Automated decomposition of model-based learning problems
A new generation of sensor rich, massively distributed autonomous systems is being developed that has the potential for unprecedented performance, such as smart buildings, reconfigurable factories, adaptive traffic systems and remote earth ecosystem monitoring. To achieve high performance these mass...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
1996
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.1771 |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.330.1771 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.330.1771 2023-05-15T16:01:29+02:00 Automated decomposition of model-based learning problems Brian C. Williams Bill Millar The Pennsylvania State University CiteSeerX Archives 1996 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.1771 en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.1771 Metadata may be used without restrictions as long as the oai identifier remains attached to it. https://www.aaai.org/Papers/Workshops/1996/WS-96-01/WS96-01-032.pdf text 1996 ftciteseerx 2016-09-04T00:39:42Z A new generation of sensor rich, massively distributed autonomous systems is being developed that has the potential for unprecedented performance, such as smart buildings, reconfigurable factories, adaptive traffic systems and remote earth ecosystem monitoring. To achieve high performance these massive systems will need to accurately model themselves and their environment from sensor information. Accomplishing this on a grand scale requires automating the art of large-scale modeling. This paper presents a formalization of decompositional, model-based learning (DML), a method developed by observing a modeler’s expertise at decomposing large scale model estimation tasks. The method exploits a striking analogy between learning and consistency-based diagnosis. Moriarty, an implementation of DML, has been applied to thermal modeling of a smart building, demonstrating a significant improvement in learning rate. Text DML Unknown Moriarty ENVELOPE(165.967,165.967,-73.667,-73.667) |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
A new generation of sensor rich, massively distributed autonomous systems is being developed that has the potential for unprecedented performance, such as smart buildings, reconfigurable factories, adaptive traffic systems and remote earth ecosystem monitoring. To achieve high performance these massive systems will need to accurately model themselves and their environment from sensor information. Accomplishing this on a grand scale requires automating the art of large-scale modeling. This paper presents a formalization of decompositional, model-based learning (DML), a method developed by observing a modeler’s expertise at decomposing large scale model estimation tasks. The method exploits a striking analogy between learning and consistency-based diagnosis. Moriarty, an implementation of DML, has been applied to thermal modeling of a smart building, demonstrating a significant improvement in learning rate. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Brian C. Williams Bill Millar |
spellingShingle |
Brian C. Williams Bill Millar Automated decomposition of model-based learning problems |
author_facet |
Brian C. Williams Bill Millar |
author_sort |
Brian C. Williams |
title |
Automated decomposition of model-based learning problems |
title_short |
Automated decomposition of model-based learning problems |
title_full |
Automated decomposition of model-based learning problems |
title_fullStr |
Automated decomposition of model-based learning problems |
title_full_unstemmed |
Automated decomposition of model-based learning problems |
title_sort |
automated decomposition of model-based learning problems |
publishDate |
1996 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.1771 |
long_lat |
ENVELOPE(165.967,165.967,-73.667,-73.667) |
geographic |
Moriarty |
geographic_facet |
Moriarty |
genre |
DML |
genre_facet |
DML |
op_source |
https://www.aaai.org/Papers/Workshops/1996/WS-96-01/WS96-01-032.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.1771 |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766397320098742272 |