, logic programming has moved even further ahead.Constraint handling rules (CHR), logical functional languages (like Curry), using prolog for the semantic web, etc etc etc.It might be the best kept secret in computer science, but logic programming is really still one of the most exciting areas of programming, and Bratko's book does the best job of staying abreast of, and conveying the excitment of, this living and dynamic field.

5-0 out of 5 stars Great book for learning AI with Prolog, but....
... a horrible Prolog tutorial.

This is not a good first book on Prolog. If you are new to Prolog and Logic Programming, you should read 'Art of Prolog' first.

Prolog is quite different from other languages, and you'll need some time to get it. This book doesn't give you that time: after briefly introducing the basic concepts, Bratko dives at breakneck speed into recursion and list processing.

Don't get me wrong, this is a magnificent book on how to do AI with Prolog, but it shouldn't be your first Prolog book. It's an excellent second book.

5-0 out of 5 stars An excellent introduction to Prolog and concepts in AI
Professor Bratko has done a tremendous job of putting all the fundamental concepts of Prolog and its applications in various areas of AI. Although this book is focused on Prolog, the concepts that he has discussed are so fundamental that they can be implemented in other languages like Java as well.

I recommend this book to everyone who wants to learn Prolog. I would also recommend the readers to use a Prolog system to work out the examples and exercises as s/he goes through every chapter. A DEC10 Prolog system (like SICStus Prolog) would probably be the best companion for this book.

4-0 out of 5 stars I thought the book could be better
I find the book does not adequetly explain the more complex code examples.First of all the code is not adequetly commented.Secondly, it does not explain the code well for programmers.First when introducing a program like in the expert systems shell chapter it should first define an interface for the program, and explain each goal listed.It should adequetly explain what each goal and clause should hope to achieve.Also, for the more complicated programs it should draw some type of diagram, maybe a flow chart or something that explains the concepts involved.It leaves too much figuring out and guessing for the reader.It is not very user-friendly!
On the positive side, it does an adequate job of explaining concepts when complex code is not involved.I found that I could follow along on even the more advanced chapters mostly everything at least until code was suddenly introduced.Then it became a guessing game as to what it was trying to do.
The author does not seem to realize that it is more difficult to try to understand somebody else's program than it is to write your own program from scratch.As a consequence the reader wastes a lot of time trying to guess what his program is doing.
Note: this review is of the 2nd edition and does not necessarily reflect the 3rd.But, then again, every other review on this page prior to mine is about the 2nd edition as well! ... Read more


9. Introducing Artificial Intelligence
by Henry Brighton
Paperback: 175 Pages (2003-07-14)
list price: US$12.95 -- used & new: US$5.62
(price subject to change: see help)
Asin: 1840468416
Average Customer Review: 4.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Can machines really think? Is the mind just a complicated computer program? "Introducing Artificial Intelligence" focuses on the major issues behind one of the hardest scientific problems ever undertaken. Artificial Intelligence is not just a fictional concept. Half a century of research into the construction of intelligent machinery has resulted in machines capable of beating the best human chess players and humanoid robots that can walk and interact with us. Despite early claims that intelligent machines were just around the corner, progress has been slow and difficult. Consciousness and environment are tow of the deeply complex problems are two deeply complex problems encountered. How exactly should we go about building an intelligent machine? Should it work like a mind? Should it work like a brain? Does it require a body? "Introducing Artificial Intelligence" clearly explains the advances made over the past half-century, from Alan Turing's influential groundwork to cutting edge robotics and the New Al. ... Read more

Customer Reviews (7)

5-0 out of 5 stars Amazing Book!
This was the first real book I read on the topic of Artificial Intelligence, and I must say...the best.This books topics are not outdated at all, it completely applys to current studies.This is an amazing book for a good introduction into the topic, and mainly covers the philosophical side of creating intelligent and conscious artificial beings; explaining all sides of the issue in a incredibly information pakced and detailed cartoon format.A very good book, after reading it twice I finally understood the underlying principles of AI.If your interested in Ai I'd also recommend the other Introducing book on Consciousness, which gives a detailed description into the materialist, dualist, and mysterian views on consciousness and the formation of a theory of conscioussness, whos philosopical ideas is realted to AI.

2-0 out of 5 stars Not a technical introduction...
This book is not a technical introduction to AI.The book is targeted at people with no technical or computing expertise, and does not have enough depth to be of value to anyone interested in AI from a technical angle.

That said, it would be great as an introduction to someone like my wife (a nurse).

I wish I had read the reviews on this book before purchasing it, but I did get to look at the cool drawings in this one!

1-0 out of 5 stars An introduction of an introduction
This book is intended for a young audience... Avoid buying it in case you take the subject seriously. On the other hand, if you just want to have an overall idea of what IA is, it's ok.

5-0 out of 5 stars Thought, Consciousness and Understanding (oh my!)
This is a very light weight read on the subject that discusses the history of the slow and not certain advancement of the concept of what Artificial Intelligence is or will be.

As a person that is new to the subject I enjoyed the format -- lots of illustrations.

I was amazed to learn how inter-disciplinary the topic is. The book draws from the perspectives of psychology, mathematics, computer science, biology, and philosophy.Before starting the book, I was personally hoping to get an introduction to computer science tools (neural networks, Bayesian network etc.) that make up modern AI.However, I believe I am better off for starting with a book that helped me better understand that there is more to AI than computer science.


4-0 out of 5 stars Yet another fascinating book in the "Introducing..." series
Coming from a Computer Science background, but only having been exposed to AI via science fiction, the most interesting thing I learned while reading Introducing Artificial Intelligence was the distinction between the two major schools of thought in AI research:"strong AI," or those who believe machines can be made to think like humans or better, and "weak AI," those who seek further knowledge about natural intelligence through the use of artificial simulations of intelligence, but don't seek to create sentient thought in machines.Based solely on the descriptions of artificial intelligence that I've encountered in popular culture, it's never explicitly stated but always tacitly assumed that with sufficiently advanced technology, machines can be made to think.As this book discusses, this is not a universally acknowledged truth, but rather there is much disagreement among AI scientists as to whether this feat is even possible.

Some interesting history of AI research is covered, including the idea of Turing machines, and the robot "Shakey" who could perform simple tasks in a simplified environment, but ultimately failed to adapt when his surroundings became unfamiliar.Toward the end of the book, more recent developments are touched on, such as robot designs based on insects and robots who can negotiate more complex "real world" environments.

Overall a quick and interesting read like I've found most of the "Introducing..." books to be. ... Read more


10. Introduction to Artificial Intelligence: Second, Enlarged Edition
by Philip C. Jackson Jr.
 Paperback: 512 Pages (1985-06-01)
list price: US$17.95 -- used & new: US$6.25
(price subject to change: see help)
Asin: 048624864X
Average Customer Review: 4.5 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
This comprehensive, easy-to-read survey of how machines (computers) can be made to act intelligently explores problem-solving methods, representation and models, game playing, automated understanding of natural languages, heuristic scene analysis, specific artificial intelligence accomplishments and other related topics. With 132 illustrations.
... Read more

Customer Reviews (6)

3-0 out of 5 stars Good, but somewhat outdated
This is an interesting introduction to artificial intelligence, but it is rather outdated.In addition, while it gives a general overview of the entire field (at least how the field stood during the writing of the book), it doesn't give as man concrete examples, or as many code examples, as an in-depth developer might want.I would recommend Russell & Norvig's Artificial Intelligence: A Modern Approach for the serious developer, and forego this guy.

4-0 out of 5 stars A good introduction book for grown-ups
I was thinking of purchasing an introductory book on AI for my 14 year old son since he was so interested in robots and automation. Apparently, this book is beyond him. I am not sure whether there is an AI book for children.

5-0 out of 5 stars A Little dated, but very good introduction
Having last been printed in the mid 80's some of the information is getting a little dated at this point, but for anyone new to the subject it is a very good read and an excellent introduction to the feild of AI.

5-0 out of 5 stars Great read, excellent price
I actually picked up this book at the discount bin at a local bookstore.I had always been interested in A.I research, and this deal was irresistable.However, I think this book is worth alot more, and provides more insight into the field than many of the current popular books on the subject.

This book basically goes into A.I research and leaves alot of the philosophical issues at a minimum.Basically you can look at this as a real text book about the subject of A.I.By my expirience, it isn't easy to find outside of the popular science market.

The topics that this book covers is extensive.The first few chapters go into subjects like Game Theory, and the problem-state models of A.I.He also gives a very extensive overview of the contruction of the human brain and its paralells to finite state machines.What I found particularly interesting was his coverage of many Turning Machines.Later, the author takes you into more rigorous examples dealing with problems of Theorem proving.And definitely one of the most interesting chapters was his coverage of natural languages.

I have owned this book for about 2 years, and although I do not read it faithfully everyday, I do find myself reading this book extensively for periods of 2-3 months.The material will demand a great deal of work on the behalf of the reader.As this book deals with many abstract concepts in mathematics that can be confusing to the untrained reader.Admitedly, i had to stop reading this book for a little while and take 4 months to get to a functional level of linear algebra, before I could fully comprehend the tranformation he showed chapter 6.

This is a must buy for anyone who wants to get their feet wet in the field of A.I.And with such a small price tag, you really cant lose.

5-0 out of 5 stars Great Introduction and not only that.
I was searching for a book that will introduce me to artificial intelligence concepts; and although this book seemed old (1985), I bought it because of it's low price. Then when I opened it for the first time Iwas amazed how great it is. It worths a whole lot more. I soon found outthat some concepts are for ever, and no matter how old they will be currentin the future. ... Read more


11. Artificial Intelligence Illuminated
by Ben Coppin
Paperback: 739 Pages (2004-04-05)
list price: US$129.95 -- used & new: US$21.17
(price subject to change: see help)
Asin: 0763732303
Average Customer Review: 3.5 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Artificial Intelligence Illuminated presents an overview of the background and history of artificial intelligence, emphasizing its importance in today’s society and potential for the future. The book covers a range of AI techniques, algorithms, and methodologies, including game playing, intelligent agents, machine learning, genetic algorithms, and Artificial Life. Material is presented in a lively and accessible manner and the author focuses on explaining how AI techniques relate to and are derived from natural systems, such as the human brain and evolution, and explaining how the artificial equivalents are used in the real world. Each chapter includes student exercises and review questions, and a detailed glossary at the end of the book defines important terms and concepts highlighted throughout the text. ... Read more

Customer Reviews (7)

4-0 out of 5 stars Great text on AI
My undergraduate AI class used this textbook. The writing was never dry and provided lots of information for someone new to the field of AI.

1-0 out of 5 stars Not Feeling Very Illuminated
This was the textbook for a college AI course I took. I wouldn't recommend this book for an introduction to AI. Most topic discussions were cursory and required additional online research. There were very few examples to illustrate the subject material. Those that were provided were very confusing. I actually learned more from the internet searches I ended up doing than from this textbook. I was looking forward to this class, but this textbook did nothing to make my learning experience any better.

5-0 out of 5 stars Excellent and outstanding service
Excellent and outstanding service.
Thank you for time and business.

V/R

INTULECT

3-0 out of 5 stars Disappointing
A big fan of the COMPUTER SCIENCE ILLUMINATED text, I had high hopes for this as a good text for my undergrad class on A.I..I was sorely disappointed; this text is far too shallow for even a middle-level undergrad course. It also contains several errors, although that may be expected of a first edition.

5-0 out of 5 stars Artificial Intelligence Illuminated
It's new one, which has a great quality. And very quick delivery. Perfect purchase to me. ... Read more


12. An Artificial Intelligence Approach to Legal Reasoning (Artificial Intelligence and Legal Reasoning)
by Anne von der Lieth Gardner
 Hardcover: 239 Pages (1987-05-27)
list price: US$29.95
Isbn: 0262071045
Average Customer Review: 4.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Law and legal reasoning are a natural target for artificial intelligence systems. Like medical diagnosis and other tasks for expert systems, legal analysis is a matter of interpreting data in terms of higher-level concepts. But in law the data are more like those for a system aimed at understanding natural language: they tell a story about human events that may lead to a lawsuit. Statements of the law, too, are written in natural language and legal arguments are often arguments about what that language means or ought to mean.This study is one of the few research efforts in this fertile area. It is unique in developing a computational model for analyzing legal problems in a way that brings these strands of AI research together and makes sense from a jurisprudential perspective as well.Gardner first analyzes several positions in Anglo-American jurisprudence and their relevance for work in artificial intelligence. She identifies aspects of legal reasoning that any truly expert system in law must make a place for and suggests a way of decomposing the process of legal analysis that takes these aspects into account. She compares the resulting framework with those used by other legal analysis programs. A solid exposition of current AI techniques follows in chapters covering the author's system (written in Maclisp) for offer and acceptance problems, taken from law examinations, involved in contract law.Anne von der Lieth Gardner has a law degree and a Ph.D. in computer science, both from Stanford University. An Artificial Intelligence Approach to Legal Reasoning inaugurates the series Artificial Intelligence and the Law: Processes and Models of Legal Reasoning, edited by L. Thorne McCarty and Edwina L. Rissland. A Bradford Book. ... Read more

Customer Reviews (1)

4-0 out of 5 stars Of historical importance
To design a machine that can engage in legal reasoning has been of great interest in the field of artificial intelligence and in some schools of jurisprudence. This goal has not been achieved to the satisfaction of all those involved in building legal reasoning machines, but some progress has been made. This book, which is widely cited by those working in legal artificial intelligence, was one of the few at the time of publication that gave a fresh approach to the problem.

When reading the book it is apparent that many questions must be answered before a successful legal machine can be constructed. These include: How does one apply a rule to the stated facts of a legal case? Is there a demarcation between the conclusions that can be reached using ordinary logical deduction and those arrived at by the discretion of the judge? Can a machine analyze full and encapsulate in its knowledge base the concepts of wisdom and justice? How does the language of rules connect with the language in which facts are stated? What kinds of predicates are to be used only in the antecedents of rules? If the descriptions and examples are only `usually fairly good,' when can a machine make the conclusion that these examples are good enough for a particular issue at hand? How does one determine that a legal predicate not defined further by rules is clearly satisfied by the facts of a case being analyzed? How are past cases to be represented? How is the legal machine to represent the reason(s) for a decision? Which facts are to be considered relevant in determining the satisfaction of which legal predicate?

The author addresses these questions in this book, and even a reader not interested in the applications of artificial intelligence will gain good insights into the processes of legal reasoning. Legal conclusions for example can be divided into two classes, those that are the result of deductive reasoning and those that require the judge to select the `just' conclusion. A `just' conclusion is therefore to be distinguished from those arrived at deductively. This observation, if valid, definitely has ramifications for the building of legal machines, since deductive reasoning patterns are fairly easy to implement in machines. But the concept of a `just' conclusion would be a challenge for a machine implementation.

As brought out in the book, any kind of reasoning pattern utilized by a machine must be subject to constraints, these constraints being unique to the domain in which the machine reasons. In legal reasoning, this constraint takes the form of `stare decisis', which means that the machine must be able to make analogies and be aware of cases in the past. In addition, legal reasoning is `rule-guided', rather than rule-governed, and legal rules are heuristic in nature, generally have exceptions, and sometimes may contradict one another. Besides these constraints, the terms in legal discourse are what the author calls `open-textured,' in that the meaning of terms and predicates are inherently indeterminable. Legal questions frequently invite more than one answer, and these answers can change over time. Hence legal reasoning patterns must be able to adapt to a dynamic knowledge base.

According to the author, the strategy for a successful legal reasoning machine would involve the ability to distinguish between `hard' versus `easy' questions. The hard questions in legal discourse arise because of the existence of competing rules, unresolved predicates, and competing cases. The machine must be able to detect `hard' cases, and it could do this by using a collection of heuristics. One of these heuristics involves the use of what the author calls `common sense knowledge' (CSK) rules, which are to be distinguished from general human commonsense knowledge. If an answer can be derived using CSK rules and if there does not exist any objection to using this answer, then question is assumed to be `easy.' The second heuristic entails that if no answer about the satisfaction of a legal predicate can be defined using CSK rules, then the machine will search for cases that illustrate that the facts of the case at hand are actually an example of a situation that the legal predicate has covered in the past. The third states that if a tentative answer is derived using non-legal knowledge, then the machine will search for cases that call for the opposite answer.

To test and benchmark her strategy, the author works in the field of `offer and acceptance' and `contract law', and deals specifically with the case `Adams vs Lindsell'. To construct the reasoning patterns, she brings in a highly interesting construction that she calls a `augmented transition network' (ATN). An ATN represents the standard states in a contract situation and the interpretations of events are represented as links between the states. The ATN that she constructs has twenty-three sates, twenty legal rules, and one hundred generalized `fact patterns.' The latter are associated with each legal predicate, and can be supported by several cases.

The author gives detailed analysis of her approach, and remarks that its use has not produced situations wherein a `tentative' truth value is defeated. Several test problems are analyzed at the end of the book, these dealing mostly with how the reasoning patterns analyze events, and one that deals, interestingly, with legal study aids. From her conclusions it is readily apparent that legal reasoning is very difficult to implement in artificial intelligence, for the primary reason that deduction does not by itself determine the outcome of a case. Another reason is the role of legal precedent, which can give a new interpretation to the language of old rules.

The author also makes commentary on the future of legal artificial intelligence. Considering the progress made in this field since this book was published, especially in the use of knowledge engineering in the practice of law, one can be confident that legal machines will make their presence known in the courts, in legal philosophy, and in constitutional interpretation in the years to come. ... Read more


13. Artificial Intelligence: A Systems Approach (Computer Science)
by M. Tim Jones
Hardcover: 500 Pages (2008-12-26)
list price: US$91.95 -- used & new: US$41.55
(price subject to change: see help)
Asin: 0763773379
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
This book offers students and AI programmers a new perspective on the study of artificial intelligence concepts. The essential topics and theory of AI are presented, but it also includes practical information on data input & reduction as well as data output (i.e., algorithm usage). Because traditional AI concepts such as pattern recognition, numerical optimization and data mining are now simply types of algorithms, a different approach is needed. This sensor / algorithm / effecter approach grounds the algorithms with an environment, helps students and AI practitioners to better understand them, and subsequently, how to apply them. The book has numerous up to date applications in game programming, intelligent agents, neural networks, artificial immune systems, and more. A CD-ROM with simulations, code, and figures accompanies the book. ... Read more

Customer Reviews (2)

5-0 out of 5 stars Plain simple English!
I think this book is great! It explains the fundamentals of AI in a way that is easy to read and understand! I recommend this book to AI newbies who don't want to spend hours figuring out technical language. It was really useful for me!

5-0 out of 5 stars Best AI book I've seen so far
I am just getting into AI and I've been looking for some good AI books. This is the first one I've found that covers a great selection of AI topics and talks about them in PLAIN ENGLISH instead of trying to baffle you with lots of academic gibberish! It's also liberally sprinkled with clear diagrams and programming code. So if you want a practical AI book you can actually use and understand, I think this is a good one. It's written by an AI professional who can actually WRITE and communicate clearly! What a surprise!

... Read more


14. A.I. Artificial Intelligence: From Stanley Kubrick to Steven Spielberg: The Vision Behind the Film
Hardcover: 160 Pages (2009-11-03)
list price: US$60.00 -- used & new: US$34.98
(price subject to change: see help)
Asin: 0500514895
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Reveals how the project originated and how it was brought to fruition through the efforts of two great movie directors.Film is the medium of the modern age, and in this spectacular, large-format publication, one of the pinnacles of contemporary moviemaking is celebrated. A.I. Artificial Intelligence (2001) was a collaboration between two cinematic giants: Stanley Kubrick and Steven Spielberg. Here, the directors’ combined visions and sensibilities are presented along with the work of their remarkably talented colleagues—above all, Chris Baker, the film’s conceptual artist.

At the heart of the book are Baker’s drawings, many never before seen. Commissioned by Kubrick and used in Spielberg’s eventual production designs, the drawings display Baker’s imagination and rare technical skill. Accompanying the drawings are extracts from Kubrick’s notebooks, stills from the finished film, and photographs of behind-the-scenes action, highlighting the use of pioneering special effects, animatronic work, and the “virtual studio.” 300 color, 100 b&w illustrations ... Read more

Customer Reviews (4)

4-0 out of 5 stars A.I. Artificial Intelligence: From Stanley Kubrick.
A.I. Artificial Intelligence: From Stanley Kubrick.
Wonderful colored pictures and great information on the feature film.
One draw back not enough behind the scenes on the miniatures from ILM.

Very nice book overall!

5-0 out of 5 stars Great and amzing book............but
Why not include the DVD of the movie or some special features as a Tie in to aid the cause

5-0 out of 5 stars Finally...
A great and beautifully produced book about an enigmatic and mysterious film. The large format reproductions of Chris Baker's artwork are gorgeous. Stanley Kubrick's notes, annotations from Brian Aldiss, Ian Watson and Spielberg are gold. The editorials by Jan Harlan and Jane Struthers are fascinating and insightful, and at times quite moving -- especially Mr. Harlan's comment in the introduction, remarking on Stanley Kubrick's philosophy of filmmaking: 'First love it, and then worry about how to do it.'

For full disclosure, "A.I." was somewhat of a personal obsession, which haunted me from first reports that began appearing in the early days of the Internet rumor mill. Around the time of the film's release, I had the privilege to interview many of the filmmakers for an article about the film for Cinefex magazine, which I'm honored to see included in the 'recommended reading' notes of this book. One thing that my article lacked was Stanley Kubrick's voice. This book gives you that, in the annotations accompanying Chris's artwork and the observations of his colleagues. Bravo to Chris and to Thames & Hudson for pulling this material together; and to Messrs. Harlan and Spielberg, thank you for allowing this book to happen. It's long overdue, and it is a treasure.

Highly recommended.

Joe Fordham
Cinefex, associate editor

5-0 out of 5 stars Very well researched and in depth
Watch Video Here: http://www.amazon.com/review/R3DZKVVD4Q7UAQ I was a bit surprised when I saw this book, published eight years after A.I. Artificial Intelligence was released. Time seems to stretch out with everything with this movie.

This book looks in depth at the production and also analyses the whole film thoroughly. If you don't already know, the film is inspired by a short story called "Super-Toys Last All Summer Long" written by Brian Aldiss in 1969. In 1976, Stanley Kubrick approached Brian Aldiss, and later with Steven Spielberg in 1984. With authorization from Kubrick before he passed away in 1999, Spielberg manages to finish the film in 2001. What happens during within all those time is all in the book. It's incredibly well researched and put together.

Besides production, there's also an extensive analysis of the film, act by act, with interviews from staff. It explores the philosophy, science and social-biology issues with robotics in the future. There's even an essay written by the director from the Personal Robots Group from MIT Media Lab.

This is one huge book measuring almost 20 inches diagonal, if go you by tv/monitor sizes. The pages are so big that the short story from Brian Aldiss are scanned and reproduced with handwritten notes.

Also included are storyboards and concept sketches from Chris Baker, as well as many photos from the set. It's interesting to see how the concept art evolved into actual sets and the discarded ideas. I didn't know that Rouge City, the one with lots of bright lights, is actually a miniature set. And Teddy, the bear, has more articulation joints than T-Rex from Jurassic Park. There are also extracts from Kubrick's notebooks but his handwriting is difficult to read.

This is a nice super-sized book looking at the art and making of the film. Recommended for fans of the movie.

(More pictures are available on my blog. Just visit my Amazon profile for the link.) ... Read more


15. Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies (Intelligent Robotics and Autonomous Agents)
by Dario Floreano, Claudio Mattiussi
Hardcover: 659 Pages (2008-09-30)
list price: US$53.00 -- used & new: US$39.72
(price subject to change: see help)
Asin: 0262062712
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
New approaches to artificial intelligence spring from the idea that intelligence emerges as much from cells, bodies, and societies as it does from evolution, development, and learning. Traditionally, artificial intelligence has been concerned with reproducing the abilities of human brains; newer approaches take inspiration from a wider range of biological structures that that are capable of autonomous self-organization. Examples of these new approaches include evolutionary computation and evolutionary electronics, artificial neural networks, immune systems, biorobotics, and swarm intelligence—to mention only a few. This book offers a comprehensive introduction to the emerging field of biologically inspired artificial intelligence that can be used as an upper-level text or as a reference for researchers.

Each chapter presents computational approaches inspired by a different biological system; each begins with background information about the biological system and then proceeds to develop computational models that make use of biological concepts. The chapters cover evolutionary computation and electronics; cellular systems; neural systems, including neuromorphic engineering; developmental systems; immune systems; behavioral systems—including several approaches to robotics, including behavior-based, bio-mimetic, epigenetic, and evolutionary robots; and collective systems, including swarm robotics as well as cooperative and competitive co-evolving systems. Chapters end with a concluding overview and suggested reading.

A teacher's kit with slides and exercises is available online at http://baibook.epfl.ch/ ... Read more

Customer Reviews (1)

5-0 out of 5 stars A very cohearent covering of a large territory understandable even to a layperson
www.gabrielfalco.com
Concepts detailed in this text have become pillars of my thinking. Every year I purchase several textbooks to educate myself on topics that interest me. Bio-Inspired Artificial Intelligence balances delivering conceptual detail with real world integrated examples to aid in deep and successful comprehension of the topics. The text answers questions, informs and prompts one ask broader questions. Incredibly, it is actually very enjoyable to read; I think this may have to do with the good writing.
... Read more


16. Affect and Artificial Intelligence (In Vivo)
by Elizabeth A. Wilson
Paperback: 200 Pages (2010-08-01)
list price: US$25.00 -- used & new: US$17.00
(price subject to change: see help)
Asin: 0295990473
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
In 1950, Alan Turing, the British mathematician, cryptographer, and computer pioneer, looked to the future: now that the conceptual and technical parameters for electronic brains had been established, what kind of intelligence could be built? Should machine intelligence mimic the abstract thinking of a chess player or should it be more like the developing mind of a child? Should an intelligent agent only think, or should it also learn, feel, and grow?

Affect and Artificial Intelligence is the first in-depth analysis of affect and intersubjectivity in the computational sciences. Elizabeth Wilson makes use of archival and unpublished material from the early years of AI (1945-70) until the present to show that early researchers were more engaged with questions of emotion than many commentators have assumed. She documents how affectivity was managed in the canonical works of Walter Pitts in the 1940s and Turing in the 1950s, in projects from the 1960s that injected artificial agents into psychotherapeutic encounters, in chess-playing machines from the 1940s to the present, and in the Kismet (sociable robotics) project at MIT in the 1990s.

Elizabeth A. Wilson is a professor in the Department of Women's Studies at Emory University. She is the author of Neural Geographies: Feminism and the Microstructure of Cognition and Psychosomatic: Feminism and the Neurological Body.

"Original and beautifully written." -Lucy Suchman, Lancaster University

"An elegantly written, thoroughly engaging, and absolutely compelling history of the role of emotions and affect in thought about, and design of, 'artificial intelligence.'" -Robert Mitchell, Duke University ... Read more


17. Artificial Intelligence: Foundations of Computational Agents
by Poole David L., Mackworth Alan K.
Hardcover: 688 Pages (2010-04-19)
list price: US$90.00 -- used & new: US$55.99
(price subject to change: see help)
Asin: 0521519004
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
Recent decades have witnessed the emergence of artificial intelligence as a serious science and engineering discipline. Artificial Intelligence: Foundations of Computational Agents is a textbook aimed at junior to senior undergraduate students and first-year graduate students. It presents artificial intelligence (AI) using a coherent framework to study the design of intelligent computational agents. By showing how basic approaches fit into a multidimensional design space, readers can learn the fundamentals without losing sight of the bigger picture. The book balances theory and experiment, showing how to link them intimately together, and develops the science of AI together with its engineering applications.Although structured as a textbook, the book's straightforward, self-contained style will also appeal to a wide audience of professionals, researchers, and independent learners. AI is a rapidly developing field: this book encapsulates the latest results without being exhaustive and encyclopedic. It teaches the main principles and tools that will allow readers to explore and learn on their own.The text is supported by an online learning environment, AIspace, http://aispace.org, so that students can experiment with the main AI algorithms plus problems, animations, lecture slides, and a knowledge representation system, AIlog, for experimentation and problem solving. ... Read more

Customer Reviews (1)

5-0 out of 5 stars A "neo-classical", logical approach to AI
This is really a "2nd edition" of their book by a different name and publisher:"Computational Intelligence - a logical approach" (1998, Oxford, minus one co-author), with some new material.

It's a very good introductory AI book, similar to AIMA, but with a focus on logic-based AI.I haven't read the new book in detail only because I use exactly the same approach in my AI R&D.

In particular, probabilistic reasoning in logic-based AI is explained here.

Logic-based AI fell out of favor in the 90s, being eclipsed by connectionism and statistical learning.But I think it can have a revival, partly thanks to the new popularity of Bayesian networks.The Semantic Web is also logic-based. ... Read more


18. Artificial Intelligence for Games (The Morgan Kaufmann Series in Interactive 3D Technology)
by Ian Millington
Hardcover: 896 Pages (2006-06-21)
list price: US$79.95 -- used & new: US$18.85
(price subject to change: see help)
Asin: 0124977820
Average Customer Review: 4.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description

Creating robust artificial intelligence is one of the greatest challenges for game developers. The commercial success of a game is often dependent upon the quality of the AI, yet the engineering of AI is often begun late in the development process and is frequently misunderstood.


In this book, Ian Millington brings extensive professional experience to the problem of improving the quality of AI in games. A game developer since 1987, he was founder of Mindlathe Ltd., at the time the largest specialist AI company in gaming. Ian shows how to think about AI as an integral part of game play.


He describes numerous examples from real games and explores the underlying ideas through detailed case studies. He goes further to introduce many techniques little used by developers today. The book's CD-ROM contains a library of C++ source code and demonstration programs, and provides access to a website with a complete commercial source code library of AI algorithms and techniques.



* A comprehensive, professional tutorial and reference to implement true AI in games.
* Walks through the entire development process from beginning to end.
* Includes over 100 pseudo code examples of techniques used in commercial games, case studies for all major genres, a CD-ROM and companion website with extensive C++ source code implementations for Windows, and source code libraries for Linux and OS X available through the website. ... Read more

Customer Reviews (6)

3-0 out of 5 stars Dissapointing
I bought this book for an Artificial Intelligence for Games class at my University.I haven't read through all of the book, but I can already tell you that the pseudo-code in this book is very poor.It's obvious that the author didn't actually go through and run the code to make sure it worked.In the movement algorithms, the code would sometimes alter rotation (speed of orientation) when it should be altering the orientation itself.In the dynamic kinematics class, the code multiplies the velocity by the acceleration instead of just simply adding the acceleration to the velocity.

Even when you get the provided movement algorithms to work the way the author probably intended, there are still issues that aren't considered.I won't get into too much detail but an example is the "Arrive" behavior.It doesn't work properly because the bot never arrives at it's target.There is nothing in the algorithm that actually decelerates the bot or nullifies the velocity.So you basically get a bot that wiggles back and forth on stationary targets.

The explanations are pretty straight foward, and I admit I haven't read the full book yet.I just think it's pretty unacceptable to publish something with so many errors in the pseudo-code.

5-0 out of 5 stars Great academic approach of AI
This book is really good and is different from other ones in the field of Artificial Intelligence. Millington explains difficult stuff in an easy and readable way. I like the academic approach of the book, I used it during my last year in college and it turned out really useful. If you want implementation details you have the source code in c++. The use of pseudocode is the best idea when writing these sort of books.

5-0 out of 5 stars Excellent C++ Source for AI
This is a very solid book on AI for games.

The C++ source code provided with the book is excellent.While the examples are visually unexciting, they demonstrate the power of the book's principles without the clutter that a complete graphics game would require.I was able to compile and build all the examples on the CD in one evening. The code demonstrates many of the best practices of C++ programming and design patterns.

The author builds up a nice AI engine as you progress through the book.The C++ code from the CD (or web-site) is well commented and ties exactly into the pseudocode in the book.

Millington goes into considerable detail as he reveals the power of Artificial Intelligence for Games. He carefully explains each step including the math and physics required to carry out the execution. It is obvious that he has a great deal of experience in writing computer games. He shows you a clear solid way of doing things and then discussed the strengths and weaknesses by comparing it to other techniques and addressing possible optimizations.

To read and understand this book takes time and hard work. Artificial Intelligence is a large and complex topic in math and computer science programs.The author has brought many nuggets of wisdom from that branch of research and made them understandable and useful for game programmers.Not an easy job, but Millington is one of the best at explaining difficult concepts in a clear and straight forward way.

The other reviewer's that are knocking this book because of the code, don't knowwhat they are talking about. The code is excellent and what makes this a 5-star pick.

5-0 out of 5 stars Powerful Concepts Made Easy
Understand that the pseudo-code approach this book takes is what makes it such a standout from the rest of the crowd. The author is technically thorough and the syntax is straightforward enough to use in any language needed. Moreover, it frees the author to discuss AI in abstract terms which, in the end, proves to be much more valuable content. C++ source code puts the pseudo-code discussions into practice for those looking for real-world examples.

I would HIGHLY recommend this book as a follow up to Mat Buckland's "Programming Game AI by Example" (Nov., 2004)

2-0 out of 5 stars Not a great source for code
The author uses "pseudo-code" through out the book. The cd contains only a pc-executable program. There is no source code on the CD.

This book is a poor source of programming code where the author explains how ai works based on the pseudo-code.

If you're looking for source code (ie C++ source code) you'll not find it here. ... Read more


19. The Connection Machine (Artificial Intelligence)
by W. Danny Hillis
Paperback: 208 Pages (1989-02-15)
list price: US$25.00
Isbn: 0262580977
Average Customer Review: 5.0 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description
The Connection Machine describes a fundamentally different kind of computer. It offers a preview of a parallel processing computer that Daniel Hillis and others are now developing to perform tasks that no conventional, sequential machine can solve in a reasonable time.

W. Daniel Hillis is a founder of Thinking Machines Corporation where he is engaged in building connection machines as a significant step toward real thinking machines. The Connection Machine is included in the Artificial Intelligence series, edited by Patrick Winston, Michael Brady, and Daniel Bobrow.Amazon.com Review
This book is essentially an edited version of Hillis'slandmark thesis describing the design and implementation of theConnection Machine (CM), a massively parallel computer. The philosophybehind the CM's design is that the right kind of machine for manyimportant computational tasks is a machine with vast numbers of simpleprocessors doing the same thing on different data. This notion of oneprocessor per important data element (one processor per pixel in imageprocessing) is inspiring.

The Connection Machine is not atextbook and may be intimidating to beginners, but it provides awonderful picture of the kinds of issues involved in designing a newmachine. The book is well written and features a host of interestingdiscussions by Hillis on related topics (such as general philosophy ofparallel computing). Anyone interested in the subject of computerarchitecture will enjoy and profit greatly from this book. ... Read more

Customer Reviews (3)

5-0 out of 5 stars Connection Machine? Count me in!
This book is great. I have loved computers for years, and this book has given me a completely different way to think about them.

Hats off to Daniel Hillis!

-n8

5-0 out of 5 stars easy reading, good intro to massive multiprocessing
Especially given that this book is in fact a doctoral dissertation, it's extremely easy to read.This is not to say that it is written for children, but rather, the author has used language well to convey concepts rather than to confuse and sound stuffy.

The book states the limitations of the traditional Von Neumann computer architecture (which by and large we are still stuck with today) and then goes on to explain how an entirely different approach with many processors could work.

5-0 out of 5 stars What do you get when you connect a zillion computers togethe
This reference describes a computer architecture containing thousands of processor/memory cells that can be connected together by software, and the rational behind this architecture. It is easy to read, and is useful in providing the general reader with a feel for large multiple processor computation, in particular an architecture well suited for semantic network marker propagation. ... Read more


20. Artificial Intelligence: A Guide to Intelligent Systems (2nd Edition)
by Michael Negnevitsky
Hardcover: 440 Pages (2004-11-12)
list price: US$116.00 -- used & new: US$38.00
(price subject to change: see help)
Asin: 0321204662
Average Customer Review: 4.5 out of 5 stars
Canada | United Kingdom | Germany | France | Japan
Editorial Review

Product Description

Artificial Intelligence is one of the most rapidly evolving subjects within the computing/engineering curriculum, with an emphasis on creating practical applications from hybrid techniques. Despite this, the traditional textbooks continue to expect mathematical and programming expertise beyond the scope of current undergraduates and focus on areas not relevant to many of today's courses. Negnevitsky shows students how to build intelligent systems drawing on techniques from knowledge-based systems, neural networks, fuzzy systems, evolutionary computation and now also intelligent agents. The principles behind these techniques are explained without resorting to complex mathematics, showing how the various techniques are implemented, when they are useful and when they are not. No particular programming language is assumed and the book does not tie itself to any of the software tools available. However, available tools and their uses will be described and program examples will be given in Java. The lack of assumed prior knowledge makes this book ideal for any introductory courses in artificial intelligence or intelligent systems design, while the contempory coverage means more advanced students will benefit by discovering the latest state-of-the-art techniques.

... Read more

Customer Reviews (5)

3-0 out of 5 stars Undergraduate Textbook
I got this book as part of a short course in AI by Negnevitsky that I attended a while back. The course was, in my opinion, too short for the material covered. The book, however, appeared to be more promising. I'll start with the good points. First, it is well-written and covers the "essentials" of AI such as expert systems, fuzzy logic, neural networks, genetic algorithms, hybrid intelligent systems and data mining. Second, each chapter is well-organized with sufficient examples, a summary of key points and questions for review at the end. Third, at just over 400 pages and being only around 9.5 x 6.25 inches, it is also quite easy to carry around and read at your convenience. Fourth, the pages are bright white with crisp black text which also makes for easy reading even where lighting is not perfect.

However, I do have a few issues with the book. First, it does not really cover things like Monte-Carlo search, the minimax algorithm (used in chess) or swarm intelligence, to name a few. I found that as I looked for clarifications about certain things, I came across these other topics which weren't in the book; which brings me to the second issue. The beginning of each chapter is seductive with its easy-going introduction and general overview, especially to the uninitiated, I would imagine. However, the average reader (I have advanced degrees in computer science, by the way) will likely find himself trying to catch his breath after that. There is a little too much content squeezed into too few pages. Even more, Negnevitsky uses a considerable amount of mathematics, charts and diagrams which are not always easy understand. It is assumed, of course, that the reader has a "basic" understanding of math. If "advanced" math is used in say, rocket science, "basic" is just a relative term. If you simply skip over these things or assume they are true without trying hard to really understand them, you will not likely learn as much.

I did not intend to read this book to relive my undergraduate course in AI but it put me through it nonetheless. I was actually hoping for a less technical but sufficiently lucid explication of the different approaches currently used in AI; a "refresher" course, so to speak. Something that would explain the general principles without focusing too much on actual pen and paper calculations (which are unnecessary, even if one works in AI, unless one actually plans to employ a particular approach; in which case they can pursue it further elsewhere). In that respect, I was somewhat disappointed. This book appears to be intended mainly for undergraduates with the "be ready for the exam" mentality.

The problem is, by the end of the book, you begin to wonder just how much you've really learned. I would say it unlikely reaches even 50% of all that has been jam-packed into this book. To test this hypothesis, just see how many of the "questions for review", in total, that you can answer correctly after reading the whole book. Not to mention actually being able to do the kind of calculations the book seems to emphasize. To summarize the second issue, the book kind of pulls the reader away from gaining an important conceptual perspective of AI techniques and how they relate to each other. This is still possible despite the undergraduate and generally technical nature of the book but you will have to be careful to see the forest for the trees. Having both a strong, technical grasp of the techniques *and* a conceptual overview of how they relate to each other as a field is what, I think, the book tries to do but falls short at the expense of one.

The third issue pertains to the *ten* case studies at the end of the book. I'm not really sure that many are necessary, though (something to keep in mind for a possible 3rd edition of the book). While some of them are a refreshingly straightforward read, by the end of the book, you will likely find yourself having to go back to the chapters in which the techniques employed were initially explained to really make sense of them (even more so if you had skipped over the technical parts, which I didn't). In certain cases, Negnevitsky seems to have forgotten that while this book was "developed from lectures to undergraduates" (see the back cover), his readers are not necessarily attending those lectures afterward to ask for clarifications. For instance, in Case Study 9, he mentions the Gini coefficient and says they were used in Figure 9.46a but it is not explained *how* exactly they were used. If you look up the Gini coefficient in Wikipedia, it doesn't help much in this context, either. I, for one, was not previously familiar with it. The fourth issue is that I think there is also at least one significant error in the book in Figure 9.22. It says on page 327 that we can improve digit recognition by feeding the network with 'noisy' examples and that this is shown in Figure 9.22 (on the next page). However, the figure seems to show that the network trained with noisy examples has a higher percentage of recognition error. How is this an improvement?

Another thing I noticed is that there isn't really an equal treatment of even the topics covered. Fuzzy logic and neural networks seem to come up more often. This can be condoned to an extent but I really did not see the purpose of bringing up Adaptive Neuro-Fuzzy Inference Systems (ANFIS) as part of an "introductory text for a course in AI" and later referencing it in Case Study 8, which implies that it should be properly understood. Perhaps it deserved better treatment in the context of this book. Genetic algorithms, on the other hand, was nicely explained and later made Case Study 7 relatively easy to understand. Finally, I have to say that the cover art does the book only further injustice.

In summary, I would still recommend purchasing this book because some parts are beautifully explained and this is good for quick reference, especially when memory fails. However, there is still room out there for a less-technical, conceptually-inclined *introduction* to how things work in AI. Such a book may not be on the required reading list of undergraduate courses in AI or advanced courses in philosophy but it would probably be much more accessible to the public and even computer scientists in general.

5-0 out of 5 stars explains key ideas with minimal maths complications
The field of Artificial Intelligence has been around for decades. During which there have been numerous advances and disappointments. Often, the advances have been described in other texts using highly mathematical treatments. All to the good. Except that this does tend to act as a barrier to newcomers to AI, who might not have a very strong maths background. And even for those who do, the sheer amount of maths to understand in those books can be time consuming.

Which is the attraction of Negnevitsky's approach. He deliberately de-emphasises the maths. Enough is retained to give a valid treatment. But it is now far easier to understand the underlying ideas. Such as artificial neural networks. Here, I was also impressed to see him give proper prominence to John Hopfield's seminal contributions to neural network theory.

More generally, the book covers well the entire breadth of AI. From fuzzy systems to genetic algorithms to rule-based systems.

5-0 out of 5 stars A very good introductory text book for intelligent systems
The author explains various AI concepts in very simple terms and has managed to present the math behind some of the ideas in an understandable manner.

The treatment of various topics is intermediate though but it is a good place to start and does not leave the reader riddled with complex math equations.

In-fact the author has done a great job at keeping the concepts separate from the mathematics, except for some places like neural networks where it is not possible to explain the concepts without talking about the math involved.

Instead of focusing too much on a particular aspect of intelligent systems this book deals with a whole spectrum of technologies such as fuzzy systems, neural networks, hybrid systems etc.

The writing style of the author is very simple and clear and it is possible to finish the entire book over a period of one semester or a little more.

5-0 out of 5 stars Excellent Treatment of Complex Topics
What Dr. Negnevitsky states in the preface of this book, "Most of the literature on AI is expressed in the jargon of computer science, and crowded with complex matrix algebra and differential equations" is an accurate assessment of current textbooks that try to go beyond just the basics of AI.

Actually, this book does contain some of the same complex material that Dr. Negnevitsky accuses others for having with one exception:He does a terrific job in simplifying the complex theories behind them.

At first, when I flipped through the pages, huge equations and matrices jumped at me.My first impression was that this book was for serious computer scientists or mathematicians.I was looking for simpler material for my beginning AI students.I started reading the preface and found the argument interesting.

I speed-read through the first chapter and found the history of the field presented in a concise and a very well laid out fashion.I jumped into reading the beginning of chapter 2 and I was amazed at how well Dr. Negnevitsky progressed from basic ideas to more and more complex layers.With other similar books, the reader will need many basic theory books (mathematics, basic AI...) in order to understand the topics.Dr. Negnevitsky provides all the basics necessary.This same strategy is repeated for the remaining chapters.

I acquired the book and read it from beginning to end.I found the material consistently well presented.One warning: this book does get very technical and complex in many chapters.However, the material in each of those chapters is progressively laid out.Even if a reader stops in the middle of some chapters, there is still a lot to gain from the experience of reading the entire book.I highly recommend it to anyone interested in really understanding beyond just keywords and delve into the internals of AI topics.

Thanks to Dr. Negnevitsky for a great book.

5-0 out of 5 stars Great Introductory Book on Soft Computing
For a beginner that wants to know where the stories about Soft Computing really converge, this book is a starting point. The style of the author is simple and great.

My interest was to get a book that keeps the daunting mathematical jargons in Fuzzy Logic (contained in several other books) minimal, while presenting the concepts. I fell in love with this book, that I had to run through all the pages as if it's a novel.

This book really demonstrates that the whole idea behind intelligent systems are simple and straightforward. You do not need another teacher. He presented algorithms (e.g. back-propagation)in a very simple to understand manner.

Dr. Michael Negnevitsky, the author, must be a great teacher. It's a handy and nice book. I strongly recommend it. ... Read more


  1-20 of 100 | Next 20

Prices listed on this site are subject to change without notice.
Questions on ordering or shipping? click here for help.

site stats