Community Research and Development Information Service - CORDIS

FP7 MASH Logo

MASH

Project ID: 247022
Funded under

Massive Sets of Heuristics for Machine Learning

From 2010-01-01 to 2013-06-30, closed project | MASH Website

Project details

Total cost:

EUR 3 052 268

EU contribution:

EUR 2 308 999

Coordinated in:

Switzerland

Call for proposal:

FP7-ICT-2009-4See other projects for this call

Funding scheme:

CP - Collaborative project (generic)

Description

New tools for the collaborative development of very complex machine learning systems.
The <a href="http://mash-project.eu/" target="_blank">MASH</a> 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.

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.

Related information

Documents and Publications

Coordinator

FONDATION DE L'INSTITUT DE RECHERCHE IDIAP
Switzerland

EU contribution: EUR 717 382


RUE MARCONI 19
1920 MARTIGNY
Switzerland
Activity type: Research Organisations
Administrative contact: François Fleuret
Tel.: +41277217739
Fax: +41277217712
E-mail

Participants

CESKE VYSOKE UCENI TECHNICKE V PRAZE
Czech Republic

EU contribution: EUR 423 040


ZIKOVA 4
16636 PRAHA
Czech Republic
Activity type: Higher or Secondary Education Establishments
Administrative contact: Igor Mraz
Tel.: +420224352014
Fax: +420224357385
E-mail
UNIVERSITAET POTSDAM
Germany

EU contribution: EUR 327 334


AM NEUEN PALAIS 10
14469 POTSDAM
Germany
Activity type: Higher or Secondary Education Establishments
Administrative contact: Regina Gerber
Tel.: +493319771080
E-mail
FORSCHUNGSVERBUND BERLIN E.V.
Participation ended
Germany

EU contribution: EUR 101 466


Rudower Chaussee 17
12489 BERLIN
Germany
Activity type: Research Organisations
Administrative contact: Margitta Teuchert
Tel.: +49 30 20372 594
Fax: +49 30 2044975
E-mail
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE (CNRS)
France

EU contribution: EUR 345 268


Rue Michel -Ange 3
75794 PARIS
France
Activity type: Research Organisations
Administrative contact: Gilles Pulvermuller
Tel.: +33 3 20 12 58 07
Fax: +33 3 20 63 00 43
E-mail
INSTITUT NATIONAL DE RECHERCHE ENINFORMATIQUE ET AUTOMATIQUE
France

EU contribution: EUR 394 509


DOMAINE DE VOLUCEAU ROCQUENCOURT
78153 LE CHESNAY CEDEX
France
Activity type: Research Organisations
Administrative contact: Mireille MOULIN
Tel.: +33 1 7292 5964
Fax: +33 1 7292 5936
E-mail
UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE
France

EU contribution: EUR 0


Centre Benjamin Franklin, Rue Roger Couttolenc
60206 COMPIEGNE
France
Activity type: Higher or Secondary Education Establishments
Administrative contact: N/A N/A
Tel.: +00 0 000000
E-mail
Record Number: 93563 / Last updated on: 2017-04-20
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top