English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  On the complexity of inference about probabilistic relational models

Jaeger, M. (2000). On the complexity of inference about probabilistic relational models. Artificial Intelligence, 117, 297-308.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-344A-0 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-344B-E
Genre: Journal Article

Files

show Files
hide Files
:
aij00.ps.gz (Any fulltext), 78KB
 
File Permalink:
-
Name:
aij00.ps.gz
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/gzip
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Jaeger, Manfred1, Author           
Affiliations:
1Programming Logics, MPI for Informatics, Max Planck Society, ou_40045              

Content

show
hide
Free keywords: -
 Abstract: We investigate the complexity of probabilistic inference from knowledge bases that encode probability distributions on finite domain relational structures. Our interest here lies in the complexity in terms of the domain under consideration in a specific application instance. We obtain the result that assuming NETIME$\neq$ETIME this problem is not polynomial for reasonably expressive representation systems. The main consequence of this result is that it is unlikely to find inference techniques with a better worst-case behavior than the commonly employed strategy of constructing standard Bayesian networks over ground atoms (knowledge based model construction).

Details

show
hide
Language(s): eng - English
 Dates: 2010-03-122000
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: eDoc: 519773
Other: Local-ID: C1256104005ECAFC-ADCD4005448FD8EFC12569D500647999-Jaeger00
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Artificial Intelligence
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 117 Sequence Number: - Start / End Page: 297 - 308 Identifier: ISSN: 0004-3702