Artificial Intelligence: Theory and Practice [Paperback]

Thomas Dean (Author)

Book Description

ISBN-10: 0805325476 | ISBN-13: 978-0805325478 | Publication Date: January 10, 1995 | Edition: 1

This book provides a detailed understanding of the broad issues in artificial intelligence and a useful survey of current AI technology. The author delivers broad coverage of innovative representational techniques, including neural networks, image processing, and probabilistic reasoning, alongside the traditional methods of symbolic reasoning. AI algorithms are described in detailed prose in the text and fully implemented in LISP at the ends of chapters. A stand-alone LISP chapter makes an excellent reference and refresher. Each chapter includes a detailed description of an AI application.

Editorial Reviews

From the Back Cover

Emphasize both scientific theory and practical applications with Artifical Intelligence: Theory and Practice, a new text by Thomas Dean with James Allen and Yiannis Aloimonos. This modern, balanced introduction to artificial intelligence examines both the representational and computational issues that arise in developing systems capable of machine intelligence. The authors discuss these issues in terms of their syntax, semantics, and computation and offer detailed coverage of both traditional symbolic reasoning techniques and alternative techniques such as neural networks, probabilistic reasoning, and image processing. In addition, they emphasize the role of experimental computer science by showing the practical implementation of algorithms by first using pseudocode and then LISP code.

To ensure that readers fully understand the topic and its applications, the authors provide motivating examples throughout. AI in Practice boxes appear in each chapter, demonstrating real-world uses of artificial intelligence by NASA, General Motors Corporation, Microsoft Corporation, and other companies. LISP Implementation appendices are found at the end of most chapters, providing fully-documented implementations of important algorithms (also available in Scheme and C++ implementations via ftp). These are carefully coordinated with the discussions in the chapters making it easy for students to complete computational experiments. Plus, the text features summaries, exercises, and background sections describing related work at the end of each chapter.

0805325476B04062001

About the Author

James Allen is the John H. Dessaurer Professor of Computer Science at the University of Rochester. He has taught natural language processing to undergraduate and graduate students for 14 years. He is a fellow of the AAAI and was the recipient of the Presidential Young Investigator Award (1985-1989). In addition, Professor Allen was the Editor-in- Chief of Computational Linguistics from 1983-1993.

0805325476AB04062001

Product Details

• Paperback: 650 pages
• Publisher: Addison Wesley; 1 edition (January 10, 1995)
• Language: English
• ISBN-10: 0805325476
• ISBN-13: 978-0805325478
• Product Dimensions: 9.4 x 7.8 x 1.1 inches
• Shipping Weight: 2.3 pounds (View shipping rates and policies)
• Average Customer Review: 3.5 out of 5 stars  See all reviews (2 customer reviews)
• Amazon Best Sellers Rank: #1,880,257 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

11 of 11 people found the following review helpful:

2.0 out of 5 stars Serious errors, September 20, 2002

By A Customer

This review is from: Artificial Intelligence: Theory and Practice (Paperback)

I used to use this text for AI undergraduate courses, and have given up. It has grievous errors in it, including in the on-line errata. Two quick examples: the information theoretic equations for decision trees is dead wrong. And the alpha-beta algorithm is completely incorrect. The text also has packed large amounts of information into very tight spaces, leading to poor explanations in important sections: the backpropagation section in particular consistently leads to serious confusion among students. And attempts to reduce algorithms into a procedural rather than functional/recursive format only result in excess complexity.

This is particularly frustrating because there really is no good undergraduate text for AI. This one comes close, packing in lots of stuff into an inexpensive volume. But the errors are serious enough, and in such high-utility sections, that this book cannot be recommended.

14 of 16 people found the following review helpful:

5.0 out of 5 stars This is a useful book by eminent authors., March 28, 2000

By 

Amit Konar - See all my reviews

This review is from: Artificial Intelligence: Theory and Practice (Paperback)

This is a good book for the beginners in the subject. I liked the book for its beautiful writing style. The most useful chapters of this book are chapter 5 on learning, chapter 7 on planning and chapter 9 on image understanding.The concepts on the situation calculus discussed in chapter 6 are also presented very interestingly. The examples used to illustrate different issues are realistic. The book must be on the desk of anyone interested in the domain of Artificial Intelligence.