CORDIS Project
Funding breakdown and partner intelligence are Premium
Sign in and upgrade to Premium for EU contribution totals, consortium analytics, OpenAlex research context, and AI summaries. · 0 consortium intelligence fields visible of 1
Start free • Cancel anytime • 14-day refund guarantee
The beyond2 project aims to enhance our understanding of how deep neural networks learn from complex data patterns. By analyzing learning dynamics and the role of high-order correlations, it seeks to bridge theoretical insights with practical applications in machine learning.
Deep neural networks (DNNs) have revolutionised how we learn from data.
Rather than requiring careful engineering and domain knowledge to extract features from raw data, DNNs learn the relevant features for a task automatically from data.
In particular, high-order correlations (HOCs) of the data are crucial for both the performance of DNNs and the type of features they learn.
However, existing theoretical frameworks cannot capture the impact of HOCs – they either study “lazy” regimes where DNNs…
SCUOLA INTERNAZIONALE SUPERIORE DI STUDI AVANZATI DI TRIESTE
Partner organizations (coordinator is shown above), with normalized type and CORDIS activity type. Guests see up to 4 partners.
Similar projects, consortium collaboration history, frequent partners, and OpenAlex research context.
Guests see up to 5 EuroSciVoc fields.
Guests see up to 5 topics.
Guests see up to 5 keywords.
