4 citations · 4 across the 4 of their papers we have counts for
5 papers
Gradient Surgery for Physics-Informed Neural Networks
Thomas Borsani, Giuseppe Di Fatta
Physics-Informed Neural Networks (PINNs) are trained by optimising a composite objective that combines data fitting with physics-based constraints, typically resulting in a highly…
Operator-Theoretic Generalization Bounds for Multitask Deep Learning
Mahdi Mohammadigohari, Thomas Borsani, Giuseppe Di Fatta
We develop operator-theoretic generalization bounds for deep multi-output function classes by representing network layers as Koopman composition operators on vector-valued reproduc…
High-quality data augmentation for code comment classification
Thomas Borsani, Andrea Rosani, Giuseppe Di Fatta
Code comments serve a crucial role in software development for documenting functionality, clarifying design choices, and assisting with issue tracking. They capture developers' ins…
Gradient Similarity Surgery in Multi-Task Deep Learning
Thomas Borsani, Andrea Rosani, Giuseppe Nicosia +1
The multi-task learning () paradigm aims to simultaneously learn multiple tasks within a single model capturing higher-level, more general hidden patterns that are shared by t…
Optimizing Deep Learning Models to Address Class Imbalance in Code Comment Classification
Moritz Mock, Thomas Borsani, Giuseppe Di Fatta +1
Developers rely on code comments to document their work, track issues, and understand the source code. As such, comments provide valuable insights into developers' understanding of…