Artificial Intelligence: A Modern Approach

From Wikipedia, the free encyclopedia

This article or section reads like a review and may need cleanup.
Please help improve this article to make it neutral in tone and meet Wikipedia's quality standards. (talk, help, how to edit)

This article or section may require cleanup to meet Wikipedia's quality standards.
Please help improve this article or replace this tag with a more specific message. This article has been tagged since August 2006. (help, talk)

Artificial Intelligence: A Modern Approach (ISBN 0-13-790395-2) (AIMA) is the current standard undergraduated text book on Artificial Intelligence, written by Stuart J. Russell and Peter Norvig. The second edition of this book was released on December 20, 2002. It is used in over 900 universities including all of those ranked in the top 40 schools with the best computer science schools that offer a course in artificial intelligence.

The book is intended for an undergraduate audience but can also be used for graduate-level studies with the suggestion of adding some of the primary sources listed in the extensive bibliography. The volume has a conversational tone and is very easy to read.

The authors present the subject of artificial intelligence (AI) in a unified manner using the concept of an intelligent agent to develop a common framework for problem solving. The theory and practice of intelligent agent design are given equal weight in the text. The principles of intelligent agent design are clarified through implementation with over 300 exercises included in the book, of which some are large enough for term-level projects.

[edit] Chapters

Artificial Intelligence: A Modern Approach is divided into eight parts with a total of 27 chapters. The authors state that it is a large text which would take two semesters to cover all the chapters and projects.

'Part I': Artificial Intelligence
This section sets the stage for the following sections by viewing AI systems as intelligent agents that can decide what actions to take and when to take them.

'Part II': Problem Solving
Focuses on methods for deciding what action to take when needing to think several steps ahead, such as playing a game of chess.

'Part III': Knowledge and Reasoning
Discusses ways to represent knowledge about the intelligent agents' environment and how to reason logically with that knowledge.

'Part IV': Acting Logically
Concentrates on constructing plans using the reasoning methods discussed in the previous section.

'Part V': Uncertain Knowledge and Reasoning
This section is analogous to Parts III and IV, but deals with reasoning and decision-making in the presence of uncertainty in the environment, such as a system for medical diagnosis.

'Part VI': Learning
Describes ways for generating knowledge required by the decision-making components and introduces a new component, the neural network.

'Part VII': Communicating, Perceiving, and Acting
Concentrates on ways an intelligent agent can perceive its environment whether by touch, vision, or understanding language and ways to turn plans into actions.

'Part VIII': Conclusions
Considers the past and future of AI by discussing what AI really is and why it has succeeded to some degree. Also, the views of those philosophers who believe that AI can never succeed are given discussion.