SM-DeepResNet Statistical Mechanics of Deep Residual Networks in the Feature Learning Regime
- Coordinator
- Universita Degli Studi Di Parma, Italy
- Runs
- 1 October 2026 to 30 September 2029
- Status
- Running
- EU funding
- €397k
- Total cost
- —
- Partners
- 2 organisations in 2 countries
- Type
- Marie Skłodowska-Curie Action
- Grant agreement
- 101279927
What the project is doing
In the project's own words, from its summary on CORDIS.
Since their introduction a decade ago, neural networks with residual connections have come to dominate the field of artificial neural architectures thanks to their outstanding performance, and are nowadays the building blocks of most state-of-the-art, scalable AI systems. Nevertheless, despite their widespread use, relatively little is known about the quantitative mechanisms underlying feature learning in these architectures and how to improve their inference capabilities.
To this aim, ""Statistical Mechanics of Deep Residual Networks in the Feature Learning Regime"" (SM-DeepResNet) lays the groundwork to close this gap and achieve a broad theoretical understanding of residual learning. Leveraging recent successful applications of statistical mechanics to the study of deep fully connected architectures, SM-DeepResNet will contributes to: (i) building a novel statistical-mechanics-inspired framework to study deep residual nets in the feature learning regime, providing low-dimensional predictive models that theoretically describe their behavior through scaling limits
Topics
Who is involved
| Organisation | City | Country | Role |
|---|---|---|---|
| Universita Degli Studi Di Parma | Parma | Italy | Coordinator |
| Trustees of Princeton University | Princeton, Nj | United States | Associatedpartner |
Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI