CORDIS - Forschungsergebnisse der EU
CORDIS

Reliable and cost-effective large scale machine learning

Projektbeschreibung

Antrieb der Gehirne hinter der Maschine

Algorithmen für maschinelles Lernen sind die Gehirne, die es Maschinen ermöglichen, aus Daten zu lernen und Verbesserungen automatisch und ohne menschliches Zutun vorzunehmen. Maschinen imitieren, passen sich an und bieten Lösungen für viele Branchen – vom Sicherheitssektor bis zum Gesundheitswesen und vom Fertigungssektor bis zum Marketingbereich. Da die Menge an Daten jedoch exponentiell zunimmt, muss das maschinelle Lernen in Bezug auf Kosteneffizienz und Zuverlässigkeit Schritt halten. Vor diesem Hintergrund wird das EU-finanzierte Projekt REAL das klassische maschinelle Lernen erweitern, um Algorithmen bereitzustellen, die mit möglichst geringen Rechenressourcen zuverlässige Vorhersagen gewährleisten können. Dies soll schließlich an wichtigen Richtwerten aus den Bereichen maschinelles Sehen, Verarbeitung natürlicher Sprache und Bioinformatik erprobt werden.

Ziel

In the last decade, machine learning (ML) has become a fundamental tool with a growing impact in many disciplines, from science to industry. However, nowadays, the scenario is changing: data are exponentially growing compared to the computational resources (post Moore's law era), and ML algorithms are becoming crucial building blocks in complex systems for decision making, engineering, science. Current machine learning is not suitable for the new scenario, both from a theoretical and a practical viewpoint: (a) the lack of cost-effectiveness of the algorithms impacts directly the economic/energetic costs of large scale ML, making it barely affordable by universities or research institutes; (b) the lack of reliability of the predictions affects critically the safety of the systems where ML is employed. To deal with the challenges posed by the new scenario, REAL will lay the foundations of a solid theoretical and algorithmic framework for reliable and cost-effective large scale machine learning on modern computational architectures. In particular, REAL will extend the classical ML framework to provide algorithms with two additional guarantees: (a) the predictions will be reliable, i.e. endowed with explicit bounds on their uncertainty guaranteed by the theory; (b) the algorithms will be cost-effective, i.e. they will be naturally adaptive to the new architectures and will provably achieve the desired reliability and accuracy level, by using minimum possible computational resources. The algorithms resulting from REAL will be released as open-source libraries for distributed and multi-GPU settings, and their effectiveness will be extensively tested on key benchmarks from computer vision, natural language processing, audio processing, and bioinformatics. The methods and the techniques developed in this project will help machine learning to take the next step and become a safe, effective, and fundamental tool in science and engineering for large scale data problems.

Finanzierungsplan

ERC-STG - Starting Grant

Gastgebende Einrichtung

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE
Netto-EU-Beitrag
€ 1 498 830,00
Adresse
DOMAINE DE VOLUCEAU ROCQUENCOURT
78153 Le Chesnay Cedex
Frankreich

Auf der Karte ansehen

Region
Ile-de-France Ile-de-France Yvelines
Aktivitätstyp
Research Organisations
Links
Gesamtkosten
€ 1 498 830,00

Begünstigte (1)