Fabrizio Pittorino received the BSc (2011) and MSc (2013) degrees in Physics from Roma University “La Sapienza”, and the PhD degree in Physics from Parma University (2017), specializing during his studies in statistical physics and its applications to biological and artificial neural networks. After the PhD, he has been a Postdoctoral Researcher in the Computing Sciences department of Bocconi University (Milan), consolidating his background with approaches to statistical inference and empirical deep learning. Currently he is Assistant Professor at the Dipartimento di Elettronica, Informazione e Bioingegneria of Politecnico di Milano (Italy) working with the AI-Tech Research Lab.
His current research interests are focused on AI and in particular on artificial neural networks, both from the mathematical modelling and technological points of view.
His research blends theoretical tools and computational experiments in order to investigate foundational/algorithmic questions and design new technological solutions in deep learning. Active areas of research are the role of the loss function in the optimization landscape of neural networks and concept drift detection/adaptation in machine learning. Another area in which he is interested are the neuroscientifically-inspired alternatives to the backpropagation algorithm.