From the 6 of 108 papers with an AI index.
37 citations
- Federico Giannini5 · h 5
- Emanuele Della Valle3 profiles4 · h 33
- Stefano Longhi3 profiles4 · h 7
- Valeria Russo2 profiles4 · h 4
- C. Casari3 · h 42
- C. Pillet3 · h 33
- E. Santos3 profiles3 · h 53
- Giacomo Ziffer3 · h 5
- Himanshu Gupta3 profiles3 · h 10
- Micah Carroll2 profiles3 · h 15
- Michael Kirchhof2 profiles3 · h 10
- M. Zavrtanik2 profiles3 · h 53
- Centre National de la Recherche ScientifiqueFR9 papers
- University of MilanIT8 papers
- ETH ZurichCH6 papers
- Institute for Cross-Disciplinary Physics and Complex SystemsES5 papers
- University of PaduaIT5 papers
- Beihang UniversityCN4 papers
- New York UniversityUS4 papers
- Sorbonne UniversitéFR4 papers
- Université Paris-SaclayFR4 papers
- University of PalermoIT4 papers
- Astronomical Observatory of RomeIT3 papers
- Case Western Reserve UniversityUS3 papers
13 papers · 1 filter
Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics
Eugenio Varetti, Matteo Torzoni, Marco Tezzele +1
This work shows how adaptivity can enhance value realization of digital twins in civil engineering. We focus on adapting the state transition models within digital twins represente…
Probing Dec-POMDP Reasoning in Cooperative MARL
Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni +2
Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stem…
Architecture-Aware Minimization (AM): How to Find Flat Minima in Neural Architecture Search
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neura…
MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
Federico Giannini, Emanuele Della Valle
Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to conti…
Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
Federico Giannini, Sandro D'Andrea, Emanuele Della Valle
Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning…
cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series
Federico Giannini, Giacomo Ziffer, Emanuele Della Valle
Dealing with an unbounded data stream involves overcoming the assumption that data is identically distributed and independent. A data stream can, in fact, exhibit temporal dependen…