Pattern Recognition Basis AI - Couverture souple

Tveter, Donald

Couverture souple

ISBN 10 : 0818677961 ISBN 13 : 9780818677960

Editeur : John Wiley & Sons, 1998

Synopsis

The Pattern Recognition Basis of Artificial Intelligence This book pays extra attention to the new ideas in AI: neural networking, case based reasoning, and memory based reasoning, while including the important aspects of traditional symbol processing AI. As much as possible, these methods are compared with each other so that the reader will see the advantages and disadvantages of each method. Second, the new and traditional methods are presented as dif... Full description

A propos du livre

Présentation de l'éditeur

This book takes the viewpoint that plain symbol processingtechniques have little hope of reproducing the depth and breadth ofcapabilities found in human beings. The book introduces newfoundational principles to AI: connectionist/neural networkingmethods, case based and memory based methods and pictureprocessing.

The book looks at methods of AI as different ways of doing patternrecognition. One way to do pattern recognition is to compare aproblem to stored cases. At the other end of the spectrum,Classical Symbol Processing AI compresses cases down to a small setof rules and then works only with this condensed knowledge. Inbetween these two extremes are neural networks, especially backproptype networks. As much as possible the book compares these threebasic methods using actual AI programs.

The structure of the book starts at the bottom of human abilitieswith vision and other simple pattern recognition abilities andmoves on to the higher levels of problem solving and game playingand finally to the level of natural language and understanding ofthe world. At the higher levels more complex computer architecturesare needed that include methods for structuring thoughts.

The book is organized in a manner in which the reader will get anintuitive feeling for the principles of AI. Throughout the bookapplications of basic principles are demonstrated by examining someclassic AI programs in detail. The book can serve as a text forjuniors, seniors and first year graduate students in ComputerScience or Psychology and includes sample problems and data forexercises and a list of frequently asked questions.

À propos de cette édition

• Éditeur: John Wiley & Sons
• Date d'édition: 1998
• ISBN 10: 0818677961
• ISBN 13: 9780818677960
• Reliure: Broché
• Nombre de pages: 388