MASH
Massive Sets of Heuristics for Machine Learning
| Coordinatore | FONDATION DE L'INSTITUT DE RECHERCHE IDIAP
Organization address
address: RUE MARCONI 19 contact info |
| 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
| # | ||||
|---|---|---|---|---|
| 1 |
FONDATION DE L'INSTITUT DE RECHERCHE IDIAP
Organization address
address: RUE MARCONI 19 contact info |
CH (MARTIGNY) | coordinator | 0.00 |
| 2 |
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE
Organization address
address: RUE MICHEL -ANGE contact info |
FR (PARIS) | participant | 0.00 |
| 3 |
CESKE VYSOKE UCENI TECHNICKE V PRAZE
Organization address
address: ZIKOVA contact info |
CZ (PRAHA) | participant | 0.00 |
| 4 |
INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE
Organization address
address: Domaine de Voluceau, Rocquencourt contact info |
FR (LE CHESNAY Cedex) | participant | 0.00 |
| 5 |
UNIVERSITAET POTSDAM
Organization address
address: AM NEUEN PALAIS contact info |
DE (POTSDAM) | participant | 0.00 |
| 6 |
UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE
Organization address
address: Centre Benjamin Franklin, Rue Roger Couttolenc contact info |
FR (COMPIEGNE) | participant | 0.00 |
Mappa
Word cloud
Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.
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.