Learning with Multiple Representations – LEMUR

Project data

Funding Entity: European Commission

Call: Marie Skłodowska-Curie Actions (MSCA)

Coordinator: UNIVERSITAET PADERBORN Germany

UNISI Principal Investigator: Marco Gori

Department: Dipartimento di Ingegneria dell’informazione e scienze matematiche

Start date: 1 January 2023

End date: 31 December 2026

 

Description

Funded by the Marie Skłodowska-Curie Actions programme, the LEMUR project will develop the theoretical foundations and a first set of algorithms for a novel branch of machine learning (ML) called learning with multiple representations (LMR). These LMR algorithms will allow flexible representations (simple and fair) with diverse target functions (environmental and social impact) to ensure they are in line with the Green Charter and trustworthy AI criteria by design. The project will focus on learning with weak supervision as it addresses one of the major flaws of modern ML approaches. LEMUR will provide 10 experts with highly interdisciplinary and intersectoral training to implement the third and subsequent waves of AI in Europe.

Source: Cordis

Project website

 

This project has received funding from the European Union’s Horizon 2020 programme under Grant agreement ID: 101073307