Artificial Intelligence (3rd Edition) [Hardcover]

Winston (Author)

Book Description

ISBN-10: 0201533774 | ISBN-13: 978-0201533774 | Publication Date: May 10, 1992 | Edition: 3

This is the all-time bestselling introduction to artificial intelligence. The third edition retains the best features of the earlier works, including superior readability, currency, and excellence in the selection of examples. Winston emphasizes how artificial intelligence can be viewed from an engineering or a scientific point of view. The new edition offers comprehensive coverage of more material, and many of the ideas presented are enhanced with a variety of side pieces, including application examples such as the Westinghouse nuclear fuel plant optimizer.

Editorial Reviews

Amazon.com Review

This book is one of the oldest and most popular introductions to artificial intelligence. An accomplished artificial intelligence (AI) scientist, Winston heads MIT's Artificial Intelligence Laboratory, and his hands-on AI research experience lends authority to what he writes. Winston provides detailed pseudo-code for most of the algorithms discussed, so you will be able to implement and test the algorithms immediately. The book contains exercises to test your knowledge of the subject and helpful introductions and summaries to guide you through the material.

From the Back Cover

This book explains how it is possible for computers to reason and perceive, thus introducing the field called artificial intelligence. From the book, you learn why the field is important, both as a branch of engineering and as a science.

If you are a computer scientist or an engineer, you will enjoy the book, because it provides a cornucopia of new ideas for representing knowledge, using knowledge, and building practical systems. If you are a psychologist, biologist, linguist, or philosopher, you will enjoy the book because it provides an exciting computational perspective on the mystery of intelligence.

The Knowledge You Need

This completely rewritten and updated edition of Artificial Intelligence reflects the revolutionary progress made since the previous edition was published.

Part I is about representing knowledge and about reasoning methods that make use of knowledge. The material covered includes the semantic-net family of representations, describe and match, generate and test, means-ends analysis, problem reduction, basic search, optimal search, adversarial search, rule chaining, the rete algorithm, frame inheritance, topological sorting, constraint propagation, logic, truth maintenance, planning, and cognitive modeling.

Part II is about learning, the sine qua non of intelligence. Some methods involve much reasoning; others just extract regularity from data. The material covered includes near-miss analysis, explanation-based learning, knowledge repair, case recording, version-space convergence, identification-tree construction, neural-net training, perceptron convergence, approximation-net construction, and simulated evolution.

Part III is about visual perception and language understanding. You learn not only about perception and language, but also about ideas that have been a major source of inspiration for people working in other subfields of artificial intelligence. The material covered includes object identification, stereo vision, shape from shading, a glimpse of modern linguistic theory, and transition-tree methods for building practical natural-language interfaces.

Special Features of this Edition

• Based on extensive teaching experience
• Semiformal representation and procedure specifications bring the ideas to within a step or two of implementation and highlight unifying themes.
• Application examples provide a glimpse of the ideas at work in real-world systems.
• Powerful ideas and principles are identified and emphasized.

0201533774B04062001

See all Editorial Reviews

Product Details

• Hardcover: 737 pages
• Publisher: Addison Wesley; 3 edition (May 10, 1992)
• Language: English
• ISBN-10: 0201533774
• ISBN-13: 978-0201533774
• Product Dimensions: 9.5 x 7.8 x 1.4 inches
• Shipping Weight: 3.3 pounds (View shipping rates and policies)
• Average Customer Review: 3.4 out of 5 stars  See all reviews (11 customer reviews)
• Amazon Best Sellers Rank: #255,302 in Books (See Top 100 in Books)

More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

Most Helpful Customer Reviews

23 of 26 people found the following review helpful:

5.0 out of 5 stars Very useful and well written; an industry perspective:, August 17, 1999

By A Customer

This review is from: Artificial Intelligence (3rd Edition) (Hardcover)

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 how to do it: buy this book and Sipser's on the Theory of Computation. After digesting them (which is easy if you're as good with logical mathematics as the typical software engineer), you should be able to read current literature in either field, and will have a deep, fundamental understanding of how to best solve whatever problem you're working on. That's what worked for me, anyway. An excellent book, as is Sipser's.

12 of 13 people found the following review helpful:

5.0 out of 5 stars A truly excellent survey of the field of AI, June 18, 1999

By A Customer

This review is from: Artificial Intelligence (3rd Edition) (Hardcover)

Having purchased this book as a supplement to Winston's course at MIT, I can very highly recommend it as a very comprehensive, up-to-date, well written text summarizing the field. The book covers essentially all of the topics pertenant in modern AI with enough detail for a complete implementation without being overly technical. I strongly recommend it to anybody looking to build intelligent systems or to anybody simply perusing the field for abstract ideas.

17 of 20 people found the following review helpful:

4.0 out of 5 stars Good as an undergraduate text, December 18, 1998

By A Customer

This review is from: Artificial Intelligence (3rd Edition) (Hardcover)

This book serves as an excellent introduction to what is in reality a very broad topic. Not meant for serious research into any one particular area of AI, the text is excellent for undergraduates(with questions that aren't worded too badly - a rarity in AI texts). More advanced AI topics are given short shrift(as is typical), but are covered in sufficient depth to give students an idea of how they work(three chapters worth if I'm not mistaken, more than most texts).