Advances in Data Science Seminar: Certified learning, or learning for verification?
Time: 14:00 - 15:00
Leading researchers present their recent advances in Machine Learning and Computational Statistics. This is an online seminar from the University of Manchester's Institute for Data Science & Artificial Intelligence.
We will be video recording all of the talks in this year's Advances in Data Science seminar series. If you have registered for any of the seminars and oppose to us doing so, please notify us immediately.
Speaker: Prof Alessandro Abate (University of Oxford)
Title: Certified learning, or learning for verification?
We are witnessing an inter-disciplinary convergence between areas underpinned by model-based reasoning (such as formal verification or control theory) and by data-driven learning (ML and AI). Original work across these areas is strongly justified by scientific endeavours and industrial applications, where access to information-rich data has to be traded off with a demand for safety criticality: cyber-physical systems are exemplar applications.
In this talk, I will report on ongoing initiatives within my group in this cross-disciplinary domain. According to the dual perspective in the title of this talk, I will sketch, on the one hand, results where formal verification can provide certificates to learning algorithms, and on the other hand, results where learning can bolster formal verification and control synthesis objectives.
Alessandro Abate is Professor of Verification and Control in the Department of Computer Science at the University of Oxford. Earlier, he did research at Stanford University and at SRI International, and was an Assistant Professor at the Delft Center for Systems and Control, TU Delft. He received a Laurea degree from the University of Padova and MS/PhD at UC Berkeley.
Alessandro's research interests lie on the analysis, verification, and optimal control of heterogeneous and complex dynamical models -- in particular of stochastic hybrid systems -- and in their applications in cyber-physical systems (particularly involving energy networks) and in the life sciences (systems biology). He is interested in a principled integration of model-based mathematical techniques with data-driven learning algorithms.