MASH

Massive Sets of Heuristics for Machine Learning

 Coordinatore FONDATION DE L'INSTITUT DE RECHERCHE IDIAP 

 Organization address address: RUE MARCONI 19
city: MARTIGNY
postcode: 1920

contact info
Titolo: Dr.
Nome: François
Cognome: Fleuret
Email: send email
Telefono: 41277217739
Fax: 41277217712

 Nazionalità Coordinatore Switzerland [CH]
 Totale costo 3˙052˙268 €
 EC contributo 2˙308˙999 €
 Programma FP7-ICT
Specific Programme "Cooperation": Information and communication technologies
 Code Call FP7-ICT-2009-4
 Funding Scheme CP
 Anno di inizio 2010
 Periodo (anno-mese-giorno) 2010-01-01   -   2013-06-30

 Partecipanti

# participant  country  role  EC contrib. [€] 
1    FONDATION DE L'INSTITUT DE RECHERCHE IDIAP

 Organization address address: RUE MARCONI 19
city: MARTIGNY
postcode: 1920

contact info
Titolo: Dr.
Nome: François
Cognome: Fleuret
Email: send email
Telefono: 41277217739
Fax: 41277217712

CH (MARTIGNY) coordinator 0.00
2    CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE

 Organization address address: RUE MICHEL -ANGE
city: PARIS
postcode: 75794

contact info
Titolo: Mr.
Nome: Gilles
Cognome: Pulvermuller
Email: send email
Telefono: +33 3 20 12 58 07
Fax: +33 3 20 63 00 43

FR (PARIS) participant 0.00
3    CESKE VYSOKE UCENI TECHNICKE V PRAZE

 Organization address address: ZIKOVA
city: PRAHA
postcode: 166 36

contact info
Titolo: Mr.
Nome: Igor
Cognome: Mraz
Email: send email
Telefono: 420224000000
Fax: 420224000000

CZ (PRAHA) participant 0.00
4    INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE

 Organization address address: Domaine de Voluceau, Rocquencourt
city: LE CHESNAY Cedex
postcode: 78153

contact info
Titolo: Ms.
Nome: Mireille
Cognome: MOULIN
Email: send email
Telefono: +33 1 7292 5964
Fax: +33 1 7292 5936

FR (LE CHESNAY Cedex) participant 0.00
5    UNIVERSITAET POTSDAM

 Organization address address: AM NEUEN PALAIS
city: POTSDAM
postcode: 14469

contact info
Titolo: Dr.
Nome: Regina
Cognome: Gerber
Email: send email
Telefono: 493320000000

DE (POTSDAM) participant 0.00
6    UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE

 Organization address address: Centre Benjamin Franklin, Rue Roger Couttolenc
city: COMPIEGNE
postcode: 60206

contact info
Nome: N/A
Cognome: N/A
Email: send email
Telefono: +00 0 000000

FR (COMPIEGNE) participant 0.00

Mappa


 Word cloud

Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.

software    techniques    realistic    performance    arm    tools    real    heuristics    learning    collaborative    statistical   

 Obiettivo del progetto (Objective)

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.

Altri progetti dello stesso programma (FP7-ICT)

OPTIMIS (2010)

Optimized Infrastructure Services

Read More  

EURO-DOTS-2 (2013)

European Doctoral Training Support in Micro/Nano-electronics

Read More  

FI-STAR (2013)

Future Internet Social and Technological Alignment Research

Read More