In this seminar I will present recent work on the use of statistical learning tools for the analysis of stochastic dynamic model of complex systems. Statistical learning offers powerful tools to manage uncertainty, particularly in model parameters. Statistical learning methods, combined with model simulations, can be used to estimate efficiently the probability of observing a given behaviour as a function of model parameters. This can be turned into a jackknife method to perform several tasks: optimise likelihoods efficiently, doing parameter synthesis, design, and control. At the same time, statistical learning provides novel ways to look into model abstraction, something we called statistical correction maps. In this talk, I will give an overview of these ideas, focussing on some aspects with more detail.
Luca Bortolussi is an Associate Professor (since 2015) in Computer Science at the Department of Mathematics and Geosciences, University of Trieste and he is an associate researcher at ISTI-CNR in Pisa, Italy.
From June 2014 to May 2015, he was a guest professor at the department of Computer Science of the University of Saarland in Saarbruecken, Germany and previously an assistant professor of Computer Science at the Department of Mathematics and Geosciences of the University of Trieste, Italy. He graduated in Mathematics at the University of Trieste in 2003 and he got his PhD in Computer Science at the University of Udine in 2007. Until 2015, he was an honorary fellow of the School of Informatics of the University of Edinburgh, where he spent a sabbatical year in 2012. His research interests focus on quantitative formal methods, modelling and simulation and machine learning, with applications in computational biology and smart systems.
This talk is organized by the Cyber-Physical Systems Group at the Institute of Computer Engineering. It is a part of Erasmus Mundus Scholar within the European Master's Program in Computational Logic at TU Wien, Austria.