Learning from Incongruence
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00200333" target="_blank" >RIV/68407700:21230/12:00200333 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-642-24034-8_10" target="_blank" >http://dx.doi.org/10.1007/978-3-642-24034-8_10</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-24034-8_10" target="_blank" >10.1007/978-3-642-24034-8_10</a>
Alternative languages
Result language
angličtina
Original language name
Learning from Incongruence
Original language description
We present an approach to constructing a model of the universe for explaining observations and making decisions based on learning new concepts. We use a weak statistical model, e.g. a discriminative classifier, to distinguish errors in measurements fromimproper modeling. We use boolean logic to combine outcomes of direct detectors of relevant events, e.g. presence of sound and presence of human shape in the field of view, into more complex models explaining the states in which the universe may appear.The process of constructing a new concept is initiated when a significant disagreement - incongruence -- has been observed between incoming data and the current model of the universe. Then, a new concept, i.e. a new direct detector, is trained on incongruent data and combined with existing models to remove the incongruence. We demonstrate the concept in an experiment with human audio-visual detection.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
DA - Hydrology and limnology
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Detection and Identification of Rare Audiovisual Cues
ISBN
978-3-642-24033-1
ISSN
1860-949X
e-ISSN
—
Number of pages
9
Pages from-to
119-127
Publisher name
Springer
Place of publication
Berlin
Event location
Barcelona
Event date
Sep 24, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000302002500011