Please use this identifier to cite or link to this item: http://hdl.handle.net/11400/10437
Title: Machine learning for a general purpose declarative scene modeler
Authors: Πλεμμένος, Δημήτρης
Μιαούλης, Γεώργιος
Βασιλάς, Νικόλαος
Item type: Conference publication
Conference Item Type: Full Paper
Keywords: Μάθηση μηχανής;δηλωτική μοντελοποίηση σκηνής;νευρωνικά δίκτυα;γενετικοί αλγόριθμοι;Machine learning;declarative scene modelling;Neural networks;Genetic algorithms
Subjects: Πληροφορική
Μηχανική
Computer science
Engineering
Issue Date: 15-May-2015
16-Sep-2002
Date of availability: 14-May-2015
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.
Language: English
Citation: Plemenos, D., Miaoulis, G. and Vassilas, N. (2002) Machine Learning for a General Purpose Declarative Scene Modeler. GraphiCon 2002. Nizhny Novgorod, Russia.
Conference: GraphiCon 2002
Access scheme: Publicly accessible
License: Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες
URI: http://hdl.handle.net/11400/10437
Appears in Collections:Δημοσιεύσεις

Files in This Item:
File Description SizeFormat 
Machine Learning for a General Purpose Declarative Scene.pdf766.04 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons