Projects

The laboratory is currently undergoing several internal collaborations with colleagues of the Computer Science Department, specifically with the Anacleto and OPTLab laboratories. The main external collaborations involve the following projects.

AISMA AI for Superconducting MAgnets

AISMA is a joint research group of the Computer Science and Physics Departments of the University of Milan, the Laboratory for Accelerators and Applied Superconductivity of the National Institute for Nuclear Physics, and the Department of Electrical and Information Technology Engineering of the Federico II University. Its activities are focused on the use of Machine Learning methods for the design and implementation of fault detection systems in superconducting materials.

MIABC Metodi di Intelligenza Artificiale per i Beni Culturali

MIABC (Artificial Intelligence Methods for Cultural Heritage) is a joint research group of the Department of Computer Science and Physics of the University of Milan, focused on the study of artificial intelligence techniques in the realm of Cultural Heritage, with special focus on the classification of ancient pottery in function of their chemical elements concentration [Zanaboni et al., 2022; Ruschioni et al., 2023; Malchiodi et al., 2025].

ML4LM Machine Learning for Legal Medicine

ML4LM is a joint research group of the University of Milan (Departments of Computer Science, Biomedical Sciences for Health, Oncology and Hemato-Oncology and Institute of Legal Medicine) and of the Vita-Salute San Raffaele University, devoted to develop statistical and machine learning methodologies tailored to the forensics context. Its scientific activities are focused on predicting the type of vehicle involved in a pedestrian struck [Casali et al., 2021] and in estimating the height of fatal falls [Blandino et al., 2024].

μLearn Machine learning for fuzzy sets

μLearn is a joint research group of the Computer Science Department of the University of Milan and the Electrical & Computer Engineering Department of the University of Alberta, whose aim is to design and implement machine learning algorithms for the induction of the membership functions of a fuzzy set [Malchiodi and Pedrycz, 2013]. These algorithms have been applied to the semantic Web [Malchiodi and Tettamanzi, 2018] and bioinformatics [Frasca and Malchiodi, 2017; Frasca and Malchiodi, 2016] realms, and extended to the simultaneous induction of several fuzzy sets [Cermenati et al., 2020] and to learning shadowed sets [Malchiodi and Zanaboni, 2019].

Possibilearn Machine learning for the Semantic Web

Possibilearn is a joint research group of the Computer Science Department of the University of Milan, the Computer Science, Signals and Systems laboratory of the Université Côte d'Azur and the National Institute for Research in Digital Science and Technology, devoted to discovering axioms within Semantic Web knowledge bases using learned fuzzy sets [Malchiodi and Tettamanzi, 2018], kernel-based regression [Malchiodi et al., 2018a] and dimensionality reduction techniques [Malchiodi et al., 2020].