Objectif The aim of this project is to advance the state of the art of cognitive systems by developing a methodology for autonomous and continuous learning. The project will concentrate on structural learning, where relations between components and compositional hierarchies play a central role in object categorization. Such learning is particularly relevant for the interpretation of man-made objects, hence the project will use the recognition of buildings and parts of buildings in outdoor scenes as its exemplary application domain.Due to the diversity of shapes and spatial arrangements of the different parts of a building, the recognition system must be capable of continually updating its conceptual knowledge. This requires the development of innovative methods for continuous learning. The project will advance the state of the art by concentrating on techniques of pattern discovery, concept learning, and ultimately self-learning. Just like a human child which has to be taught not only a certain subject but also the skills of autonomous learning, the proposed system will incorporate several levels of learning with decreasing responsibility of the teacher and increasing autonomy of the trained system, developing some self-awareness.The project will use symbolic primitives extracted by low-level modules. The relationships between the extracted components will be represented by- Bayesian networks, which will be used to model hierarchical structures,- Markov Random Fields, which will be used to model peer-to-peer relations,- logical structures which represent taxonomical and compositional hierarchies, and- 2D grammars which will attempt to capture the structural relations syntactically.For the development and evaluation of the system the project will use a rich dataset of several thousands of images of urban environments in the different countries of the participants. The learning components will be developed around the knowledge-based interpretation system SCENIC. Champ scientifique social scienceseducational sciencesdidactics Programme(s) FP6-IST - Information Society Technologies: thematic priority under the specific programme "Integrating and strengthening the European research area" (2002-2006). Thème(s) IST-2004-2.4.8 - Cognitive Systems Appel à propositions Data not available Régime de financement STREP - Specific Targeted Research Project Coordinateur RHEINISCHE FRIEDRICH-WILHELMS-UNIVERSITAET BONN Contribution de l’UE Aucune donnée Adresse REGINA-PACIS-WEG 3 53113 BONN Allemagne Voir sur la carte Coût total Aucune donnée Participants (4) Trier par ordre alphabétique Trier par contribution de l’UE Tout développer Tout réduire CESKE VYSOKE UCENI TECHNICKE V PRAZE Tchéquie Contribution de l’UE Aucune donnée Adresse ZIKOVA 4 166 36 PRAHA 6 Voir sur la carte Coût total Aucune donnée HAMBURGER INFORMATIK TECHNOLOGIE CENTER E.V. Allemagne Contribution de l’UE Aucune donnée Adresse C/O FACHBEREICH INFORMATIK - VOGT-KOELLN-STR. 30 22527 HAMBURG Voir sur la carte Coût total Aucune donnée IMPERIAL COLLEGE OF SCIENCE, TECHNOLOGY AND MEDICINE Royaume-Uni Contribution de l’UE Aucune donnée Adresse SOUTH KENSINGTON CAMPUS, EXHIBITION ROAD SW7 2AZ LONDON Voir sur la carte Coût total Aucune donnée UNIVERSITAET HAMBURG Allemagne Contribution de l’UE Aucune donnée Adresse EDMUND-SIEMERS-ALLEE 1 HAMBURG Voir sur la carte Liens Site web Opens in new window Coût total Aucune donnée