معرفی
Alessandro Betti is an Assistant Professor of Computer Science at IMT Lucca within the SySMA research unit. Previously, he held postdoctoral positions at Université Côte d’Azur (Maasai team) and Università di Siena (Siena Artificial Intelligence Lab/SAILab). He earned his Ph.D. in Computer Science (Smart Computing) from the Universities of Florence, Pisa, and Siena in 2020, and a Master’s in Theoretical Physics from the University of Pisa, focusing on large-N CP(N-1) sigma models and solitonic solutions related to QCD confinement.
His research integrates theoretical foundations of machine learning with practical applications in computer vision. Key areas include data stream processing, online continual learning, and motion-invariant visual feature extraction using deep architectures. Current work explores optimal control principles for learning dynamics and formalizes a transport equation derived from discrete mancala games. He co-authored two books: Machine Learning: A Constraint-Based Approach (2023) and Deep Learning to See (2022), both foundational texts in their fields.
His publications span journals like Neurocomputing and Frontiers in Artificial Intelligence, with contributions to conferences such as NeurIPS and AAAI. Research highlights include developing variational calculus frameworks for learning laws, neural time-reversed Riccati equations, and foveated neural computation models inspired by biological vision systems.
Betti collaborates with institutions like SAILab and Maasai, focusing on interdisciplinary projects blending physics-inspired mathematics with AI. His work bridges theoretical rigor and applied challenges in dynamic, real-world data environments.
