A Multiattribute Utility Approach to Inference Understandability and Explanation

From Tetherless World Wiki

Jump to: navigation, search

Citation: Eric Horvitz. (1987) A Multiattribute Utility Approach to Inference Understandability and Explanation. In KSL-87-28, 1987.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Eric Horvitz
title A Multiattribute Utility Approach to Inference Understandability and Explanation
number KSL-87-28
institution Knowledge Systems, AI Laboratory
year 1987
Bibtex more
note 34 pages.
Access Paper
abstract We describe research on the use of multiattribute utility models for tailoring expert-system inference and explanation to classes of users within alternative decision-making contexts. In particular, we introduce a formalization of automated explanation. We describe how useful explanations can be synthesized through the optimization of utility models that capture components of value in explanation. We discuss techniques for balancing the benefits of increased detail or completeness of analyses and explanations with the costs associated with accompanying increases in computational and cognitive complexity. We describe how the nature and optimal solution of such tradeoffs depend on the user and on the context. After introducing early work on user-specific multiattribute utility models in the PATHFINDER expert system for tissue-pathology diagnoses, we discuss current research on making complex reasoning more valuable through the explicit representation and manipulation of knowledge about multiple attributes of value in computational behavior.

KSL Technical Report ID: KSL-87-28
Facts about A Multiattribute Utility Approach to Inference Understandability and ExplanationRDF feed
Abstract We describe research on the use of multiat … We describe research on the use of multiattribute utility models for tailoring expert-system inference and explanation to classes of users within alternative decision-making contexts. In particular, we introduce a formalization of automated explanation. We describe how useful explanations can be synthesized through the optimization of utility models that capture components of value in explanation. We discuss techniques for balancing the benefits of increased detail or completeness of analyses and explanations with the costs associated with accompanying increases in computational and cognitive complexity. We describe how the nature and optimal solution of such tradeoffs depend on the user and on the context. After introducing early work on user-specific multiattribute utility models in the PATHFINDER expert system for tissue-pathology diagnoses, we discuss current research on making complex reasoning more valuable through the explicit representation and manipulation of knowledge about multiple attributes of value in computational behavior. ibutes of value in computational behavior.
Author Eric Horvitz  +
Bibtype techreport  +
Has author Eric Horvitz  +
Has identifier KSL-87-28  +
Has publishing details 1987  +
Has title A Multiattribute Utility Approach to Inference Understandability and Explanation  +
Has where published KSL-87-28  +
Has year 1987  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-87-28  +
Note 34 pages.
Number KSL-87-28  +
Process note NO  +
Title A Multiattribute Utility Approach to Inference Understandability and Explanation  +
Year 1987  +
Retrieved from "http://tw.rpi.edu/wiki/A_Multiattribute_Utility_Approach_to_Inference_Understandability_and_Explanation"
Personal tools