Machine learning for a general purpose declarative scene modeler

dc.contributor.author	Πλεμμένος, Δημήτρης	el
dc.contributor.author	Μιαούλης, Γεώργιος	el
dc.contributor.author	Βασιλάς, Νικόλαος	el
dc.date.accessioned	2015-05-14T21:38:55Z
dc.date.available	2015-05-14T21:38:55Z
dc.date.issued	2015-05-15
dc.identifier.uri	http://hdl.handle.net/11400/10437
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.189.1590&rep=rep1&type=pdf	en
dc.subject	Μάθηση μηχανής
dc.subject	δηλωτική μοντελοποίηση σκηνής
dc.subject	νευρωνικά δίκτυα
dc.subject	γενετικοί αλγόριθμοι
dc.subject	Machine learning
dc.subject	declarative scene modelling
dc.subject	Neural networks
dc.subject	Genetic algorithms
dc.title	Machine learning for a general purpose declarative scene modeler	en
heal.type	conferenceItem
heal.classification	Πληροφορική
heal.classification	Μηχανική
heal.classification	Computer science
heal.classification	Engineering
heal.classificationURI	N/A-Πληροφορική
heal.classificationURI	N/A-Μηχανική
heal.classificationURI	http://skos.um.es/unescothes/C00750
heal.classificationURI	http://skos.um.es/unescothes/C01363
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh85079324
heal.keywordURI	http://zbw.eu/stw/descriptor/19808-6
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh92002377
heal.identifier.secondary	DOI: 10.1.1.189.1590
heal.language	en
heal.access	free
heal.recordProvider	Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Πληροφορικής Τ.Ε.	el
heal.publicationDate	2002-09-16
heal.bibliographicCitation	Plemenos, D., Miaoulis, G. and Vassilas, N. (2002) Machine Learning for a General Purpose Declarative Scene Modeler. GraphiCon 2002. Nizhny Novgorod, Russia.	en
heal.abstract	In this paper we discuss about the implementation of machine learning mechanisms in declarative scene modelling. After a study of the different kinds of declarative modellers and the different cases where machine learning seems useful, we describe two implemented techniques allowing machine learning for declarative modelling by hierarchical decomposition. The first technique is based on neural networks and allows reduction of the solution space in order to generate only solutions corresponding to the user’s wishes. The second one uses a genetic algorithm which, starting from a set of scenes produced by the generation engine of the declarative modeller, produces other solutions under the user’s control, taking hence the place of the generation engine. The obtained results are then explained and discussed.	en
heal.fullTextAvailability	true
heal.conferenceName	GraphiCon 2002	en
heal.conferenceItemType	full paper