Description du projet Cognitive Systems and RoboticsNew tools for the collaborative development of very complex machine learning systems.The MASH project aims at creating new tools for the collaborative development of very complex machine learning systems. Machine learning is concerned with the design of software able to learn from example. Since machine learning methods remain far from their biological counterpart in terms of performance, MASH will investigate a new strategy, by developing new theoretical tools and software to help large groups of individuals design large families of feature extractors. The idea is to combine several types of features developed by independent teams in order to improve performance. Because they exploit different sources of information, different modules mutually compensate their weaknesses. Afficher les objectifs du projet Masquer les objectifs du projet This project aims at developing new machine learning methods relying on very large number of hand-designed heuristics, together with statistical tools to facilitate the design of these heuristics in an open and collaborative framework.We define an heuristic to be any algorithm processing raw inputs to produce values relevant to the problem at hand. This purposely very general definition encompasses techniques spanning from simple signal processing to symbolic modeling or locally trained predictors. Since we assume high performance can only be achieved by combining hundreds of such heuristics, we propose to develop them collaboratively, in a way similar to the successful development process of open-source software or collaborative encyclopedia.We will assess the performance of that strategy on the control of an avatar in a realistic 3D simulator and on the control of a real robotic arm, and we aim at creating a generic software platform usable on alternative applications.Hence the key aspects of this proposal are to:- develop novel statistical techniques for prediction and goal-planning with a very large heterogeneous set of features,- develop statistical tools such as similarity measures in the space of features to help the design of very large sets of heuristics by many contributors,- assess the efficiency of this approach on a series of complex tasks in a realistic simulated 3D environment and with a real robot arm.The five partners of the consortium are from the fields of applied and theoretical statistical learning, reinforcement learning, artificial vision and robotics. Champ scientifique natural sciencescomputer and information sciencessoftwareengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsignal processingnatural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learningengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsnatural sciencescomputer and information sciencesartificial intelligenceheuristic programming Programme(s) FP7-ICT - Specific Programme "Cooperation": Information and communication technologies Thème(s) ICT-2009.2.1 - Cognitive Systems and Robotics Appel à propositions FP7-ICT-2009-4 Voir d’autres projets de cet appel Régime de financement CP - Collaborative project (generic) Coordinateur FONDATION DE L'INSTITUT DE RECHERCHE IDIAP Contribution de l’UE € 717 382,00 Adresse RUE MARCONI 19 1920 Martigny Suisse Voir sur la carte Région Schweiz/Suisse/Svizzera Région lémanique Valais / Wallis Type d’activité Research Organisations Contact administratif François Fleuret (Dr.) Liens Contacter l’organisation Opens in new window Coût total Aucune donnée Participants (6) 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 € 423 040,00 Adresse JUGOSLAVSKYCH PARTYZANU 1580/3 160 00 Praha Voir sur la carte Région Česko Praha Hlavní město Praha Type d’activité Higher or Secondary Education Establishments Contact administratif Igor Mraz (Mr.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée UNIVERSITAET POTSDAM Allemagne Contribution de l’UE € 327 334,00 Adresse AM NEUEN PALAIS 10 14469 Potsdam Voir sur la carte Région Brandenburg Brandenburg Potsdam Type d’activité Higher or Secondary Education Establishments Contact administratif Regina Gerber (Dr.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée FORSCHUNGSVERBUND BERLIN EV Participation terminée Allemagne Contribution de l’UE € 101 466,00 Adresse RUDOWER CHAUSSEE 17 12489 Berlin Voir sur la carte Région Berlin Berlin Berlin Type d’activité Research Organisations Contact administratif Margitta Teuchert (Ms.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS France Contribution de l’UE € 345 268,00 Adresse RUE MICHEL ANGE 3 75794 Paris Voir sur la carte Région Ile-de-France Ile-de-France Paris Type d’activité Research Organisations Contact administratif Gilles Pulvermuller (Mr.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE France Contribution de l’UE € 394 509,00 Adresse DOMAINE DE VOLUCEAU ROCQUENCOURT 78153 Le Chesnay Cedex Voir sur la carte Région Ile-de-France Ile-de-France Yvelines Type d’activité Research Organisations Contact administratif Mireille MOULIN (Ms.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE France Contribution de l’UE € 0,00 Adresse RUE DU DOCTEUR SCHWEITZER CS 60319 CENTRE PIERRE GUILLAUMAT 60203 Compiegne Cedex Voir sur la carte Région Hauts-de-France Picardie Oise Type d’activité Higher or Secondary Education Establishments Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée