16 citations · 43 across the 12 of their papers we have counts for
13 papers
Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model
Fabio Michele Russo, Carlo Metta, Anna Monreale +2
As predictive machine learning models become increasingly adopted and advanced, their role has evolved from merely predicting outcomes to actively shaping them. This evolution has…
Achieving Predictive Precision: Leveraging LSTM and Pseudo Labeling for Volvo's Discovery Challenge at ECML-PKDD 2024
Carlo Metta, Marco Gregnanin, Andrea Papini +5
This paper presents the second-place methodology in the Volvo Discovery Challenge at ECML-PKDD 2024, where we used Long Short-Term Memory networks and pseudo-labeling to predict ma…
Volvo Discovery Challenge at ECML-PKDD 2024
Mahmoud Rahat, Peyman Sheikholharam Mashhadi, Sławomir Nowaczyk +6
This paper presents an overview of the Volvo Discovery Challenge, held during the ECML-PKDD 2024 conference. The challenge's goal was to predict the failure risk of an anonymized c…
A Systematization of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning
Flora Angileri, Giulia Lombardi, Andrea Fois +9
In 2021, Adam Zsolt Wagner proposed an approach to disprove conjectures in graph theory using Reinforcement Learning (RL). Wagner's idea can be framed as follows: consider a conjec…
GloNets: Globally Connected Neural Networks
Antonio Di Cecco, Carlo Metta, Marco Fantozzi +2
Deep learning architectures suffer from depth-related performance degradation, limiting the effective depth of neural networks. Approaches like ResNet are able to mitigate this, bu…
Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling
Carlo Metta, Riccardo Guidotti, Yuan Yin +2
Explainable AI consists in developing mechanisms allowing for an interaction between decision systems and humans by making the decisions of the formers understandable. This is part…
Increasing biases can be more efficient than increasing weights
Carlo Metta, Marco Fantozzi, Andrea Papini +7
We introduce a novel computational unit for neural networks that features multiple biases, challenging the traditional perceptron structure. This unit emphasizes the importance of…
Artificial intelligence and renegotiation of commercial lease contracts affected by pandemic-related contingencies from Covid-19. The project A.I.A.Co
Maurizio Parton, Marco Angelone, Carlo Metta +4
This paper aims to investigate the possibility of using artificial intelligence (AI) to resolve the legal issues raised by the Covid-19 emergency about the fate of continuing execu…
Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?
Luca Pasqualini, Gianluca Amato, Marco Fantozzi +5
In the last years, the DeepMind algorithm AlphaZero has become the state of the art to efficiently tackle perfect information two-player zero-sum games with a win/lose outcome. How…
Explainable Deep Image Classifiers for Skin Lesion Diagnosis
Carlo Metta, Andrea Beretta, Riccardo Guidotti +4
A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificia…
Stationary solutions for dyadic mixed model of the Euler equation. A complete spectrum
Carlo Metta
Dyadic models of the Euler equations were introduced as toy models to study the behaviour of an inviscid fluid in turbulence theory. In 1974 Novikov proposed a generalized mixed dy…
SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)
Francesco Morandin, Gianluca Amato, Marco Fantozzi +3
We develop a new model that can be applied to any perfect information two-player zero-sum game to target a high score, and thus a perfect play. We integrate this model into the Mon…
SAI, a Sensible Artificial Intelligence that plays Go
Francesco Morandin, Gianluca Amato, Rosa Gini +3
We propose a multiple-komi modification of the AlphaGo Zero/Leela Zero paradigm. The winrate as a function of the komi is modeled with a two-parameters sigmoid function, so that th…