David Heckerman - Probabilistic Similarity Networks



David Heckerman - Probabilistic Similarity Networks
Publisher: MIT Press | 1991-11-04 | ISBN: 0262082063 | File type: PDF | 265 pages | 2.70 mb


In this remarkable blend of formal theory and practical application, David Heckerman develops methods for building normative expert systems - expert systems that encode knowledge in a decision-theoretic framework.
Heckerman introduces the similarity network and partition, two extensions to the influence diagram representation. He uses the new representations to construct Pathfinder, a large, normative expert system for the diagnosis of lymph-node diseases. Heckerman shows that such expert systems can be built efficiently, and that the use of a normative theory as the framework for representing knowledge can dramatically improve the quality of expertise that is delivered to the user. He concludes with a formal evaluation of the power of his methods for building normative expert systems.
This book has been written for readers from backgrounds in various areas, including artificial intelligence, decision analysis, and medical informatics. Chapters 1, 2, and 6 contain the fundamental ideas regarding similarity networks and partitions, and should be read by everyone.
Appendix A contains a discussion of basic concepts from decision theory and a tutorial on knowledge maps and influence diagrams. People should read this appendix before reading the main body of the book if they are unfamiliar with the concept of the joint probability distribution, the principle of maximum expected utility, or the distinctions between Bayesian and frequentist philosophies, between normative and descriptive reasoning, or between decision theory and decision analysis. Chapter 3 contains a detailed axiomatic characterization of the similarity-network representation. Those readers who are mainly interested in an intuitive understanding of the representations may skip this chapter. Readers who are technically inclined should note that all the major results, and the arguments for those results, are contained in Chapter 3. The more complicated proofs are given in Appendix B. Chapters 4 and 5 describe the construction and evaluation of Pathfinder. Researchers in the field of medical informatics and others who are interested in learning about the practical application of the similarity-network and partition representations to knowledge acquisition will find these chapters particularly relevant.
David Heckerman is Assistant Professor of Computer Science at the University of Southern California. He received his doctoral degree in Medical Information Sciences from Stanford University.


Download Link:

http://depositfiles.com/files/mf52jnctq

http://www.filesonic.com/file/32412023/b252-0262082063 .rar





[Fast Download] David Heckerman - Probabilistic Similarity Networks


Related eBooks:
Radiation Oncology: A Question-Based Review 3rd Edition
A Practical Guide to Laser Procedures
A History of Surgical Paediatrics
Genetics of Asthma and Chronic Obstructive Pulmonary Disease
Patty's Toxicology
Sexually Transmitted Diseases
Insulin Resistance
Handbook of Topical Antimicrobials: Industrial Applications in Consumer Products and Pharmaceutical
Cancer in Adolescents and Young Adults, 2nd edition
Dental Computing and Applications
Injury Control: Research and Program Evaluation
Case Files Family Medicine (LANGE Case Files) by Eugene Toy
Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.