4 papers
An Explainable Failure Prediction Framework for Neural Networks in Radio Access Networks
Khaleda Papry, Francesco Spinnato, Marco Fiore +2
As 5G networks continue to evolve to deliver high speed, low latency, and reliable communications, ensuring uninterrupted service has become increasingly critical. While millimeter…
Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithms
Riccardo Guidotti, Martina Cinquini, Marta Marchiori Manerba +2
Interpretable-by-design models are crucial for fostering trust, accountability, and safe adoption of automated decision-making models in real-world applications. In this paper we f…
An Interpretable Data-Driven Unsupervised Approach for the Prevention of Forgotten Items
Luca Corbucci, Javier Alejandro Borges Legrottaglie, Francesco Spinnato +2
Accurately identifying items forgotten during a supermarket visit and providing clear, interpretable explanations for recommending them remains an underexplored problem within the…
MASCOTS: Model-Agnostic Symbolic COunterfactual explanations for Time Series
Dawid PÅudowski, Francesco Spinnato, Piotr WilczyÅski +4
Counterfactual explanations provide an intuitive way to understand model decisions by identifying minimal changes required to alter an outcome. However, applying counterfactual met…