This research group is dedicated to developing and advancing data-driven algorithms and applications. Through a combination of theoretical research and practical implementations, the group strive to push the boundaries of machine learning to discover novel solutions and drive meaningful impact.

Research topics

We study the theory and practice of machine learning and its applications to real‑world problems. Our group advances reliable and reproducible ML, with an emphasis on transparent methodology, efficient computation, and open science.

The main research topics are:

• Supervised, Unsupervised and Reinforcement Learning
• Classic ML methods (Clustering, Classification, Regression, Bayesian methods, Time-series and Forecasting, Association Rules)
• Deep Learning, Multi-task Deep Learning
• Generative AI
• Mathematical foundation of ML
• Fair, Trustworthy and Robust ML, Explainable AI
• Bioinformatics, Medical Informatics (Alzheimer's and Neurodegenerative diseases)
• Data Science tools, KNIME
• Data-driven scientific and industrial applications

Equipment and technologies

Main projects

AI4SWEng - EU Project  (2024-2028)

AI Engineering Suite to support Agile Efficient Software Engineering.

AI4SWEng represents an excellent chemistry of 15 Partners including experts and practitioners in Model-Drive Software Engineering and AI Engineering (particularly LLMs) from across Europe with four use-cases from Software Development, Healthcare, Cyber-Physical System involving multi-architectural and resource-constrained systems and Next Generation Battery Management in EVs. The AI4SWEng mission is to significantly contribute to the transformation of agile software development into a sector turbocharged for design-by-contact high efficiency, reliability, and security-privacy compliant delivery. This is to exploit advanced AI-powered software development support to deliver high-quality reliable fast time-to-market solutions that are socially responsible, scalable, sustainable and lend themselves to audible ethical and regulatory compliance.

AI4SWEng has received funding from the European Union Horizon Europe research and innovation programme under grant agreement number 101189909.

IRIS_MoDECT - call ID2025 (2025-2027)

Integrating Remote Sensing and Molecular Diagnostics for Early Detection and Comparative Analysis of targeted Colletotrichum Species in South Tyrol Apple Orchards

South Tyrol’s apple industry faces increasing losses caused by Colletotrichum pathogens, which remain difficult to detect early with traditional visual, molecular, or remote-sensing methods used in isolation. This project develops an integrated, data-driven early-detection and prediction system by combining spore-trap molecular data, remote-sensing vegetation indices, and field observations. These multimodal inputs will be used to train machine learning models capable of predicting postharvest disease risk from preharvest pathogen pressure, enabling proactive interventions and precision disease management. The approach will validate remote sensing against molecular ground-truth data, providing growers with scalable ML-based forecasting tools to mitigate crop loss and support sustainable orchard management.

European Digital Innovation Hub (EDIH) on AI (2025)

...

AI Lab (2024-2025)

...

Multi-task Deep Learning (MTDL) (2023-2025)

...

5VREAL - MIMIT (2024)

In collaboration with the vision group, 5vReal focuses on developing real-time multimodal perception and AI-driven interaction systems for augmented and virtual reality environments. The project integrates computer vision, haptic feedback, and spatial computing to create immersive and responsive human-machine experiences. It explores advanced sensing, signal processing, and machine learning techniques to support natural interaction, realistic feedback, and collaborative intelligence across physical and virtual spaces.

People