Opis projektu 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. Pokaż cel projektu Ukryj cel projektu 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. Dziedzina nauki 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 Program(-y) FP7-ICT - Specific Programme "Cooperation": Information and communication technologies Temat(-y) ICT-2009.2.1 - Cognitive Systems and Robotics Zaproszenie do składania wniosków FP7-ICT-2009-4 Zobacz inne projekty w ramach tego zaproszenia System finansowania CP - Collaborative project (generic) Koordynator FONDATION DE L'INSTITUT DE RECHERCHE IDIAP Wkład UE € 717 382,00 Adres RUE MARCONI 19 1920 Martigny Szwajcaria Zobacz na mapie Region Schweiz/Suisse/Svizzera Région lémanique Valais / Wallis Rodzaj działalności Research Organisations Kontakt administracyjny François Fleuret (Dr.) Linki Kontakt z organizacją Opens in new window Koszt całkowity Brak danych Uczestnicy (6) Sortuj alfabetycznie Sortuj według wkładu UE Rozwiń wszystko Zwiń wszystko CESKE VYSOKE UCENI TECHNICKE V PRAZE Czechy Wkład UE € 423 040,00 Adres JUGOSLAVSKYCH PARTYZANU 1580/3 160 00 Praha Zobacz na mapie Region Česko Praha Hlavní město Praha Rodzaj działalności Higher or Secondary Education Establishments Kontakt administracyjny Igor Mraz (Mr.) Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych UNIVERSITAET POTSDAM Niemcy Wkład UE € 327 334,00 Adres AM NEUEN PALAIS 10 14469 Potsdam Zobacz na mapie Region Brandenburg Brandenburg Potsdam Rodzaj działalności Higher or Secondary Education Establishments Kontakt administracyjny Regina Gerber (Dr.) Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych FORSCHUNGSVERBUND BERLIN EV Zakończenie uczestnictwa Niemcy Wkład UE € 101 466,00 Adres RUDOWER CHAUSSEE 17 12489 Berlin Zobacz na mapie Region Berlin Berlin Berlin Rodzaj działalności Research Organisations Kontakt administracyjny Margitta Teuchert (Ms.) Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS Francja Wkład UE € 345 268,00 Adres RUE MICHEL ANGE 3 75794 Paris Zobacz na mapie Region Ile-de-France Ile-de-France Paris Rodzaj działalności Research Organisations Kontakt administracyjny Gilles Pulvermuller (Mr.) Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE Francja Wkład UE € 394 509,00 Adres DOMAINE DE VOLUCEAU ROCQUENCOURT 78153 Le Chesnay Cedex Zobacz na mapie Region Ile-de-France Ile-de-France Yvelines Rodzaj działalności Research Organisations Kontakt administracyjny Mireille MOULIN (Ms.) Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE Francja Wkład UE € 0,00 Adres RUE DU DOCTEUR SCHWEITZER CS 60319 CENTRE PIERRE GUILLAUMAT 60203 Compiegne Cedex Zobacz na mapie Region Hauts-de-France Picardie Oise Rodzaj działalności Higher or Secondary Education Establishments Linki Kontakt z organizacją Opens in new window Strona internetowa Opens in new window Koszt całkowity Brak danych