Skip to content

Free University of Bozen-Bolzano

Toggle the language menu. Current language: EN

Data-driven Artificial Intelligence (D2AI)


The Data-Driven Artificial Intelligence group is devoted to handling Big Data, using advanced data science, machine learning and database technologies, to tackle a variety of grand challenges in AI and its use in mission-critical domains such as medicine, biology, climate, energy, finance, industry , and smart living. 

Covered Topics

  • Advanced machine learning (ML): development of new methods and techniques for the creation of models based on both big and small data, including deep learning, multi-task learning, transfer learning, reinforcement learning, explainable & interpretable ML, neural architecture search, frequent subgraph mining, efficient classification, regression and clustering. 
  • Computer vision: use of advanced machine learning to address complex computer vision problems, such as detection and tracking, pose estimation, and activity recognition in video, anomaly detection, classification and segmentation in image and volumetric data, reconstruction of geometry and appearance of objects from sets of images. 
  • Data management and analytics: development of efficient and scalable database technologies and algorithms for different types of complex multi-dimensional data, including temporal data, data series and graphs, in different application scenarios such as industrial automation, biomedicine, and food production. 
  • Machine learning in embedded systems: development of new methodologies to miniaturise and accelerate machine learning algorithms, to enable these in mobile devices, considering scenarios such as intelligent Internet of Things, smart sensing, and embedded vision.  
  • Intelligent networks: data-driven communication protocols, networks, and systems for dependable data exchange across domains using AI models, including IoT networks, vehicular networks, sensor networks, and hybrid networks for smart  systems. 
  • Mathematical foundation of D2AI: physics-informed machine learning, model order reduction, statistical techniques, linear algebra methods, optimization algorithms, data compression techniques, graph theory and network analysis, high-performance and GPU computing. 
  • Multidisciplinary data-driven grand challenges: applications of machine learning algorithms and data science methods to scientific and industrial domains, such as medicine, neuroscience, bioinformatics, computational biology, climate, energy, finance, economics, food security, industry automation, digital marketing, computer security, the public administration, and the mega-cities. 

Associated laboratories

Vision Computing and Learning 
The group conducts research in the field of computer vision and machine learning. We build on advances in modern machine learning to develop novel methods for image and video understanding with real use cases in mind.

Database systems
The Database Systems Group aims at enhancing current DB technologies to support complex query processing and data analysis, in particular for temporal and spatial data. The research is driven by real-world applications in different areas. 

Machine Learning and Data Science
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.

Intelligent Networks and Systems
This research group is dedicated to developing and advancing intelligent, networked systems. We are at the forefront of influential research in embedded & cooperative machine learning, IoT data analytics, smart sensing, and intelligent networks. We have a track record of projects in which AI is used to address grand challenges in climate, energy, medicine, and complex smart systems.

Covision Lab
This lab is a solution provider in computer vision and machine learning, through state-of-the-art research, industry applications, and spin-off start-ups.