European Commission logo
italiano italiano
CORDIS - Risultati della ricerca dell’UE
CORDIS

Learning with Multiple Representations

Descrizione del progetto

Le fondamenta teoriche di una nuova branca dell’apprendimento automatico

Il progetto LEMUR, finanziato dal programma di azioni Marie Skłodowska-Curie, svilupperà le fondamenta teoriche e una prima serie di algoritmi per una nuova branca dell’apprendimento automatico (AA) chiamata apprendimento con rappresentazioni multiple (LMR, learning with multiple representations). Questi algoritmi per LMR consentiranno di fornire rappresentazioni flessibili (semplici ed eque) con diverse funzioni bersaglio (impatto ambientale e sociale) allo scopo di garantirne la coerenza con la Carta della Terra e i criteri di affidabilità dell’IA sin dalla progettazione. Il progetto si incentrerà sull’apprendimento con supervisione debole, affrontando uno dei maggiori difetti dei moderni approcci di AA. LEMUR fornirà 10 esperti con elevata formazione interdisciplinare e intersettoriale per implementare la terza ondata di IA in Europa, nonché le successive.

Obiettivo

Machine learning methods operate on formal representations of the data at hand and the models or patterns induced from the data. They also assume a suitable formalization of the learning task itself (e.g. as a classification problem), including a specification of the objective in terms of a suitable performance metric, and sometimes other criteria the induced model is supposed to meet. Different representations or problem formalizations may be more or less appropriate to address a particular task and to deal with the type of training information available. The goal of LEMUR is to create a novel branch of machine learning we call Learning with Multiple Representations. We aim to develop the theoretical foundations and a first set of algorithms for this new paradigma. Moreover, corresponding applications are to demonstrate the usefulness of the new family of approaches. We regard LEMUR as very timely, as LMR algorithms will allow to flexible representations (e.g. suitable for explainability, fairness) with diverse target functions (e.g. incorporating environmental or even social impact) so as to make the induced models abide by the Green Charter and trustworthy AI criteria by design. We will focus on learning with weak supervision because it addresses one of the major flaws of modern ML approaches, i.e. their data hunger, by means of weaker sources of labelling for training data. The outcome of the DN will be a set of 10 experts trained to implement the third and subsequent waves of AI in Europe. The highly interdisciplinary and intersectoral context in which they will be trained will provide them with research-related and transferable competences relevant to successful careers in central AI areas.

Coordinatore

UNIVERSITAET PADERBORN
Contribution nette de l'UE
€ 260 539,20
Indirizzo
WARBURGER STRASSE 100
33098 Paderborn
Germania

Mostra sulla mappa

Regione
Nordrhein-Westfalen Detmold Paderborn
Tipo di attività
Higher or Secondary Education Establishments
Collegamenti
Costo totale
Nessun dato

Partecipanti (9)

Partner (10)