Objectif The aim of the project is to develop a geometrically meaningful framework that allows generalizing deep learning paradigms to data on non-Euclidean domains. Such geometric data are becoming increasingly important in a variety of fields including computer graphics and vision, sensor networks, biomedicine, genomics, and computational social sciences. Existing methodologies for dealing with geometric data are limited, and a paradigm shift is needed to achieve quantitatively and qualitatively better results. Our project is motivated by the recent dramatic success of deep learning methods in a wide range of applications, which has literally shaken the academic and industrial world. Though these methods have been known for decades, the computational power of modern computers, availability of large datasets, and efficient optimization methods allowed creating and effectively training complex models that made a qualitative breakthrough. In particular, in computer vision, deep neural networks have achieved unprecedented performance on notoriously hard problems such as object recognition. However, so far research has mainly focused on developing deep learning methods for Euclidean data such as acoustic signals, images, and videos. In fields dealing with geometric data, the adoption of deep learning has been lagging behind, primarily since the non-Euclidean nature of objects dealt with makes the very definition of basic operations used in deep networks rather elusive. The ambition of the project is to develop geometric deep learning methods all the way from a mathematical model to an efficient and scalable software implementation, and apply them to some of today’s most important and challenging problems from the domains of computer graphics and vision, genomics, and social network analysis. We expect the proposed framework to lead to a leap in performance on several known tough problems, as well as to allow addressing new and previously unthinkable problems. Champ scientifique natural sciencesphysical sciencestheoretical physicsparticle physicsneutrinosnatural sciencescomputer and information sciencesartificial intelligencecomputer visionnatural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learningnatural sciencesmathematicspure mathematicsgeometrynatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Mots‑clés geometric deep learning convolutional neural networks intrinsic geometry shape analysis shape correspondence signal processing on graphs spectral methods face analysis social network analysis Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Thème(s) ERC-2016-COG - ERC Consolidator Grant Appel à propositions ERC-2016-COG Voir d’autres projets de cet appel Régime de financement ERC-COG - Consolidator Grant Institution d’accueil THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD Contribution nette de l'UE € 200 000,10 Adresse WELLINGTON SQUARE UNIVERSITY OFFICES OX1 2JD Oxford Royaume-Uni Voir sur la carte Région South East (England) Berkshire, Buckinghamshire and Oxfordshire Oxfordshire Type d’activité Higher or Secondary Education Establishments Liens Contacter l’organisation Opens in new window Site web Opens in new window Participation aux programmes de R&I de l'UE Opens in new window Réseau de collaboration HORIZON Opens in new window Coût total € 200 000,10 Bénéficiaires (4) Trier par ordre alphabétique Trier par contribution nette de l'UE Tout développer Tout réduire THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD Royaume-Uni Contribution nette de l'UE € 200 000,10 Adresse WELLINGTON SQUARE UNIVERSITY OFFICES OX1 2JD Oxford Voir sur la carte Région South East (England) Berkshire, Buckinghamshire and Oxfordshire Oxfordshire Type d’activité Higher or Secondary Education Establishments Liens Contacter l’organisation Opens in new window Site web Opens in new window Participation aux programmes de R&I de l'UE Opens in new window Réseau de collaboration HORIZON Opens in new window Coût total € 200 000,10 UNIVERSITA DELLA SVIZZERA ITALIANA Participation terminée Suisse Contribution nette de l'UE € 87 624,90 Adresse VIA GIUSEPPE BUFFI 13 6900 Lugano Voir sur la carte Région Schweiz/Suisse/Svizzera Ticino Ticino Type d’activité Higher or Secondary Education Establishments Liens Contacter l’organisation Opens in new window Site web Opens in new window Participation aux programmes de R&I de l'UE Opens in new window Réseau de collaboration HORIZON Opens in new window Coût total € 87 624,90 TWITTER UK LIMITED Participation terminée Royaume-Uni Contribution nette de l'UE € 375 000,00 Adresse 1ST FLOOR 20 AIR STREET W1B 5AN London Voir sur la carte Région London Inner London — West Westminster Type d’activité Private for-profit entities (excluding Higher or Secondary Education Establishments) Liens Contacter l’organisation Opens in new window Participation aux programmes de R&I de l'UE Opens in new window Réseau de collaboration HORIZON Opens in new window Coût total € 375 000,00 IMPERIAL COLLEGE OF SCIENCE TECHNOLOGY AND MEDICINE Royaume-Uni Contribution nette de l'UE € 1 335 250,00 Adresse SOUTH KENSINGTON CAMPUS EXHIBITION ROAD SW7 2AZ LONDON Voir sur la carte Région London Inner London — West Westminster Type d’activité Higher or Secondary Education Establishments Liens Contacter l’organisation Opens in new window Site web Opens in new window Participation aux programmes de R&I de l'UE Opens in new window Réseau de collaboration HORIZON Opens in new window Coût total € 1 335 250,00
