Alessandro Betti

Assistant Professor

Google ScholarORCIDLink

About me

I am an Assistant Professor (RTD-A) of Computer Science within the SySMA research unit of IMT Lucca.  Previously I was a postdoctoral researcher at the Université Côte d’Azur (Nice, France) as member of the Maasai team and at Università di Siena at the Siena Artificial Intelligence Lab (SAILab). I recived my Ph.D. in Computer Science (Smart Computing) from the Universities of Florence, Pisa, and Siena in 2020.

Research Activities

My research interests lie in Machine Learning and Artificial Intelligence. Specifically, I focus on studying Machine Learning algorithms for processing data streams that exhibit dynamical properties. My research encompasses both theoretical exploration and practical applications in Computer Vision. From the theoretical standpoint, I have proposed and developed a framework rooted in Calculus of Variations for interpreting laws of learning. In the visual domain, I have applied these ideas to develop learning agents that utilize deep architectures to extract features that consider motion-induced regularities. Currently, I am working on formulating online continual learning in a principled manner, aiming to investigate the relationship between learning problems over time and optimal control.

In addition to these activities, I have recently studies a singular transport equation that arises as a formal limit of the discrete open mancala game.

Prior to my PhD, I obtained a Master’s Degree in Theoretical Physics from the University of Pisa. During my master’s studies, I focused on investigating the large-N CP(N-1) sigma model on a finite interval in connection with solitonic solutions, which are believed to be relevant for the problem of confinement in QCD.


Selected Publications

See my Google Scholar profile for a full list of publications.