BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Machine Learning-enhanced Monitoring - Andrea Brunello and
  Nicola Saccomanno\, University of Udine
DTSTART:20240222T170000Z
DTEND:20240222T180000Z
UID:TALK212668@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:This talk presents a novel framework aimed at improving failur
 e detection in critical computing systems\, where high reliability and saf
 ety are essential. It merges machine learning's predictive power with the 
 reliability of formal verification methods\, using data streams from syste
 m operations\, like telemetry\, for early failure detection. The approach 
 overcomes traditional verification challenges\, such as specifying all pro
 perties of interest and fully modeling systems\, by employing a lightweigh
 t runtime verification technique called monitoring\, which bypasses the ne
 ed for explicit model specifications. The integration of machine learning 
 allows for the direct identification of failure patterns from system trace
 s\, represented as logical formulas\, enabling effective real-time system 
 verification and providing natural interpretability. The seminar will expl
 ore the framework's development\, from its conceptual basis to its prototy
 pe and potential extensions\, while underscoring its implications for cutt
 ing-edge interdisciplinary research.\n\nBio 1: "Andrea Brunello":https://w
 ww.andreabrunello.com/ got his PhD in Computer Science in 2020 from the Un
 iversity of Udine (Italy). He is now an Assistant Professor at the Humanit
 ies Department of the same University. His main research interests are in 
 data modelling\, applied machine learning and on the integration between l
 earning and formal methods. \n\nBio 2: "Nicola Saccomanno":http://users.di
 mi.uniud.it/~nicola.saccomanno is a Postdoc at the Department of Mathemati
 cs\, Computer Science\, and Physics of the University of Udine (Italy)\, w
 here he got his PhD in 2023. His main research interests are in artificial
  intelligence\, specifically symbolic and sub-symbolic integration\, and a
 pplied machine learning\, focusing on indoor positioning and healthcare do
 mains.\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR