Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from Databases

From Tetherless World Wiki

Jump to: navigation, search

Citation: Edward Herskovits and Gregory F. Cooper. (1990) Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from Databases. In KSL-90-22, March,1990.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Edward Herskovits and Gregory F. Cooper
title Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from Databases
number KSL-90-22
institution Knowledge Systems, AI Laboratory
year 1990
month March
Bibtex more
Access Paper
abstract Kutato is a system that takes as input a database of cases and produces a belief network that captures many of the dependence relations represented by those data. This system incorporates a module for determining the entropy of a belief network and a module for constructing belief networks based on entropy calculations. Kutato constructs an initial belief network in which all variables in the database are assumed to be marginally independent. The entropy of this belief network is calculated, and that arc is added that minimizes the entropy of the resulting belief network. Conditional probabilities for an arc are obtained directly from the database. This process continues until an entropy-based threshold is reached. We have tested the system by generating databases from networks with Henrion's probabilistic logic-sampling method, and then using those databases as input to Kutato. The system consistently reproduces the original belief networks with high fidelity.

KSL Technical Report ID: KSL-90-22
Facts about Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from DatabasesRDF feed
Abstract Kutato is a system that takes as input a d … Kutato is a system that takes as input a database of cases and produces a belief network that captures many of the dependence relations represented by those data. This system incorporates a module for determining the entropy of a belief network and a module for constructing belief networks based on entropy calculations. Kutato constructs an initial belief network in which all variables in the database are assumed to be marginally independent. The entropy of this belief network is calculated, and that arc is added that minimizes the entropy of the resulting belief network. Conditional probabilities for an arc are obtained directly from the database. This process continues until an entropy-based threshold is reached. We have tested the system by generating databases from networks with Henrion's probabilistic logic-sampling method, and then using those databases as input to Kutato. The system consistently reproduces the original belief networks with high fidelity. iginal belief networks with high fidelity.
Author Edward Herskovits and Gregory F. Cooper  +
Bibtype techreport  +
Has author Edward Herskovits and Gregory F. Cooper  +
Has identifier KSL-90-22  +
Has publishing details March,1990  +
Has title Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from Databases  +
Has where published KSL-90-22  +
Has year 1990  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-90-22  +
Month March  +
Number KSL-90-22  +
Process note NO  +
Title Kutato: An Entropy-Driven System for Construction of Probabilistic Expert Systems from Databases  +
Year 1990  +
Retrieved from "http://tw.rpi.edu/wiki/Kutato:_An_Entropy-Driven_System_for_Construction_of_Probabilistic_Expert_Systems_from_Databases"
Personal tools