Management of Knowledge Imperfection in Building Intelligent Systems

ISBN-13: 9783540774624 / Angielski / Twarda / 2008 / 254 str.

Eugene Roventa; Tiberiu Spircu

Opis

This book is among the very few to be entirely dedicated to the treatment of knowledge imperfection when building intelligent systems. The authors are of the belief that an entire book should be focused on this important aspect of knowledge processing.

Spis treści

“Classical” Expert Systems.- Knowledge Representation.- Uncertainty and Classical Theory of Probability.- Statistical Inference.- Bayesian (Belief) Networks.- Certainty Factors Theory.- Belief Theory.- Possibility Theory.- Approximate Reasoning.- Review.

Blurb

There are many good AI books. Usually they consecrate at most one or two chapters to the imprecision knowledge processing. This book is among the few books to be entirely dedicated to the treatment of knowledge imperfection when building intelligent systems. We consider that an entire book should be focused on this important aspect of knowledge processing. The expected audience for this book includes undergraduate students in computer science, IT&C, mathematics, business, medicine, etc., graduates, specialists and researchers in these fields. The subjects treated in the book include expert systems, knowledge representa-tion, reasoning under knowledge Imperfection (Probability Theory, Possibility Theory, Belief Theory, and Approximate Reasoning). Most of the examples discussed in details throughout the book are from the medical domain. Each chapter ends with a set of carefully pedagogically chosen exercises, which complete solution provided. Their understanding will trigger the comprehension of the theoretical notions, concepts and results.

Features of the book:
a) Comprehensive comparative approach to deal with most of the techniques of management of knowledge imperfection
b) Breakthrough fuzzy techniques approach for handling real word imprecision
c) Numerous examples throughout the book in the medical domain
d) Each chapter is followed by a set of detailed solved exercises.